Showing 1–50 of 1,141 results for author: Xu, B

Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs

Authors: Binxing Xu, Hao Gu, Lujun Li, Hao Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Xintong Yang, Chao Li, Sirui Han, Yike Guo

Abstract: Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and error accumulation across layers. To address these issues, we present Bit-by-Bit, a progressive QAT framework with outlier channel splitting. Our approach integrate… ▽ More Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and error accumulation across layers. To address these issues, we present Bit-by-Bit, a progressive QAT framework with outlier channel splitting. Our approach integrates three key components: (1) block-wise progressive training that reduces precision stage by stage, ensuring stable initialization for low-bit optimization; (2) nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm, allowing a single model to support multiple bit-widths without retraining; (3) rounding-aware outlier channel splitting, which mitigates quantization error while acting as an identity transform that preserves the quantized outputs. Furthermore, we follow microscaling groups with E4M3 scales, capturing dynamic activation ranges in alignment with OCP/NVIDIA standards. To address the lack of efficient 2-bit kernels, we developed custom operators for both W2A2 and W2A16 configurations, achieving up to 11$\times$ speedup over BF16. Under W2A2 settings, Bit-by-Bit significantly outperforms baselines like BitDistiller and EfficientQAT on both Llama2/3, achieving a loss of only 2.25 WikiText2 PPL compared to full-precision models. △ Less

Submitted 9 April, 2026; originally announced April 2026.

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch

Authors: Hao Gu, Hao Wang, Jiacheng Liu, Lujun Li, Qiyuan Zhu, Bei Liu, Binxing Xu, Lei Wang, Xintong Yang, Sida Lin, Sirui Han, Yike Guo

Abstract: Large language model (LLM) reinforcement learning (RL) pipelines are often bottlenecked by rollout generation, making end-to-end training slow. Recent work mitigates this by running rollouts with quantization to accelerate decoding, which is the most expensive stage of the RL loop. However, these setups destabilize optimization by amplifying the training-inference gap: rollouts are operated at low… ▽ More Large language model (LLM) reinforcement learning (RL) pipelines are often bottlenecked by rollout generation, making end-to-end training slow. Recent work mitigates this by running rollouts with quantization to accelerate decoding, which is the most expensive stage of the RL loop. However, these setups destabilize optimization by amplifying the training-inference gap: rollouts are operated at low precision, while learning updates are computed at full precision. To address this challenge, we propose QaRL (Rollout Alignment Quantization-Aware RL), which aligns training-side forward with the quantized rollout to minimize mismatch. We further identify a failure mode in quantized rollouts: long-form responses tend to produce repetitive, garbled tokens (error tokens). To mitigate these problems, we introduce TBPO (Trust-Band Policy Optimization), a sequence-level objective with dual clipping for negative samples, aimed at keeping updates within the trust region. On Qwen3-30B-A3B MoE for math problems, QaRL outperforms quantized-rollout training by +5.5 while improving stability and preserving low-bit throughput benefits. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Towards Knowledgeable Deep Research: Framework and Benchmark

Authors: Wenxuan Liu, Zixuan Li, Bai Long, Chunmao Zhang, Fenghui Zhang, Zhuo Chen, Wei Li, Yuxin Zuo, Fei Wang, Bingbing Xu, Xuhui Jiang, Jin Zhang, Xiaolong Jin, Jiafeng Guo, Tat-Seng Chua, Xueqi Cheng

Abstract: Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive reports. In contrast to existing studies that mainly focus on unstructured web content, a more challenging DR task should additionally utilize structured knowledge to provide a solid data foundation, facilitate quantitative computation, and lead to in-d… ▽ More Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive reports. In contrast to existing studies that mainly focus on unstructured web content, a more challenging DR task should additionally utilize structured knowledge to provide a solid data foundation, facilitate quantitative computation, and lead to in-depth analyses. In this paper, we refer to this novel task as Knowledgeable Deep Research (KDR), which requires DR agents to generate reports with both structured and unstructured knowledge. Furthermore, we propose the Hybrid Knowledge Analysis framework (HKA), a multi-agent architecture that reasons over both kinds of knowledge and integrates the texts, figures, and tables into coherent multimodal reports. The key design is the Structured Knowledge Analyzer, which utilizes both coding and vision-language models to produce figures, tables, and corresponding insights. To support systematic evaluation, we construct KDR-Bench, which covers 9 domains, includes 41 expert-level questions, and incorporates a large number of structured knowledge resources (e.g., 1,252 tables). We further annotate the main conclusions and key points for each question and propose three categories of evaluation metrics including general-purpose, knowledge-centric, and vision-enhanced ones. Experimental results demonstrate that HKA consistently outperforms most existing DR agents on general-purpose and knowledge-centric metrics, and even surpasses the Gemini DR agent on vision-enhanced metrics, highlighting its effectiveness in deep, structure-aware knowledge analysis. Finally, we hope this work can serve as a new foundation for structured knowledge analysis in DR agents and facilitate future multimodal DR studies. △ Less

Submitted 8 April, 2026; originally announced April 2026.

ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding

Authors: Xuanle Zhao, Xinyuan Cai, Xiang Cheng, Xiuyi Chen, Bo Xu

Abstract: While Vision-Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimized for direct visual question-answering tasks. This paradigm often results in "black-box" systems that fail to utilize the inherent capability of Large Language Models (LLMs) to infer underlying reaction mechanisms. In this work, we introduce ChemVLR… ▽ More While Vision-Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimized for direct visual question-answering tasks. This paradigm often results in "black-box" systems that fail to utilize the inherent capability of Large Language Models (LLMs) to infer underlying reaction mechanisms. In this work, we introduce ChemVLR, a chemical VLM designed to prioritize reasoning within the perception process. Unlike conventional chemical VLMs, ChemVLR analyzes visual inputs in a fine-grained manner by explicitly identifying granular chemical descriptors, such as functional groups, prior to generating answers. This approach ensures the production of explicit and interpretable reasoning paths for complex visual chemical problems. To facilitate this methodology, we implement a cross-modality reverse-engineering strategy, combined with a rigorous filtering pipeline, to curate a large-scale reasoning-and-captioning dataset comprising 760k high-quality samples across molecular and reaction tasks. Furthermore, we adopt a three-stage training framework that systemically builds model perception and reasoning capacity. Experiments demonstrate that ChemVLR achieves state-of-the-art (SOTA) performance, surpassing both leading proprietary models and domain-specific open-source baselines. We also provide comprehensive ablation studies to validate our training strategy and data generation designs. Code and model weights will be available at https://github.com/xxlllz/ChemVLR. △ Less

Submitted 8 April, 2026; originally announced April 2026.

Comments: Accepted by ACL 2026 Findings, Preprint Version

Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection

Authors: Zi Liang, Qipeng Xie, Jun He, Bohuan Xue, Weizheng Wang, Yuandao Cai, Fei Luo, Boxian Zhang, Haibo Hu, Kaishun Wu

Abstract: Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic or rule-based methods. However, existing LLM-based approaches typically attempt to replace human experts directly without integrating effectively with existing… ▽ More Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic or rule-based methods. However, existing LLM-based approaches typically attempt to replace human experts directly without integrating effectively with existing SAST tools. This lack of integration results in ineffectiveness, including high rates of false positives, hallucinations, limited reasoning depth, and excessive token usage, making them impractical for industrial deployment. To overcome these limitations, we present a paradigm shift that reorchestrates the SAST workflow from current LLM-assisted structure to a new LLM-centered workflow. We introduce Argus (Agentic and Retrieval-Augmented Guarding System), the first multi-agent framework designed specifically for vulnerability detection. Argus incorporates three key novelties: comprehensive supply chain analysis, collaborative multi-agent workflows, and the integration of state-of-the-art techniques such as Retrieval-Augmented Generation (RAG) and ReAct to minimize hallucinations and enhance reasoning. Extensive empirical evaluation demonstrates that Argus significantly outperforms existing methods by detecting a higher volume of true vulnerabilities while simultaneously reducing false positives and operational costs. Notably, Argus has identified several critical zero-day vulnerabilities with CVE assignments. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Brain-to-Speech: Prosody Feature Engineering and Transformer-Based Reconstruction

Authors: Mohammed Salah Al-Radhi, Géza Németh, Andon Tchechmedjiev, Binbin Xu

Abstract: This chapter presents a novel approach to brain-to-speech (BTS) synthesis from intracranial electroencephalography (iEEG) data, emphasizing prosody-aware feature engineering and advanced transformer-based models for high-fidelity speech reconstruction. Driven by the increasing interest in decoding speech directly from brain activity, this work integrates neuroscience, artificial intelligence, and… ▽ More This chapter presents a novel approach to brain-to-speech (BTS) synthesis from intracranial electroencephalography (iEEG) data, emphasizing prosody-aware feature engineering and advanced transformer-based models for high-fidelity speech reconstruction. Driven by the increasing interest in decoding speech directly from brain activity, this work integrates neuroscience, artificial intelligence, and signal processing to generate accurate and natural speech. We introduce a novel pipeline for extracting key prosodic features directly from complex brain iEEG signals, including intonation, pitch, and rhythm. To effectively utilize these crucial features for natural-sounding speech, we employ advanced deep learning models. Furthermore, this chapter introduces a novel transformer encoder architecture specifically designed for brain-to-speech tasks. Unlike conventional models, our architecture integrates the extracted prosodic features to significantly enhance speech reconstruction, resulting in generated speech with improved intelligibility and expressiveness. A detailed evaluation demonstrates superior performance over established baseline methods, such as traditional Griffin-Lim and CNN-based reconstruction, across both quantitative and perceptual metrics. By demonstrating these advancements in feature extraction and transformer-based learning, this chapter contributes to the growing field of AI-driven neuroprosthetics, paving the way for assistive technologies that restore communication for individuals with speech impairments. Finally, we discuss promising future research directions, including the integration of diffusion models and real-time inference systems. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Comments: OpenAccess chapter: 10.1007/978-3-032-10561-5_16. In: Curry, E., et al. Artificial Intelligence, Data and Robotics (2026)

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

Authors: Bin Wang, Tianyao He, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Tao Chu, Yuan Qu, Zhenjiang Jin, Weijun Zeng, Ziyang Miao, Bangrui Xu, Junbo Niu, Mengzhang Cai, Jiantao Qiu, Qintong Zhang, Dongsheng Ma, Yuefeng Sun, Hejun Dong, Wenzheng Zhang, Jutao Xiao, Jiayong Shi, Pengyu Liao, Xiaomeng Zhao, Huaping Zhong, Liqun Wei , et al. (18 additional authors not shown)

Abstract: Current document parsing methods advance primarily through model architecture innovation, while systematic engineering of training data remains underexplored. Yet state-of-the-art models spanning diverse architectures and parameter scales exhibit highly consistent failure patterns on the same set of hard samples, suggesting that the performance bottleneck stems from shared deficiencies in training… ▽ More Current document parsing methods advance primarily through model architecture innovation, while systematic engineering of training data remains underexplored. Yet state-of-the-art models spanning diverse architectures and parameter scales exhibit highly consistent failure patterns on the same set of hard samples, suggesting that the performance bottleneck stems from shared deficiencies in training data rather than from architectural differences. Building on this finding, we present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design while retaining the 1.2B-parameter architecture of MinerU2.5 unchanged. At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy: Diversity-and-Difficulty-Aware Sampling expands training data from under 10M to 65.5M samples while mitigating distribution shift; Cross-Model Consistency Verification leverages output consensus among heterogeneous models to assess sample difficulty and generate reliable annotations; the Judge-and-Refine pipeline improves annotation quality for hard samples through render-then-verify iterative correction. A three-stage progressive training strategy--large-scale pre-training, hard sample fine-tuning, and GRPO alignment--sequentially exploits these data at different quality tiers. On the evaluation front, we rectify element-matching biases in OmniDocBench v1.5 and introduce a Hard subset, establishing the more discriminative OmniDocBench v1.6 protocol. Without any architectural modification, MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods, including those based on models with over 200x more parameters. △ Less

Submitted 9 April, 2026; v1 submitted 6 April, 2026; originally announced April 2026.

Comments: Technical Report

GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis

Authors: Yuwen Zhai, Runze Li, Liang Wang, Nian Shi, Liwu Xu, Wei Zhang, Ran Lin, Bo Xu, Benlei Cui

Abstract: Evaluating GUI agents presents a distinct challenge: trajectories are long, visually grounded, and open-ended, yet evaluation must be both accurate and interpretable. Existing approaches typically apply a single holistic judgment over the entire action-observation sequence-a strategy that proves unreliable on long-horizon tasks and yields binary verdicts offering no insight into where or why an ag… ▽ More Evaluating GUI agents presents a distinct challenge: trajectories are long, visually grounded, and open-ended, yet evaluation must be both accurate and interpretable. Existing approaches typically apply a single holistic judgment over the entire action-observation sequence-a strategy that proves unreliable on long-horizon tasks and yields binary verdicts offering no insight into where or why an agent fails. This opacity limits the utility of evaluation as a diagnostic tool for agent development. We introduce GUIDE (GUI Understanding and Interpretable Diagnostic Evaluation), a framework that decomposes trajectory assessment into three sequential stages mirroring the compositional structure of GUI tasks. Trajectory Segmentation partitions the full trace into semantically coherent subtask units. Subtask Diagnosis evaluates each unit in context, assigning a completion verdict and generating a structured error analysis with corrective recommendations. Overall Summary aggregates per-subtask diagnoses into a task-level judgment. By operating on bounded subtask segments rather than full trajectories, GUIDE mitigates the context overload that degrades existing evaluators as task complexity grows. We validate GUIDE on three benchmarks: an industrial e-commerce dataset of 932 trajectories, AGENTREWARDBENCH spanning five web agent tasks with 1302 trajectories, and AndroidBench for mobile device control. Across all settings, GUIDE substantially outperforms existing evaluators-achieving up to 5.35 percentage points higher accuracy than the strongest baseline-while producing structured diagnostic reports that directly inform agent improvement. △ Less

Submitted 5 April, 2026; originally announced April 2026.

DebugHarness: Emulating Human Dynamic Debugging for Autonomous Program Repair

Authors: Maolin Sun, Yibiao Yang, Xuanlin Liu, Yuming Zhou, Baowen Xu

Abstract: Patching severe security flaws in complex software remains a major challenge. While automated tools like fuzzers efficiently discover bugs, fixing deep-rooted low-level faults (e.g., use-after-free and memory corruption) still requires labor-intensive manual analysis by experts. Emerging Large Language Model (LLM) agents attempt to automate this pipeline, but they typically treat bug fixing as a p… ▽ More Patching severe security flaws in complex software remains a major challenge. While automated tools like fuzzers efficiently discover bugs, fixing deep-rooted low-level faults (e.g., use-after-free and memory corruption) still requires labor-intensive manual analysis by experts. Emerging Large Language Model (LLM) agents attempt to automate this pipeline, but they typically treat bug fixing as a purely static code-generation task. Relying solely on static artifacts, these methods miss the dynamic execution context strictly necessary for diagnosing intricate memory safety violations. To overcome these limitations, we introduce DebugHarness, an autonomous LLM-powered debugging agent harness that resolves complex vulnerabilities by emulating the interactive debugging practices of human systems engineers. Instead of merely examining static code, DebugHarness actively queries the live runtime environment. Driven by a reproducible crash, it utilizes a pattern-guided investigation strategy to formulate hypotheses, interactively probes program memory states and execution paths, and synthesizes patches via a closed-loop validation cycle. We evaluate DebugHarness on SEC-bench, a rigorous dataset of real-world C/C++ security vulnerabilities. DebugHarness successfully patches approximately 90% of the evaluated bugs. This yields a relative improvement of over 30% compared to state-of-the-art baselines, demonstrating that dynamic debugging significantly enhances LLM diagnostic capabilities. Overall, DebugHarness establishes a novel paradigm for automated program repair, bridging the gap between static LLM reasoning and the dynamic intricacies of low-level systems programming. △ Less

Submitted 4 April, 2026; originally announced April 2026.

Comments: 15 pages, 6 figures

Physics-Informed Untrained Learning for RGB-Guided Superresolution Single-Pixel Hyperspectral Imaging

Authors: Hao Zhang, Bilige Xu, Lichen Wei, Xu Ma, Wenyi Ren

Abstract: Single-pixel imaging (SPI) offers a cost-effective route to hyperspectral acquisition but struggles to recover high-fidelity spatial and spectral details under extremely low sampling rates, a severely ill-posed inverse problem. While deep learning has shown potential, existing data-driven methods demand large-scale pretraining datasets that are often impractical in hyperspectral imaging. To overco… ▽ More Single-pixel imaging (SPI) offers a cost-effective route to hyperspectral acquisition but struggles to recover high-fidelity spatial and spectral details under extremely low sampling rates, a severely ill-posed inverse problem. While deep learning has shown potential, existing data-driven methods demand large-scale pretraining datasets that are often impractical in hyperspectral imaging. To overcome this limitation, we propose an end-to-end physics-informed framework that leverages untrained neural networks and RGB guidance for joint hyperspectral reconstruction and super-resolution without any external training data. The framework comprises three physically grounded stages: (1) a Regularized Least-Squares method with RGB-derived Grayscale Priors (LS-RGP) that initializes the solution by exploiting cross-modal structural correlations; (2) an Untrained Hyperspectral Recovery Network (UHRNet) that refines the reconstruction through measurement consistency and hybrid regularization; and (3) a Transformer-based Untrained Super-Resolution Network (USRNet) that upsamples the spatial resolution via cross-modal attention, transferring high-frequency details from the RGB guide. Extensive experiments on benchmark datasets demonstrate that our approach significantly surpasses state-of-the-art algorithms in both reconstruction accuracy and spectral fidelity. Moreover, a proof-of-concept experiment using a physical single-pixel imaging system validates the framework's practical applicability, successfully reconstructing a 144-band hyperspectral data cube at a mere 6.25% sampling rate. The proposed method thus provides a robust, data-efficient solution for computational hyperspectral imaging. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Comments: 9 pages, 13 figures, 5 tables

Fair Aggregation in Virtual Power Plants

Authors: Liudong Chen, Hyemi Kim, Adam N. Elmachtoub, Bolun Xu

Abstract: A virtual power plant (VPP) is operated by an aggregator that acts as a market intermediary, aggregating consumers to participate in wholesale power markets. By setting incentive prices, the aggregator induces consumers to sell energy and profits by providing this aggregated energy to the market. This supply is enabled by consumers' flexibility to adjust electricity consumption in response to mark… ▽ More A virtual power plant (VPP) is operated by an aggregator that acts as a market intermediary, aggregating consumers to participate in wholesale power markets. By setting incentive prices, the aggregator induces consumers to sell energy and profits by providing this aggregated energy to the market. This supply is enabled by consumers' flexibility to adjust electricity consumption in response to market conditions. However, heterogeneity in flexibility means that profit-maximizing VPP pricing can create inequalities in participation and benefit allocation across consumers. In this paper, we develop a fairness-aware pricing framework to analyze how different fairness notions reshape system performance, measured by consumer Nash welfare, total consumer utility, and social welfare. We consider three fairness criteria: energy fairness, which ensures equitable energy provision; price fairness, which ensures similar incentive prices; and utility fairness, which ensures comparable levels of consumer utility. We model the aggregator-consumer interaction as a Stackelberg game and derive consumers' optimal responses to incentive prices. Using a stylized model, we show that profit-only pricing systematically disadvantages less flexible consumers. We further show that energy fairness can either improve or worsen all performance measures, and gains across most measures arise only at moderate fairness levels. Surprisingly, price fairness never benefits less flexible consumers, even when it reduces price disparities. By contrast, utility fairness protects less flexible consumers without benefiting more flexible ones. We validate our findings using data from an experiment in Norway under a tiered pricing scheme. Our results provide regulators and VPP operators with a systematic map linking fairness definitions and enforcement levels to operational and welfare outcomes. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Towards Realistic Class-Incremental Learning with Free-Flow Increments

Authors: Zhiming Xu, Baile Xu, Jian Zhao, Furao Shen, Suorong Yang

Abstract: Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new classes arrive, without forcing fixed-size tasks. We formalize this setting as Free-Flow Class-Incremental Learning (FFCIL), where data arrives as a more reali… ▽ More Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new classes arrive, without forcing fixed-size tasks. We formalize this setting as Free-Flow Class-Incremental Learning (FFCIL), where data arrives as a more realistic stream with a highly variable number of unseen classes each step. It will make many existing CIL methods brittle and lead to clear performance degradation. We propose a model-agnostic framework for robust CIL learning under free-flow arrivals. It comprises a class-wise mean (CWM) objective that replaces sample frequency weighted loss with uniformly aggregated class-conditional supervision, thereby stabilizing the learning signal across free-flow class increments, as well as method-wise adjustments that improve robustness for representative CIL paradigms. Specifically, we constrain distillation to replayed data, normalize the scale of contrastive and knowledge transfer losses, and introduce Dynamic Intervention Weight Alignment (DIWA) to prevent over-adjustment caused by unstable statistics from small class increments. Experiments confirm a clear performance degradation across various CIL baselines under FFCIL, while our strategies yield consistent gains. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Comments: 15pages, 5figures, 3 tables

OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration

Authors: Yiqin Yang, Hao Hu, Yihuan Mao, Jin Zhang, Chengjie Wu, Yuhua Jiang, Xu Yang, Runpeng Xie, Yi Fan, Bo Liu, Yang Gao, Bo Xu, Chongjie Zhang

Abstract: Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong barrier for PbRL. In this work, we address the problem of low query efficiency in offline PbRL, pinpoin… ▽ More Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong barrier for PbRL. In this work, we address the problem of low query efficiency in offline PbRL, pinpointing two primary reasons: inefficient exploration and overoptimization of learned reward functions. In response to these challenges, we propose a novel algorithm, \textbf{O}ffline \textbf{P}b\textbf{R}L via \textbf{I}n-\textbf{D}ataset \textbf{E}xploration (OPRIDE), designed to enhance the query efficiency of offline PbRL. OPRIDE consists of two key features: a principled exploration strategy that maximizes the informativeness of the queries and a discount scheduling mechanism aimed at mitigating overoptimization of the learned reward functions. Through empirical evaluations, we demonstrate that OPRIDE significantly outperforms prior methods, achieving strong performance with notably fewer queries. Moreover, we provide theoretical guarantees of the algorithm's efficiency. Experimental results across various locomotion, manipulation, and navigation tasks underscore the efficacy and versatility of our approach. △ Less

Submitted 18 February, 2026; originally announced April 2026.

Journal ref: ICLR-2026

From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?

Authors: Binyan Xu, Dong Fang, Haitao Li, Kehuan Zhang

Abstract: Multi-agent systems (MAS) tackle complex tasks by distributing expertise, though this often comes at the cost of heavy coordination overhead, context fragmentation, and brittle phase ordering. Distilling a MAS into a single-agent skill can bypass these costs, but this conversion lacks a principled answer for when and what to distill. Instead, the empirical outcome is surprisingly inconsistent: ski… ▽ More Multi-agent systems (MAS) tackle complex tasks by distributing expertise, though this often comes at the cost of heavy coordination overhead, context fragmentation, and brittle phase ordering. Distilling a MAS into a single-agent skill can bypass these costs, but this conversion lacks a principled answer for when and what to distill. Instead, the empirical outcome is surprisingly inconsistent: skill lift ranges from a 28% improvement to a 2% degradation across metrics of the exact same task. In this work, we reveal that skill utility is governed not by the task, but by the evaluation metric. We introduce Metric Freedom ($F$), the first a priori predictor of skill utility. $F$ measures the topological rigidity of a metric's scoring landscape by quantifying how output diversity couples with score variance via a Mantel test. Guided by $F$, we propose a two-stage adaptive distillation framework. Stage 1 acts as a selective extraction mechanism, extracting tools and knowledge while discarding restrictive structures on "free" metrics to preserve exploration. Stage 2 targets computationally intensive iterative refinement exclusively toward "rigid" metrics ($F \lesssim 0.6$) to eliminate trajectory-local overfitting. Evaluating across 4 tasks, 11 datasets, and 6 metrics, $F$ strongly predicts skill utility ($ρ= -0.62$, $p < 0.05$). Strikingly, identical agent trajectories yield diametrically opposite skill lifts under rigid versus free metrics, demonstrating that skill utility is fundamentally a metric-level property. Driven by this signal, our adaptive agent matches or exceeds the original MAS while reducing cost up to 8$\times$ and latency by up to 15$\times$. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Comments: 20 pages, 7 figures, 11 tables

C2RustXW: Program-Structure-Aware C-to-Rust Translation via Program Analysis and LLM

Authors: Yanyan Yan, Yang Feng, Jiangshan Liu, Di Liu, Zixi Liu, Hao Teng, Baowen Xu

Abstract: The growing adoption of Rust for its memory safety and performance has increased the demand for effective migration of legacy C codebases. However, existing rule-based translators (e.g., \ctorust) often generate verbose, non-idiomatic code that preserves unsafe C semantics, limiting readability, maintainability, and practical adoption. Moreover, manual post-processing of such outputs is labor-inte… ▽ More The growing adoption of Rust for its memory safety and performance has increased the demand for effective migration of legacy C codebases. However, existing rule-based translators (e.g., \ctorust) often generate verbose, non-idiomatic code that preserves unsafe C semantics, limiting readability, maintainability, and practical adoption. Moreover, manual post-processing of such outputs is labor-intensive and rarely yields high-quality Rust code, posing a significant barrier to large-scale migration. To address these limitations, we present \tool, a program-structure-aware C-to-Rust translation approach that integrates program analysis with Large Language Models (LLMs). \tool extracts the multi-level program structure, including global symbols, function dependencies, and control- and data-flow information, and encodes these as structured textual representations injected into LLM prompts to guide translation and repair. Based on this design, \tool performs dependency-aware translation and adopts a multi-stage repair pipeline that combines rule-based and structure-guided LLM-based techniques to ensure syntactic correctness. For semantic correctness, \tool further integrates execution-based validation with structure-guided reasoning to localize and repair behavioral inconsistencies. Experimental results show that \tool achieves 100\% syntactic correctness on CodeNet and 97.78\% on GitHub, while significantly reducing code size (up to 43.70\%) and unsafe usage (to 5.75\%). At the project level, \tool achieves perfect syntactic correctness and an average semantic correctness of 78.87\%, demonstrating its effectiveness for practical and scalable C-to-Rust migration. △ Less

Submitted 30 March, 2026; originally announced March 2026.

Unified Restoration-Perception Learning: Maritime Infrared-Visible Image Fusion and Segmentation

Authors: Weichao Cai, Weiliang Huang, Biao Xue, Chao Huang, Fei Yuan, Bob Zhang

Abstract: Marine scene understanding and segmentation plays a vital role in maritime monitoring and navigation safety. However, prevalent factors like fog and strong reflections in maritime environments cause severe image degradation, significantly compromising the stability of semantic perception. Existing restoration and enhancement methods typically target specific degradations or focus solely on visual… ▽ More Marine scene understanding and segmentation plays a vital role in maritime monitoring and navigation safety. However, prevalent factors like fog and strong reflections in maritime environments cause severe image degradation, significantly compromising the stability of semantic perception. Existing restoration and enhancement methods typically target specific degradations or focus solely on visual quality, lacking end-to-end collaborative mechanisms that simultaneously improve structural recovery and semantic effectiveness. Moreover, publicly available infrared-visible datasets are predominantly collected from urban scenes, failing to capture the authentic characteristics of coupled degradations in marine environments. To address these challenges, the Infrared-Visible Maritime Ship Dataset (IVMSD) is proposed to cover various maritime scenarios under diverse weather and illumination conditions. Building upon this dataset, a Multi-task Complementary Learning Framework (MCLF) is proposed to collaboratively perform image restoration, multimodal fusion, and semantic segmentation within a unified architecture. The framework includes a Frequency-Spatial Enhancement Complementary (FSEC) module for degradation suppression and structural enhancement, a Semantic-Visual Consistency Attention (SVCA) module for semantic-consistent guidance, and a cross-modality guided attention mechanism for selective fusion. Experimental results on IVMSD demonstrate that the proposed method achieves state-of-the-art segmentation performance, significantly enhancing robustness and perceptual quality under complex maritime conditions. △ Less

Submitted 30 March, 2026; originally announced March 2026.

Real-Time Branch-to-Tool Distance Estimation for Autonomous UAV Pruning: Benchmarking Five DEFOM-Stereo Variants from Simulation to Jetson Deployment

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green

Abstract: Autonomous tree pruning with unmanned aerial vehicles (UAVs) is a safety-critical real-world task: the onboard perception system must estimate the metric distance from a cutting tool to thin tree branches in real time so that the UAV can approach, align, and actuate the pruner without collision. We address this problem by training five variants of DEFOM-Stereo - a recent foundation-model-based ste… ▽ More Autonomous tree pruning with unmanned aerial vehicles (UAVs) is a safety-critical real-world task: the onboard perception system must estimate the metric distance from a cutting tool to thin tree branches in real time so that the UAV can approach, align, and actuate the pruner without collision. We address this problem by training five variants of DEFOM-Stereo - a recent foundation-model-based stereo matcher - on a task-specific synthetic dataset and deploying the checkpoints on an NVIDIA Jetson Orin Super 16 GB. The training corpus is built in Unreal Engine 5 with a simulated ZED Mini stereo camera capturing 5,520 stereo pairs across 115 tree instances from three viewpoints at 2m distance; dense EXR depth maps provide exact, spatially complete supervision for thin branches. On the synthetic test set, DEFOM-Stereo ViT-S achieves the best depth-domain accuracy (EPE 1.74 px, D1-all 5.81%, delta-1 95.90%, depth MAE 23.40 cm) but its Jetson inference speed of ~2.2 FPS (~450 ms per frame) remains too slow for responsive closed-loop tool control. A newly introduced balanced variant, DEFOM-PrunePlus (~21M backbone, ~3.3 FPS on Jetson), offers the best deployable accuracy-speed trade-off (EPE 5.87 px, depth MAE 64.26 cm, delta-1 87.59%): its frame rate is sufficient for real-time guidance and its depth accuracy supports safe branch approach planning at the 2m operating range. The lightweight DEFOM-PruneStereo (~6.9 FPS) and DEFOM-PruneNano (~8.5 FPS) run fast but sacrifice substantial accuracy (depth MAE > 57 cm), making estimates too unreliable for safe actuation. Zero-shot inference on real photographs confirms that full-capacity models preserve branch geometry, validating the sim-to-real transfer. We conclude that DEFOM-PrunePlus provides the most practical accuracy-latency balance for onboard distance estimation, while ViT-S serves as the reference for future hardware. △ Less

Submitted 27 March, 2026; originally announced March 2026.

RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following

Authors: Tianjun Pan, Xuan Lin, Wenyan Yang, Qianyu He, Shisong Chen, Licai Qi, Wanqing Xu, Hongwei Feng, Bo Xu, Yanghua Xiao

Abstract: Rubric-based evaluation has become a prevailing paradigm for evaluating instruction following in large language models (LLMs). Despite its widespread use, the reliability of these rubric-level evaluations remains unclear, calling for meta-evaluation. However, prior meta-evaluation efforts largely focus on the response level, failing to assess the fine-grained judgment accuracy that rubric-based ev… ▽ More Rubric-based evaluation has become a prevailing paradigm for evaluating instruction following in large language models (LLMs). Despite its widespread use, the reliability of these rubric-level evaluations remains unclear, calling for meta-evaluation. However, prior meta-evaluation efforts largely focus on the response level, failing to assess the fine-grained judgment accuracy that rubric-based evaluation relies on. To bridge this gap, we introduce RubricEval. Our benchmark features: (1) the first rubric-level meta-evaluation benchmark for instruction following, (2) diverse instructions and responses spanning multiple categories and model sources, and (3) a substantial set of 3,486 quality-controlled instances, along with Easy/Hard subsets that better differentiates judge performance. Our experiments reveal that rubric-level judging remains far from solved: even GPT-4o, a widely adopted judge in instruction-following benchmarks, achieves only 55.97% on Hard subset. Considering evaluation paradigm, rubric-level evaluation outperforms checklist-level, explicit reasoning improves accuracy, and both together reduce inter-judge variance. Through our established rubric taxonomy, we further identify common failure modes and offer actionable insights for reliable instruction-following evaluation. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Comments: 9 pages, 5 figures

AVO: Agentic Variation Operators for Autonomous Evolutionary Search

Authors: Terry Chen, Zhifan Ye, Bing Xu, Zihao Ye, Timmy Liu, Ali Hassani, Tianqi Chen, Andrew Kerr, Haicheng Wu, Yang Xu, Yu-Jung Chen, Hanfeng Chen, Aditya Kane, Ronny Krashinsky, Ming-Yu Liu, Vinod Grover, Luis Ceze, Roger Bringmann, John Tran, Wei Liu, Fung Xie, Michael Lightstone, Humphrey Shi

Abstract: Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than confining a language model to candidate generation within a prescribed pipeline, AVO instantiates variation as a self-directed agent loop that can consult the curre… ▽ More Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than confining a language model to candidate generation within a prescribed pipeline, AVO instantiates variation as a self-directed agent loop that can consult the current lineage, a domain-specific knowledge base, and execution feedback to propose, repair, critique, and verify implementation edits. We evaluate AVO on attention, among the most aggressively optimized kernel targets in AI, on NVIDIA Blackwell (B200) GPUs. Over 7 days of continuous autonomous evolution on multi-head attention, AVO discovers kernels that outperform cuDNN by up to 3.5% and FlashAttention-4 by up to 10.5% across the evaluated configurations. The discovered optimizations transfer readily to grouped-query attention, requiring only 30 minutes of additional autonomous adaptation and yielding gains of up to 7.0% over cuDNN and 9.3% over FlashAttention-4. Together, these results show that agentic variation operators move beyond prior LLM-in-the-loop evolutionary pipelines by elevating the agent from candidate generator to variation operator, and can discover performance-critical micro-architectural optimizations that produce kernels surpassing state-of-the-art expert-engineered attention implementations on today's most advanced GPU hardware. △ Less

Submitted 25 March, 2026; originally announced March 2026.

Trends in Equal-Contribution Authorship: A Large-Scale Bibliometric Analysis of Biomedical Literature

Authors: Binbin Xu

Abstract: Equal-contribution authorship, in which two or more authors are designated as having contributed equally, is increasingly common in scientific publishing. Using approximately 480,000 tagged records from PubMed and PMC (2010-2024), we examine temporal trends, journal-level patterns, geographic distributions, and byline positions of equal-contributing authors. Results show a sharp rise after 2017, w… ▽ More Equal-contribution authorship, in which two or more authors are designated as having contributed equally, is increasingly common in scientific publishing. Using approximately 480,000 tagged records from PubMed and PMC (2010-2024), we examine temporal trends, journal-level patterns, geographic distributions, and byline positions of equal-contributing authors. Results show a sharp rise after 2017, with both high-output mega-journals and smaller, discipline-specific journals contributing to the growth. Journal-level analysis indicates a median increase in the share of tagged articles from about 19% in 2015 to over 30% in 2024, with some journals exceeding 50%. Geographically, China accounts for the largest share (40.8% of fractionalized contributions), followed by the United States (15.2%) and Germany (5.2%). Normalizing to 2015 baselines, China shows a 13.1x; increase by 2024, while even the slowest-growing countries more than tripled their levels. Analysis of normalized byline positions shows that equal-contribution designations are concentrated near the first-author position, with fewer cases in middle or last positions. These findings document a broad shift toward shared first-author credit across journal sizes and regions within the biomedical literature and suggest that journals and evaluators may need to rely more on transparent contributorship information and to monitor the use of such labels over time. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Journal ref: Quantitative Science Studies, 1-15 (2026)

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal

Authors: Zining Fang, Cheng Xue, Chunhui Liu, Bin Xu, Ming Chen, Xiaowei Hu

Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restora… ▽ More Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision. △ Less

Submitted 7 April, 2026; v1 submitted 24 March, 2026; originally announced March 2026.

Comments: 12 pages,7figures,published to CVPR

Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems

Authors: Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin

Abstract: Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general nodes like Chain-of-Thought, which lack specialized expertise, or attempt to generate nodes on the f… ▽ More Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general nodes like Chain-of-Thought, which lack specialized expertise, or attempt to generate nodes on the fly. In the latter case, the orchestrator is not only bound by its internal knowledge limits but must also simultaneously generate domain-specific logic and optimize high-level topology, leading to a severe architectural coupling that degrades overall system efficacy. To bridge this gap, we propose Unified-MAS that decouples granular node implementation from topological orchestration via offline node synthesis. Unified-MAS operates in two stages: (1) Search-Based Node Generation retrieves external open-world knowledge to synthesize specialized node blueprints, overcoming the internal knowledge limits of LLMs; and (2) Reward-Based Node Optimization utilizes a perplexity-guided reward to iteratively enhance the internal logic of bottleneck nodes. Extensive experiments across four specialized domains demonstrate that integrating Unified-MAS into four Automatic-MAS baselines yields a better performance-cost trade-off, achieving up to a 14.2% gain while significantly reducing costs. Further analysis reveals its robustness across different designer LLMs and its effectiveness on conventional tasks such as mathematical reasoning. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Comments: Code is available at https://github.com/linhh29/Unified-MAS

SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments

Authors: Wen Jiang, Kangyao Huang, Li Wang, Wang Xu, Wei Fan, Jinyuan Liu, Shaoyu Liu, Hanfang Liang, Hongwei Duan, Bin Xu, Xiangyang Ji

Abstract: UAVs play an important role in applications such as autonomous exploration, disaster response, and infrastructure inspection. However, UAV VLN in complex 3D environments remains challenging. A key difficulty is the structural representation mismatch between 2D visual perception and the 3D trajectory decision space, which limits spatial reasoning. To this end, we propose SpatialFly, a geometry-guid… ▽ More UAVs play an important role in applications such as autonomous exploration, disaster response, and infrastructure inspection. However, UAV VLN in complex 3D environments remains challenging. A key difficulty is the structural representation mismatch between 2D visual perception and the 3D trajectory decision space, which limits spatial reasoning. To this end, we propose SpatialFly, a geometry-guided spatial representation framework for UAV VLN. Operating on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D representation alignment mechanism. Specifically, the geometric prior injection module injects global structural cues into 2D semantic tokens to provide scene-level geometric guidance. The geometry-aware reparameterization module then aligns 2D semantic tokens with 3D geometric tokens through cross-modal attention, followed by gated residual fusion to preserve semantic discrimination. Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments, reducing NE by 4.03m and improving SR by 1.27% over the strongest baseline on the unseen Full split. Additional trajectory-level analysis shows that SpatialFly produces trajectories with better path alignment and smoother, more stable motion. △ Less

Submitted 21 March, 2026; originally announced March 2026.

AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing

Authors: Sen Fang, Weiyuan Ding, Zhezhen Cao, Zhou Yang, Bowen Xu

Abstract: Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a root cause shared by both major mitigation paradigms (agent-based debate and retrieval augmentation): reasoning in an ungrounded deliberative space that lacks a bounded, hypothesis-specific evidence base. Without such grounding, agents fabricate cross-… ▽ More Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a root cause shared by both major mitigation paradigms (agent-based debate and retrieval augmentation): reasoning in an ungrounded deliberative space that lacks a bounded, hypothesis-specific evidence base. Without such grounding, agents fabricate cross-function dependencies, and retrieval heuristics supply generic knowledge decoupled from the repository's data-flow topology. Consequently, the resulting conclusions are driven by rhetorical persuasiveness rather than verifiable facts. To ground this deliberation, we present AEGIS, a novel multi-agent framework that shifts detection from ungrounded speculation to forensic verification over a closed factual substrate. Guided by a "From Clue to Verdict" philosophy, AEGIS first identifies suspicious code anomalies (clues), then dynamically reconstructs per-variable dependency chains for each clue via on-demand slicing over a repository-level Code Property Graph. Within this closed evidence boundary, a Verifier Agent constructs competing dialectical arguments for and against exploitability, while an independent Audit Agent scrutinizes every claim against the trace, exercising veto power to prevent hallucinated verdicts. Evaluation on the rigorous PrimeVul dataset demonstrates that AEGIS establishes a new state-of-the-art, achieving 122 Pair-wise Correct Predictions. To our knowledge, this is the first approach to surpass 100 on this benchmark. It reduces the false positive rate by up to 54.40% compared to leading baselines, at an average cost of $0.09 per sample without any task-specific training. △ Less

Submitted 21 March, 2026; originally announced March 2026.

Comments: 29 pages, 6 figures, 3 tables

HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

Authors: Beibei Xu, Yutong Ye, Chuyun Shen, Yingbo Zhou, Cheng Chen, Mingsong Chen

Abstract: Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-gen… ▽ More Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\times$ and 16$\times$, respectively, compared to the state-of-the-art open-source baseline. △ Less

Submitted 20 March, 2026; originally announced March 2026.

It Depends: Re_Authoring Play Through Clinical Reasoning in Wearable AR Rehab Games

Authors: Binyan Xu, Wei Wu, Soonhyeon Kweon, Casper Harteveld, Leanne Chukoskie

Abstract: Augmented reality games hold promise for rehabilitation, yet most remain confined to laboratory studies with limited clinical uptake. Recent advances in spatial computing, especially lightweight, glasses_form_factor AR, create a timely opportunity to embed rehabilitative play into clinical practice and daily contexts. To investigate this potential, we systematically reviewed 132 applications and c… ▽ More Augmented reality games hold promise for rehabilitation, yet most remain confined to laboratory studies with limited clinical uptake. Recent advances in spatial computing, especially lightweight, glasses_form_factor AR, create a timely opportunity to embed rehabilitative play into clinical practice and daily contexts. To investigate this potential, we systematically reviewed 132 applications and conducted playtesting with 14 licensed physical therapists. Our analysis revealed three ways therapists re_authored AR games: co_authored play (reshaping movements, progressions, and difficulty), situated play (adapting across specialties, conditions, and contexts), and dual play (mediating both physical recovery and psychological support). We reframe therapists' frequent phrase_It depends_as a generative design principle. This study contributes a clinical reasoning_based framework and design principles and guidelines for creating personalized, situated forms of play that align with therapists' everyday workflows and inform future lab_to_clinic translation. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Journal ref: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26), April 13_17, 2026, Barcelona, Spain

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

Authors: Hao Zhang, Mingjie Liu, Shaokun Zhang, Songyang Han, Jian Hu, Zhenghui Jin, Yuchi Zhang, Shizhe Diao, Ximing Lu, Binfeng Xu, Zhiding Yu, Jan Kautz, Yi Dong

Abstract: Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires generating large numbers of sandboxed rollout trajectories, and existing infrastructures often couple rollout orchestration with the training loop, making systems hard to migrate and mai… ▽ More Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires generating large numbers of sandboxed rollout trajectories, and existing infrastructures often couple rollout orchestration with the training loop, making systems hard to migrate and maintain. Under the rollout-as-a-service philosophy, we present ProRL Agent , a scalable infrastructure that serves the full agentic rollout lifecycle through an API service. ProRL Agent also provides standardized and extensible sandbox environments that support diverse agentic tasks in rootless HPC settings. We validate ProRL Agent through RL training on software engineering, math, STEM, and coding tasks. ProRL Agent is open-sourced and integrated as part of NVIDIA NeMo Gym. △ Less

Submitted 19 March, 2026; originally announced March 2026.

OCP: Orthogonal Constrained Projection for Sparse Scaling in Industrial Commodity Recommendation

Authors: Chen Sun, Beilin Xu, Boheng Tan, Jiacheng Wang, Yuefeng Sun, Rite Bo, Ying He, Yaqiang Zang, Pinghua Gong

Abstract: In industrial commodity recommendation systems, the representation quality of Item-Id vocabularies directly impacts the scalability and generalization ability of recommendation models. A key challenge is that traditional Item-Id vocabularies, when subjected to sparse scaling, suffer from low-frequency information interference, which restricts their expressive power for massive item sets and leads… ▽ More In industrial commodity recommendation systems, the representation quality of Item-Id vocabularies directly impacts the scalability and generalization ability of recommendation models. A key challenge is that traditional Item-Id vocabularies, when subjected to sparse scaling, suffer from low-frequency information interference, which restricts their expressive power for massive item sets and leads to representation collapse. To address this issue, we propose an Orthogonal Constrained Projection method to optimize embedding representation. By enforcing orthogonality, the projection constrains the backpropagation manifold, aligning the singular value spectrum of the learned embeddings with the orthogonal basis. This alignment ensures high singular entropy, thereby preserving isotropic generalized features while suppressing spurious correlations and overfitting to rare items. Empirical results demonstrate that OCP accelerates loss convergence and enhances the model's scalability; notably, it enables consistent performance gains when scaling up dense layers. Large-scale industrial deployment on JD.com further confirms its efficacy, yielding a 12.97% increase in UCXR and an 8.9% uplift in GMV, highlighting its robust utility for scaling up both sparse vocabularies and dense architectures. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Comments: 5 pages, 4 figures

iSatCR: Graph-Empowered Joint Onboard Computing and Routing for LEO Data Delivery

Authors: Jiangtao Luo, Bingbing Xu, Shaohua Xia, Yongyi Ran

Abstract: Sending massive Earth observation data produced by low Earth orbit (LEO) satellites back to the ground for processing consumes a large amount of on-orbit bandwidth and exacerbates the space-to-ground link bottleneck. Most prior work has concentrated on optimizing the routing of raw data within the constellation, yet cannot cope with the surge in data volume. Recently, advances in onboard computing… ▽ More Sending massive Earth observation data produced by low Earth orbit (LEO) satellites back to the ground for processing consumes a large amount of on-orbit bandwidth and exacerbates the space-to-ground link bottleneck. Most prior work has concentrated on optimizing the routing of raw data within the constellation, yet cannot cope with the surge in data volume. Recently, advances in onboard computing have made it possible to process data in situ, thus significantly reducing the data volume to be transmitted. In this paper, we present iSatCR, a distributed graph-based approach that jointly optimizes onboard computing and routing to boost transmission efficiency. Within iSatCR, we design a novel graph embedding utilizing shifted feature aggregation and distributed message passing to capture satellite states, and then propose a distributed graph-based deep reinforcement learning algorithm that derives joint computing-routing strategies under constrained on-board storage to handle the complexity and dynamics of LEO networks. Extensive experiments show iSatCR outperforms baselines, particularly under high load. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Comments: 14 pages, 9 figures

Agentic AI for SAGIN Resource Management_Semantic Awareness, Orchestration, and Optimization

Authors: Linghao Zhang, Haitao Zhao, Bo Xu, Hongbo Zhu, Xianbin Wang

Abstract: Space-air-ground integrated networks (SAGIN) promise ubiquitous 6G connectivity but face significant resource management challenges due to heterogeneous infrastructure, dynamic topologies, and stringent quality-of-service (QoS) requirements. Conventional model-driven approaches struggle with scalability and adaptability in such complex environments. This paper presents an agentic artificial intell… ▽ More Space-air-ground integrated networks (SAGIN) promise ubiquitous 6G connectivity but face significant resource management challenges due to heterogeneous infrastructure, dynamic topologies, and stringent quality-of-service (QoS) requirements. Conventional model-driven approaches struggle with scalability and adaptability in such complex environments. This paper presents an agentic artificial intelligence (AI) framework for autonomous SAGIN resource management by embedding large language model (LLM)-based agents into a Monitor-Analyze-Plan- Execute-Knowledge (MAPE-K) control plane. The framework incorporates three specialized agents, namely semantic resource perceivers, intent-driven orchestrators, and adaptive learners, that collaborate through natural language reasoning to bridge the gap between operator intents and network execution. A key innovation is the hierarchical agent-reinforcement learning (RL) collaboration mechanism, wherein LLM-based orchestrators dynamically shape reward functions for RL agents based on semantic network conditions. Validation through UAV-assisted AIGC service orchestration in energy-constrained scenarios demonstrates that LLM-driven reward shaping achieves 14% energy reduction and the lowest average service latency among all compared methods. This agentic paradigm offers a scalable pathway toward adaptive, AI-native 6G networks, capable of autonomously interpreting intents and adapting to dynamic environments. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Comments: eg.: 7 pages, 6 figures

MFTune: An Efficient Multi-fidelity Framework for Spark SQL Configuration Tuning

Authors: Beicheng Xu, Lingching Tung, Yuchen Wang, Yupeng Lu, Bin Cui

Abstract: Apache Spark SQL is a cornerstone of modern big data analytics.However,optimizing Spark SQL performance is challenging due to its vast configuration space and the prohibitive cost of evaluating massive workloads. Existing tuning methods predominantly rely on full-fidelity evaluations, which are extremely time-consuming,often leading to suboptimal performance within practical budgets.While multi-fi… ▽ More Apache Spark SQL is a cornerstone of modern big data analytics.However,optimizing Spark SQL performance is challenging due to its vast configuration space and the prohibitive cost of evaluating massive workloads. Existing tuning methods predominantly rely on full-fidelity evaluations, which are extremely time-consuming,often leading to suboptimal performance within practical budgets.While multi-fidelity optimization offers a potential solution, directly applying standard techniques-such as data volume reduction or early stopping-proves ineffective for Spark SQL as they fail to preserve performance correlations or represent true system bottlenecks. To address these challenges, we propose MFTune, an efficient multi-fidelity framework that introduces a query-based fidelity partitioning strategy, utilizing representative SQL subsets to provide accurate, low-cost proxies. To navigate the huge search space, MFTune incorporates a density-based optimization mechanism for automated knob and range compression, alongside an adapted transfer learning approach and a two-phase warm start to further accelerate the tuning process. Experimental results on TPC-H and TPC-DS benchmarks demonstrate that MFTune significantly outperforms five state-of-the-art tuning methods, identifying superior configurations within practical time constraints. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Physics-guided diffusion models for inverse design of disordered metamaterials

Authors: Ziyuan Xie, Weipeng Xu, Dazhi Zhao, Wenchang Zhang, Daoyang Dong, Bingbing Xu, Ning Liu, Sheng Mao, Tianju Xue

Abstract: Disordered metamaterials are promising for programming physical properties across diverse applications, yet their inverse design remains challenging due to the non-intuitive structure-property relationships and large design spaces. Recent generative approaches, particularly diffusion models, have shown potential in high-dimensional inverse design tasks. However, existing methods typically rely on… ▽ More Disordered metamaterials are promising for programming physical properties across diverse applications, yet their inverse design remains challenging due to the non-intuitive structure-property relationships and large design spaces. Recent generative approaches, particularly diffusion models, have shown potential in high-dimensional inverse design tasks. However, existing methods typically rely on carefully crafted training objectives, such as conditional data-driven or physics-informed loss functions. Because these strategies are inherently task-specific, the model must be retrained from scratch whenever the design problem changes (e.g., different governing equations, boundary conditions, or design objectives), severely limiting their flexibility and generalization ability. In this work, we propose physics-guided diffusion models that leverage differentiable physics-based solvers to instantly guide the generative process for inverse design. Drawing inspiration from classifier guidance, we develop a sampling strategy that directly incorporates physics guidance into the reverse stochastic differential equations. Our approach enables task-adaptive generation using gradients from differentiable solvers, while the diffusion model itself needs to be trained only once on unlabeled data. Focusing on disordered foam metamaterials, we present three representative design tasks: (1) achieving target effective thermal conductivity, (2) matching desired load-displacement response, and (3) maximizing energy absorption involving fractures. In each scenario, the proposed method successfully generates foam-like geometries that fulfill the prescribed physical objectives. These results demonstrate the versatility, efficiency, and practicality of physics-guided diffusion models for tackling complex inverse design problems in disordered metamaterials and beyond. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Comments: 30 pages, 13 figures

UE5-Forest: A Photorealistic Synthetic Stereo Dataset for UAV Forestry Depth Estimation

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green

Abstract: Dense ground-truth disparity maps are practically unobtainable in forestry environments, where thin overlapping branches and complex canopy geometry defeat conventional depth sensors -- a critical bottleneck for training supervised stereo matching networks for autonomous UAV-based pruning. We present UE5-Forest, a photorealistic synthetic stereo dataset built entirely in Unreal Engine 5 (UE5). One… ▽ More Dense ground-truth disparity maps are practically unobtainable in forestry environments, where thin overlapping branches and complex canopy geometry defeat conventional depth sensors -- a critical bottleneck for training supervised stereo matching networks for autonomous UAV-based pruning. We present UE5-Forest, a photorealistic synthetic stereo dataset built entirely in Unreal Engine 5 (UE5). One hundred and fifteen photogrammetry-scanned trees from the Quixel Megascans library are placed in virtual scenes and captured by a simulated stereo rig whose intrinsics -- 63 mm baseline, 2.8 mm focal length, 3.84 mm sensor width -- replicate the ZED Mini camera mounted on our drone. Orbiting each tree at up to 2 m across three elevation bands (horizontal, +45 degrees, -45 degrees) yields 5,520 rectified 1920 x 1080 stereo pairs with pixel-perfect disparity labels. We provide a statistical characterisation of the dataset -- covering disparity distributions, scene diversity, and visual fidelity -- and a qualitative comparison with real-world Canterbury Tree Branches imagery that confirms the photorealistic quality and geometric plausibility of the rendered data. The dataset will be publicly released to provide the community with a ready-to-use benchmark and training resource for stereo-based forestry depth estimation. △ Less

Submitted 27 March, 2026; v1 submitted 13 March, 2026; originally announced March 2026.

VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning

Authors: Chaoyang Wang, Wenrui Bao, Sicheng Gao, Bingxin Xu, Yu Tian, Yogesh S. Rawat, Yunhao Ge, Yuzhang Shang

Abstract: Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where visual inputs are treated as static context. This limits the ability of the model to actively revisit the environment and resolve ambiguities during long-horizon tasks. We propose VLA-Thinker, a thinking-with-image reasoni… ▽ More Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where visual inputs are treated as static context. This limits the ability of the model to actively revisit the environment and resolve ambiguities during long-horizon tasks. We propose VLA-Thinker, a thinking-with-image reasoning framework that models perception as a dynamically invocable reasoning action. To train such a system, we introduce a two-stage training pipeline consisting of (1) an SFT cold-start phase with curated visual Chain-of-Thought data to activate structured reasoning and tool-use behaviors, and (2) GRPO-based reinforcement learning to align complete reasoning-action trajectories with task-level success. Extensive experiments on LIBERO and RoboTwin 2.0 benchmarks demonstrate that VLA-Thinker significantly improves manipulation performance, achieving 97.5% success rate on LIBERO and strong gains across long-horizon robotic tasks. Project and Codes: https://cywang735.github.io/VLA-Thinker/ . △ Less

Submitted 15 March, 2026; originally announced March 2026.

Comments: We introduce VLA-Thinker, the first VLA model capable of thinking-with-image reasoning, which models visual perception as a dynamically invocable reasoning action, enabling Multimodal Embodied Chain-of-Thought

Advancing Cancer Prognosis with Hierarchical Fusion of Genomic, Proteomic and Pathology Imaging Data from a Systems Biology Perspective

Authors: Junjie Zhou, Bao Xue, Meiling Wang, Wei Shao, Daoqiang Zhang

Abstract: To enhance the precision of cancer prognosis, recent research has increasingly focused on multimodal survival methods by integrating genomic data and histology images. However, current approaches overlook the fact that the proteome serves as an intermediate layer bridging genomic alterations and histopathological features while providing complementary biological information essential for survival… ▽ More To enhance the precision of cancer prognosis, recent research has increasingly focused on multimodal survival methods by integrating genomic data and histology images. However, current approaches overlook the fact that the proteome serves as an intermediate layer bridging genomic alterations and histopathological features while providing complementary biological information essential for survival prediction. This biological reality exposes another architectural limitation: existing integrative analysis studies fuse these heterogeneous data sources in a flat manner that fails to capture their inherent biological hierarchy. To address these limitations, we propose HFGPI, a hierarchical fusion framework that models the biological progression from genes to proteins to histology images from a systems biology perspective. Specifically, we introduce Molecular Tokenizer, a molecular encoding strategy that integrates identity embeddings with expression profiles to construct biologically informed representations for genes and proteins. We then develop Gene-Regulated Protein Fusion (GRPF), which employs graph-aware cross-attention with structure-preserving alignment to explicitly model gene-protein regulatory relationships and generate gene-regulated protein representations. Additionally, we propose Protein-Guided Hypergraph Learning (PGHL), which establishes associations between proteins and image patches, leveraging hypergraph convolution to capture higher-order protein-morphology relationships. The final features are progressively fused across hierarchical layers to achieve precise survival outcome prediction. Extensive experiments on five benchmark datasets demonstrate the superiority of HFGPI over state-of-the-art methods. △ Less

Submitted 14 March, 2026; originally announced March 2026.

Reimagining Wearable AR Gesture Design: Physical Therapy Reasoning in Everyday Contexts

Authors: Wei Wu, Binyan Xu, Soonhyeon Kweon, Yujie Wang, Leanne Chukoskie, Casper Harteveld

Abstract: Lightweight augmented reality (AR) glasses are increasingly entering everyday use, extending interaction design beyond short, isolated sessions. However, most existing gesture vocabularies are inherited from VR headsets or early AR goggles. These systems tend to prioritize recognizer accuracy while overlooking fatigue, sustainability, and social legibility in daily contexts. To address this gap, w… ▽ More Lightweight augmented reality (AR) glasses are increasingly entering everyday use, extending interaction design beyond short, isolated sessions. However, most existing gesture vocabularies are inherited from VR headsets or early AR goggles. These systems tend to prioritize recognizer accuracy while overlooking fatigue, sustainability, and social legibility in daily contexts. To address this gap, we collaborated with physical therapists (PTs) to reimagine gesture design for everyday AR, drawing on their expertise in safe and sustainable movement. Through a review of 104 AR applications, we identified 15 common gesture intents and implemented an on-device gesture generator. Ten licensed physical therapists, with an average of 14.8 years of professional experience, then shaped these gesture intents through three iterative stages: unaided gesture performance, PT-guided gesture substitution, and stage-aware card sorting. This work contributes (1) a PT-informed gesture translation method, (2) the Everyday-AR Golden Ergonomic Canvas, and (3) a stage-aware social legibility framework that illustrates how gesture suitability shifts with social readability. Together, these contributions provide a recognizer-agnostic reference framework for designing sustainable and socially coherent gesture vocabularies for lightweight AR glasses. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Journal ref: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26), April 13--17, 2026, Barcelona, Spain

Long-form RewardBench: Evaluating Reward Models for Long-form Generation

Authors: Hui Huang, Yancheng He, Wei Liu, Muyun Yang, Jiaheng Liu, Kehai Chen, Bing Xu, Conghui Zhu, Hailong Cao, Tiejun Zhao

Abstract: The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to evaluate reward models in various domains and scenarios. However, a significant gap remains in assessing reward models for long-form generation, despite its critical role in real-world applications. To bridge this, we introduce Long-form Reward… ▽ More The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to evaluate reward models in various domains and scenarios. However, a significant gap remains in assessing reward models for long-form generation, despite its critical role in real-world applications. To bridge this, we introduce Long-form RewardBench, the first reward modeling testbed specifically designed for long-form generation. Our benchmark encompasses five key subtasks: QA, RAG, Chat, Writing, and Reasoning. We collected instruction and preference data through a meticulously designed multi-stage data collection process, and conducted extensive experiments on 20+ mainstream reward models, including both classifiers and generative models. Our findings reveal that current models still lack long-form reward modeling capabilities. Furthermore, we designed a novel Long-form Needle-in-a-Haystack Test, which revealed a correlation between reward modeling performance and the error's position within a response, as well as the overall response length, with distinct characteristics observed between classification and generative models. Finally, we demonstrate that classifiers exhibit better generalizability compared to generative models trained on the same data. As the first benchmark for long-form reward modeling, this work aims to offer a robust platform for visualizing progress in this crucial area. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Comments: Accepted by AAAI2026

Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization

Authors: Hongli Zhou, Hui Huang, Rui Zhang, Kehai Chen, Bing Xu, Conghui Zhu, Tiejun Zhao, Muyun Yang

Abstract: Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evaluating these biases is essential for ensuring the reliability of LLM-based judges. However, existing studies typically investigate limited biases under a single judge formulation, either generative or discriminative, lack… ▽ More Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evaluating these biases is essential for ensuring the reliability of LLM-based judges. However, existing studies typically investigate limited biases under a single judge formulation, either generative or discriminative, lacking a comprehensive evaluation. To bridge this gap, we propose JudgeBiasBench, a benchmark for systematically quantifying biases in LLM-based judges. JudgeBiasBench defines a taxonomy of judgment biases across 4 dimensions, and constructs bias-augmented evaluation instances through a controlled bias injection pipeline, covering 12 representative bias types. We conduct extensive experiments across both generative and discriminative judges, revealing that current judges exhibit significant and diverse bias patterns that often compromise the reliability of automated evaluation. To mitigate judgment bias, we propose bias-aware training that explicitly incorporates bias-related attributes into the training process, encouraging judges to disentangle task-relevant quality from bias-correlated cues. By adopting reinforcement learning for generative judges and contrastive learning for discriminative judges, our methods effectively reduce judgment biases while largely preserving general evaluation capability. △ Less

Submitted 9 March, 2026; originally announced March 2026.

Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment

Authors: Binxia Xu, Xiaoliang Luo, Luke Dickens, Robert M. Mok

Abstract: Determining whether AI systems process information similarly to humans is central to cognitive science and trustworthy AI. While modern AI models match human accuracy on standard tasks, such parity does not guarantee that their underlying decision-making strategies are aligned with human information processing. Assessing performance using i) error alignment metrics to compare how humans and models… ▽ More Determining whether AI systems process information similarly to humans is central to cognitive science and trustworthy AI. While modern AI models match human accuracy on standard tasks, such parity does not guarantee that their underlying decision-making strategies are aligned with human information processing. Assessing performance using i) error alignment metrics to compare how humans and models fail, and ii) using distorted, or otherwise more challenging, stimuli, provides a viable pathway toward a finer characterization of model-human alignment. However, existing out-of-distribution (OOD) analyses for challenging stimuli are limited due to methodological choices: they define OOD shift relative to model training data or use arbitrary distortion-specific parameters with little correspondence to human perception, hindering principled comparisons. We propose a human-centred framework that redefines the degree of OOD as a spectrum of human perceptual difficulty. By quantifying how much a collection of stimuli deviates from an undistorted reference set based on human accuracy, we construct an OOD spectrum and identify four distinct regimes of perceptual challenge. This approach enables principled model-human comparisons at calibrated difficulty levels. We apply this framework to object recognition and reveal unique, regime-dependent model-human alignment rankings and profiles across deep learning architectures. Vision-language models are the most consistently human aligned across near- and far-OOD conditions, but CNNs are more aligned than ViTs for near-OOD and ViTs are more aligned than CNNs for far-OOD conditions. Our work demonstrates the critical importance of accounting for cross-condition differences such as perceptual difficulty for a principled assessment of model-human alignment. △ Less

Submitted 7 March, 2026; originally announced March 2026.

Data Agent: Learning to Select Data via End-to-End Dynamic Optimization

Authors: Suorong Yang, Fangjian Su, Hai Gan, Ziqi Ye, Jie Li, Baile Xu, Furao Shen, Soujanya Poria

Abstract: Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate sample importance, limiting scalability across learning paradigms and making it difficult to capture the evolving utility of data throughout training. To address thi… ▽ More Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate sample importance, limiting scalability across learning paradigms and making it difficult to capture the evolving utility of data throughout training. To address this challenge, we propose Data Agent, an end-to-end dynamic data selection framework that formulates data selection as a training-aware sequential decision-making problem. The agent learns a sample-wise selection policy that co-evolves with model optimization, guided by a composite reward that integrates loss-based difficulty and confidence-based uncertainty signals. The reward signals capture complementary objectives of optimization impact and information gain, together with a tuning-free adaptive weighting mechanism that balances these signals over training. Extensive experiments across a wide range of datasets and architectures demonstrate that Data Agent consistently accelerates training while preserving or improving performance, e.g., reducing costs by over 50\% on ImageNet-1k and MMLU with lossless performance. Moreover, its dataset-agnostic formulation and modular reward make it plug-and-play across tasks and scenarios, e.g., robustness to noisy datasets, highlighting its potential in real-world scenarios. △ Less

Submitted 7 March, 2026; originally announced March 2026.

Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL

Authors: Bingfeng Chen, Shaobin Shi, Yongqi Luo, Boyan Xu, Ruichu Cai, Zhifeng Hao

Abstract: Generative language models have shown significant potential in single-turn Text-to-SQL. However, their performance does not extend equivalently to multi-turn Text-to-SQL. This is primarily due to generative language models' inadequacy in handling the complexities of context information and dynamic schema linking in multi-turn interactions. In this paper, we propose a framework named Track-SQL, whi… ▽ More Generative language models have shown significant potential in single-turn Text-to-SQL. However, their performance does not extend equivalently to multi-turn Text-to-SQL. This is primarily due to generative language models' inadequacy in handling the complexities of context information and dynamic schema linking in multi-turn interactions. In this paper, we propose a framework named Track-SQL, which enhances generative language models with dual-extractive modules designed to track schema and contextual changes in multi-turn Text-to-SQL. Specifically, Track-SQL incorporates a \emph{Semantic-enhanced Schema Extractor} and a \emph{Schema-aware Context Extractor}. Experimental results demonstrate that Track-SQL achieves state-of-the-art performance on the SparC and CoSQL datasets. Furthermore, detailed ablation studies reveal that Track-SQL significantly improves execution accuracy in multi-turn interactions by 7.1\% and 9.55\% on these datasets, respectively. Our implementation will be open-sourced at https://github.com/DMIRLAB-Group/Track-SQL. △ Less

Submitted 6 March, 2026; originally announced March 2026.

Comments: Accepted at the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025), Long Paper, 19 pages

Journal ref: Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 10690-10708. Association for Computational Linguistics, 2025

MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

Authors: Lulu Hu, Wenhu Xiao, Xin Chen, Xinhua Xu, Bowen Xu, Kun Li, Yongliang Tao

Abstract: Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models~(MLLMs) presents substantial challenges. In this paper, we analyze SmoothQuant as a case study and identify two critical issues: Smoothing Misalignment and Cross-Modal Computational Invariance. To addre… ▽ More Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models~(MLLMs) presents substantial challenges. In this paper, we analyze SmoothQuant as a case study and identify two critical issues: Smoothing Misalignment and Cross-Modal Computational Invariance. To address these issues, we propose Modality-Aware Smoothing Quantization (MASQuant), a novel framework that introduces (1) Modality-Aware Smoothing (MAS), which learns separate, modality-specific smoothing factors to prevent Smoothing Misalignment, and (2) Cross-Modal Compensation (CMC), which addresses Cross-modal Computational Invariance by using SVD whitening to transform multi-modal activation differences into low-rank forms, enabling unified quantization across modalities. MASQuant demonstrates stable quantization performance across both dual-modal and tri-modal MLLMs. Experimental results show that MASQuant is competitive among the state-of-the-art PTQ algorithms. Source code: https://github.com/alibaba/EfficientAI. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Comments: Accepted to CVPR 2026

ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation

Authors: Bo Xu, Haotian Wu, Hehai Lin, Weiquan Huang, Beier Zhu, Yao Shu, Chengwei Qin

Abstract: Model merging aims to combine multiple task-specific expert models into a single model while preserving generalization across diverse tasks. However, interference among experts, especially when they are trained on different objectives, often leads to significant performance degradation. Despite recent progress, resolving this interference without data access, retraining, or architectural modificat… ▽ More Model merging aims to combine multiple task-specific expert models into a single model while preserving generalization across diverse tasks. However, interference among experts, especially when they are trained on different objectives, often leads to significant performance degradation. Despite recent progress, resolving this interference without data access, retraining, or architectural modification remains a fundamental challenge. This paper provides a theoretical analysis demonstrating that the input covariance of each task, which is a key factor for optimal merging, can be implicitly estimated from the parameter differences of its fine-tuned model, even in a fully data-free setting. Building on this insight, we introduce \acem, an Adaptive Covariance Estimation framework that effectively mitigates inter-task interference. Our approach features a principled, closed-form solution that contrasts with prior iterative or heuristic methods. Extensive experiments on both vision and language benchmarks demonstrate that \acem sets a new state-of-the-art among data-free methods. It consistently outperforms existing baselines; for example, \acem achieves an average absolute improvement of 4\% over the previous methods across seven tasks on GPT-2. Owing to its efficient closed-form formulation, \acem delivers superior performance with a modest computational cost, providing a practical and theoretically grounded solution for model merging. △ Less

Submitted 8 April, 2026; v1 submitted 3 March, 2026; originally announced March 2026.

Comments: Accepted to CVPR 2026 (Main Track)

Boosting Meta-Learning for Few-Shot Text Classification via Label-guided Distance Scaling

Authors: Yunlong Gao, Xinyue Liu, Yingbo Wang, Linlin Zong, Bo Xu

Abstract: Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithms in the training stage. However, the labeled samples are randomly selected during the testing stage, so they may not provide effective supervision signals, leading to misclassification. To address this issue, we propose… ▽ More Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithms in the training stage. However, the labeled samples are randomly selected during the testing stage, so they may not provide effective supervision signals, leading to misclassification. To address this issue, we propose a \textbf{L}abel-guided \textbf{D}istance \textbf{S}caling (LDS) strategy. The core of our method is exploiting label semantics as supervision signals in both the training and testing stages. Specifically, in the training stage, we design a label-guided loss to inject label semantic information, pulling closer the sample representations and corresponding label representations. In the testing stage, we propose a Label-guided Scaler which scales sample representations with label semantics to provide additional supervision signals. Thus, even if labeled sample representations are far from class centers, our Label-guided Scaler pulls them closer to their class centers, thereby mitigating the misclassification. We combine two common meta-learners to verify the effectiveness of the method. Extensive experimental results demonstrate that our approach significantly outperforms state-of-the-art models. All datasets and codes are available at https://anonymous.4open.science/r/Label-guided-Text-Classification. △ Less

Submitted 28 February, 2026; originally announced March 2026.

Hierarchical Action Learning for Weakly-Supervised Action Segmentation

Authors: Junxian Huang, Ruichu Cai, Hao Zhu, Juntao Fang, Boyan Xu, Weilin Chen, Zijian Li, Shenghua Gao

Abstract: Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This highlights the difficulty of enabling hierarchical reasoning in video understanding. Interestingly, we observe that lower-level visual and high-level action latent variables evolve at different rates, with low-level visu… ▽ More Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This highlights the difficulty of enabling hierarchical reasoning in video understanding. Interestingly, we observe that lower-level visual and high-level action latent variables evolve at different rates, with low-level visual variables changing rapidly, while high-level action variables evolve more slowly, making them easier to identify. Building on this insight, we propose the Hierarchical Action Learning (\textbf{HAL}) model for weakly-supervised action segmentation. Our approach introduces a hierarchical causal data generation process, where high-level latent action governs the dynamics of low-level visual features. To model these varying timescales effectively, we introduce deterministic processes to align these latent variables over time. The \textbf{HAL} model employs a hierarchical pyramid transformer to capture both visual features and latent variables, and a sparse transition constraint is applied to enforce the slower dynamics of high-level action variables. This mechanism enhances the identification of these latent variables over time. Under mild assumptions, we prove that these latent action variables are strictly identifiable. Experimental results on several benchmarks show that the \textbf{HAL} model significantly outperforms existing methods for weakly-supervised action segmentation, confirming its practical effectiveness in real-world applications. △ Less

Submitted 27 February, 2026; originally announced February 2026.

Journal ref: CVPR2026

Hierarchical Multi-Scale Graph Learning with Knowledge-Guided Attention for Whole-Slide Image Survival Analysis

Authors: Bin Xu, Yufei Zhou, Boling Song, Jingwen Sun, Yang Bian, Cheng Lu, Ye Wu, Jianfei Tu, Xiangxue Wang

Abstract: We propose a Hierarchical Multi-scale Knowledge-aware Graph Network (HMKGN) that models multi-scale interactions and spatially hierarchical relationships within whole-slide images (WSIs) for cancer prognostication. Unlike conventional attention-based MIL, which ignores spatial organization, or graph-based MIL, which relies on static handcrafted graphs, HMKGN enforces a hierarchical structure with… ▽ More We propose a Hierarchical Multi-scale Knowledge-aware Graph Network (HMKGN) that models multi-scale interactions and spatially hierarchical relationships within whole-slide images (WSIs) for cancer prognostication. Unlike conventional attention-based MIL, which ignores spatial organization, or graph-based MIL, which relies on static handcrafted graphs, HMKGN enforces a hierarchical structure with spatial locality constraints, wherein local cellular-level dynamic graphs aggregate spatially proximate patches within each region of interest (ROI) and a global slide-level dynamic graph integrates ROI-level features into WSI-level representations. Moreover, multi-scale integration at the ROI level combines coarse contextual features from broader views with fine-grained structural representations from local patch-graph aggregation. We evaluate HMKGN on four TCGA cohorts (KIRC, LGG, PAAD, and STAD; N=513, 487, 138, and 370) for survival prediction. It consistently outperforms existing MIL-based models, yielding improved concordance indices (10.85% better) and statistically significant stratification of patient survival risk (log-rank p < 0.05). △ Less

Submitted 2 March, 2026; v1 submitted 26 February, 2026; originally announced February 2026.

Comments: 4 pages, 1 figure, 2 tables, ISBI 2026

MSC Class: 68T01 ACM Class: I.5.1; I.5.2; I.5.4

UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception

Authors: Mohammad Mahdavian, Gordon Tan, Binbin Xu, Yuan Ren, Dongfeng Bai, Bingbing Liu

Abstract: We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robotic navigation, the accurate extraction of environmental structure from raw image sequences is critical for downstream tasks. UniScale addresses this challenge with a single feed-fo… ▽ More We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robotic navigation, the accurate extraction of environmental structure from raw image sequences is critical for downstream tasks. UniScale addresses this challenge with a single feed-forward network that jointly estimates camera intrinsics and extrinsics, scale-invariant depth and point maps, and the metric scale of a scene from multi-view images, while optionally incorporating auxiliary geometric priors when available. By combining global contextual reasoning with camera-aware feature representations, UniScale is able to recover the metric-scale of the scene. In robotic settings where camera intrinsics are known, they can be easily incorporated to improve performance, with additional gains obtained when camera poses are also available. This co-design enables robust, metric-aware 3D reconstruction within a single unified model. Importantly, UniScale does not require training from scratch, and leverages world priors exhibited in pre-existing models without geometric encoding strategies, making it particularly suitable for resource-constrained robotic teams. We evaluate UniScale on multiple benchmarks, demonstrating strong generalization and consistent performance across diverse environments. We will release our implementation upon acceptance. △ Less

Submitted 26 February, 2026; originally announced February 2026.

MoDora: Tree-Based Semi-Structured Document Analysis System

Authors: Bangrui Xu, Qihang Yao, Zirui Tang, Xuanhe Zhou, Yeye He, Shihan Yu, Qianqian Xu, Bin Wang, Guoliang Li, Conghui He, Fan Wu

Abstract: Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irregular layouts. These documents are widely observed across domains and account for a large portion of real-world data. However, existing methods struggle to support natural language question answering over these documents due to three main technical… ▽ More Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irregular layouts. These documents are widely observed across domains and account for a large portion of real-world data. However, existing methods struggle to support natural language question answering over these documents due to three main technical challenges: (1) The elements extracted by techniques like OCR are often fragmented and stripped of their original semantic context, making them inadequate for analysis. (2) Existing approaches lack effective representations to capture hierarchical structures within documents (e.g., associating tables with nested chapter titles) and to preserve layout-specific distinctions (e.g., differentiating sidebars from main content). (3) Answering questions often requires retrieving and aligning relevant information scattered across multiple regions or pages, such as linking a descriptive paragraph to table cells located elsewhere in the document. To address these issues, we propose MoDora, an LLM-powered system for semi-structured document analysis. First, we adopt a local-alignment aggregation strategy to convert OCR-parsed elements into layout-aware components, and conduct type-specific information extraction for components with hierarchical titles or non-text elements. Second, we design the Component-Correlation Tree (CCTree) to hierarchically organize components, explicitly modeling inter-component relations and layout distinctions through a bottom-up cascade summarization process. Finally, we propose a question-type-aware retrieval strategy that supports (1) layout-based grid partitioning for location-based retrieval and (2) LLM-guided pruning for semantic-based retrieval. Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy. The code is at https://github.com/weAIDB/MoDora. △ Less

Submitted 27 February, 2026; v1 submitted 26 February, 2026; originally announced February 2026.

Comments: Extension of our SIGMOD 2026 paper. Please refer to source code available at https://github.com/weAIDB/MoDora

Generative Recommendation for Large-Scale Advertising

Authors: Ben Xue, Dan Liu, Lixiang Wang, Mingjie Sun, Peng Wang, Pengfei Zhang, Shaoyun Shi, Tianyu Xu, Yunhao Sha, Zhiqiang Liu, Bo Kong, Bo Wang, Hang Yang, Jieting Xue, Junhao Wang, Shengyu Wang, Shuping Hui, Wencai Ye, Xiao Lin, Yongzhi Li, Yuhang Chen, Zhihui Yin, Quan Chen, Shiyang Wen, Wenjin Wu , et al. (5 additional authors not shown)

Abstract: Generative recommendation has recently attracted widespread attention in industry due to its potential for scaling and stronger model capacity. However, deploying real-time generative recommendation in large-scale advertising requires designs beyond large-language-model (LLM)-style training and serving recipes. We present a production-oriented generative recommender co-designed across architecture… ▽ More Generative recommendation has recently attracted widespread attention in industry due to its potential for scaling and stronger model capacity. However, deploying real-time generative recommendation in large-scale advertising requires designs beyond large-language-model (LLM)-style training and serving recipes. We present a production-oriented generative recommender co-designed across architecture, learning, and serving, named GR4AD (Generative Recommendation for ADdvertising). As for tokenization, GR4AD proposes UA-SID (Unified Advertisement Semantic ID) to capture complicated business information. Furthermore, GR4AD introduces LazyAR, a lazy autoregressive decoder that relaxes layer-wise dependencies for short, multi-candidate generation, preserving effectiveness while reducing inference cost, which facilitates scaling under fixed serving budgets. To align optimization with business value, GR4AD employs VSL (Value-Aware Supervised Learning) and proposes RSPO (Ranking-Guided Softmax Preference Optimization), a ranking-aware, list-wise reinforcement learning algorithm that optimizes value-based rewards under list-level metrics for continual online updates. For online inference, we further propose dynamic beam serving, which adapts beam width across generation levels and online load to control compute. Large-scale online A/B tests show up to 4.2% ad revenue improvement over an existing DLRM-based stack, with consistent gains from both model scaling and inference-time scaling. GR4AD has been fully deployed in Kuaishou advertising system with over 400 million users and achieves high-throughput real-time serving. △ Less

Submitted 1 April, 2026; v1 submitted 26 February, 2026; originally announced February 2026.

Comments: 13 pages, 6 figures, under review

RADAR: Reasoning as Discrimination with Aligned Representations for LLM-based Knowledge Graph Reasoning

Authors: Bo Xue, Yuan Jin, Luoyi Fu, Jiaxin Ding, Xinbing Wang

Abstract: Knowledge graph reasoning (KGR) infers missing facts, with recent advances increasingly harnessing the semantic priors and reasoning abilities of Large Language Models (LLMs). However, prevailing generative paradigms are prone to memorizing surface-level co-occurrences rather than learning genuine relational semantics, limiting out-of-distribution generalization. To address this, we propose RADAR,… ▽ More Knowledge graph reasoning (KGR) infers missing facts, with recent advances increasingly harnessing the semantic priors and reasoning abilities of Large Language Models (LLMs). However, prevailing generative paradigms are prone to memorizing surface-level co-occurrences rather than learning genuine relational semantics, limiting out-of-distribution generalization. To address this, we propose RADAR, which reformulates KGR from generative pattern matching to discriminative relational reasoning. We recast KGR as discriminative entity selection, where reinforcement learning enforces relative entity separability beyond token-likelihood imitation. Leveraging this separability, inference operates directly in representation space, ensuring consistency with the discriminative optimization and bypassing generation-induced hallucinations. Across four benchmarks, RADAR achieves 5-6% relative gains on link prediction and triple classification over strong LLM baselines, while increasing task-relevant mutual information in intermediate representations by 62.9%, indicating more robust and transferable relational reasoning. △ Less

Submitted 25 February, 2026; originally announced February 2026.