Showing 1–50 of 314 results for author: Mao, D

Adaptive Spiking Neurons for Vision and Language Modeling

Authors: Chenlin Zhou, Sihang Guo, Jiaqi Wang, Dongyang Ma, Jin Cheng, Qingyan Meng, Zhengyu Ma, Yonghong Tian

Abstract: Regarded as the third generation of neural networks, Spiking Neural Networks (SNNs) have garnered significant traction due to their biological plausibility and energy efficiency. Recent advancements in large models necessitate spiking neurons capable of high performance, adaptability, and training efficiency. In this work, we first propose a novel functional perspective that provides general guida… ▽ More Regarded as the third generation of neural networks, Spiking Neural Networks (SNNs) have garnered significant traction due to their biological plausibility and energy efficiency. Recent advancements in large models necessitate spiking neurons capable of high performance, adaptability, and training efficiency. In this work, we first propose a novel functional perspective that provides general guidance for designing the new generation of spiking neurons. Following the insightful guidelines, we propose the Adaptive Spiking Neuron (ASN), which incorporates trainable parameters to learn membrane potential dynamics and enable adaptive firing. ASN adopts an integer training and spike inference paradigm, facilitating efficient SNN training. To further enhance robustness, we propose a specialized variant of ASN, the Normalized Adaptive Spiking Neuron (NASN), which integrates normalization to stabilize training. We evaluate our neuron model on 19 datasets spanning five distinct tasks in both vision and language modalities, demonstrating the effectiveness and versatility of the ASN family. Our ASN family is expected to become the new generation of general-purpose spiking neurons. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Comments: 10 pages

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks

Authors: Junlin Liu, Shengnan An, Shuang Zhou, Dan Ma, Shixiong Luo, Ying Xie, Yuan Zhang, Wenling Yuan, Yifan Zhou, Xiaoyu Li, Ziwen Wang, Xuezhi Cao, Xunliang Cai

Abstract: Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics. However, their ability to generalize these reasoning skills to more general and broader contexts--often termed general reasoning--remains under-explored. Unlike domain-specific reasoning, general reasoning relies less on expert knowledge b… ▽ More Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics. However, their ability to generalize these reasoning skills to more general and broader contexts--often termed general reasoning--remains under-explored. Unlike domain-specific reasoning, general reasoning relies less on expert knowledge but still presents formidable reasoning challenges, such as complex constraints, nested logical branches, and semantic interference. To address this gap, we introduce General365, a benchmark specifically designed to assess general reasoning in LLMs. By restricting background knowledge to a K-12 level, General365 explicitly decouples reasoning from specialized expertise. The benchmark comprises 365 seed problems and 1,095 variant problems across eight categories, ensuring both high difficulty and diversity. Evaluations across 26 leading LLMs reveal that even the top-performing model achieves only 62.8% accuracy, in stark contrast to the near-perfect performances of LLMs in math and physics benchmarks. These results suggest that the reasoning abilities of current LLMs are heavily domain-dependent, leaving significant room for improvement in broader applications. We envision General365 as a catalyst for advancing LLM reasoning beyond domain-specific tasks toward robust, general-purpose real-world scenarios. Code, Dataset, and Leaderboard: https://general365.github.io △ Less

Submitted 13 April, 2026; originally announced April 2026.

Comments: 17 pages, 9 figures

Winner-Take-All Spiking Transformer for Language Modeling

Authors: Chenlin Zhou, Sihang Guo, Jiaqi Wang, Dongyang Ma, Kaiwei Che, Baiyu Chen, Qingyan Meng, Zhengyu Ma, Yonghong Tian

Abstract: Spiking Transformers, which combine the scalability of Transformers with the sparse, energy-efficient property of Spiking Neural Networks (SNNs), have achieved impressive results in neuromorphic and vision tasks and attracted increasing attention. However, existing directly trained spiking transformers primarily focus on vision tasks. For language modeling with spiking transformer, convergence rel… ▽ More Spiking Transformers, which combine the scalability of Transformers with the sparse, energy-efficient property of Spiking Neural Networks (SNNs), have achieved impressive results in neuromorphic and vision tasks and attracted increasing attention. However, existing directly trained spiking transformers primarily focus on vision tasks. For language modeling with spiking transformer, convergence relies heavily on softmax-based spiking self-attention, which incurs high energy costs and poses challenges for neuromorphic deployment. To address this issue, we introduce Winner-Take-All (WTA) mechanisms into spiking transformers and propose two novel softmax-free, spike-driven self-attention modules: WTA Spiking Self-Attention (WSSA) and Causal WTA Spiking Self-Attention (CWSSA). Based on them, we design WTA-based Encoder-only Spiking Transformer (WE-Spikingformer) for masked language modeling and WTA-based Decoder-only Spiking Transformer (WD-Spikingformer) for causal language modeling, systematically exploring softmax-free, spiking-driven Transformer architectures trained end-to-end for natural language processing tasks. Extensive experiments on 16 datasets spanning natural language understanding, question-answering tasks, and commonsense reasoning tasks validate the effectiveness of our approach and highlight the promise of spiking transformers for general language modeling and energy-efficient artificial intelligence. △ Less

Submitted 13 April, 2026; originally announced April 2026.

Comments: 15 pages

Towards Situation-aware State Modeling for Air Traffic Flow Prediction

Authors: Anqi Liu, Bin Wang, Jiangtao Zhao, Dechuan Ma, Guiyuan Jiang, Feng Hong, Yanwei Yu, Tianrui Li

Abstract: Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on time series-based forecasting paradigms, which inherently overlook critical aircraft state information, such as real-time kinematics and proximity to airspace boundaries. To address this limitation, we propose \textit{Ae… ▽ More Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on time series-based forecasting paradigms, which inherently overlook critical aircraft state information, such as real-time kinematics and proximity to airspace boundaries. To address this limitation, we propose \textit{AeroSense}, a direct state-to-flow modeling framework for air traffic prediction. Unlike classical time series-based methods that first aggregate aircraft trajectories into macroscopic flow sequences before modeling, AeroSense explicitly represents the real-time airspace situation as \textit{a dynamic set of aircraft states}, enabling the direct processing of a variable number of aircraft instead of time series as inputs. Specifically, we introduce a situation-aware state representation that enables AeroSense to sense the instantaneous terminal airspace situation directly from microscopic aircraft states. Furthermore, we design a model architecture that incorporates masked self-attention to capture inter-aircraft interactions, together with two decoupled prediction heads to model heterogeneous flow dynamics across two key functional areas of the TA. Extensive experiments on a large-scale real-world airport dataset demonstrate that AeroSense consistently achieves state-of-the-art performance, validating that direct modeling of microscopic aircraft states yields substantially higher predictive fidelity than time series-based baselines. Moreover, the proposed framework exhibits superior robustness during peak traffic periods, achieves Pareto-optimal performance under dayparting multi-object evaluation, and provides meaningful interpretability through attention-based visualizations. △ Less

Submitted 14 April, 2026; v1 submitted 13 April, 2026; originally announced April 2026.

Comments: There are issues with the authors of the paper I submitted, as well as problems with the content of the article, so it needs to be withdrawn. Thank you for your understanding

Bottleneck Tokens for Unified Multimodal Retrieval

Authors: Siyu Sun, Jing Ren, Zhaohe Liao, Dongxiao Mao, Xiangyuan Ren, Yiyi Zhang, Haohua Zhao, Weixiong Lin, Jiang Shaohua, Liqing Zhang, Yuchao Zheng

Abstract: Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary token (e.g., <EOS>) as the sequence-level representation, a mechanism never designed for information aggregation. Second, contrastive fine-tuning specifies what the embe… ▽ More Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary token (e.g., <EOS>) as the sequence-level representation, a mechanism never designed for information aggregation. Second, contrastive fine-tuning specifies what the embedding should match but provides no token-level guidance on how information should be compressed into it. We address both gaps with two complementary components. Architecturally, we introduce Bottleneck Tokens (BToks), a small set of learnable tokens that serve as a fixed-capacity explicit pooling mechanism. For training, we propose Generative Information Condensation: a next-token prediction objective coupled with a Condensation Mask that severs the direct attention path from target tokens to query tokens. All predictive signals are thereby forced through the BToks, converting the generative loss into dense, token-level supervision for semantic compression. At inference time, only the input and BToks are processed in a single forward pass with negligible overhead over conventional last-token pooling. On MMEB-V2 (78 datasets, 3 modalities, 9 meta-tasks), our approach achieves state-of-the-art among 2B-scale methods under comparable data conditions, attaining an Overall score of 59.0 (+3.6 over VLM2Vec-V2) with substantial gains on semantically demanding tasks (e.g., +12.6 on Video-QA). △ Less

Submitted 13 April, 2026; originally announced April 2026.

LogAct: Enabling Agentic Reliability via Shared Logs

Authors: Mahesh Balakrishnan, Ashwin Bharambe, Davide Testuggine, David Geraghty, David Mao, Vidhya Venkat, Ilya Mironov, Rithesh Baradi, Gayathri Aiyer, Victoria Dudin

Abstract: Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we propose a new abstraction called LogAct, where each agent is a deconstructed state machine playing a shared log. In LogAct, agentic actions are visible in the shar… ▽ More Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we propose a new abstraction called LogAct, where each agent is a deconstructed state machine playing a shared log. In LogAct, agentic actions are visible in the shared log before they are executed; can be stopped prior to execution by pluggable, decoupled voters; and recovered consistently in the case of agent or environment failure. LogAct enables agentic introspection, allowing the agent to analyze its own execution history using LLM inference, which in turn enables semantic variants of recovery, health check, and optimization. In our evaluation, LogAct agents recover efficiently and correctly from failures; debug their own performance; optimize token usage in swarms; and stop all unwanted actions for a target model on a representative benchmark with just a 3% drop in benign utility. △ Less

Submitted 9 April, 2026; originally announced April 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

CharTool: Tool-Integrated Visual Reasoning for Chart Understanding

Authors: Situo Zhang, Yifan Zhang, Zichen Zhu, Da Ma, Lei Pan, Danyang Zhang, Zihan Zhao, Lu Chen, Kai Yu

Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multimodal large language models (MLLMs) due to the lack of high-quality training data, as well as the need for fine-grained visual grounding and precise numerical computation. To address these challenges, we first propose DuoChart, a scalable dual-source da… ▽ More Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multimodal large language models (MLLMs) due to the lack of high-quality training data, as well as the need for fine-grained visual grounding and precise numerical computation. To address these challenges, we first propose DuoChart, a scalable dual-source data pipeline that combines synthesized charts with real-world charts to construct diverse, high-quality chart training data. We then introduce CharTool, which equips MLLMs with external tools, including image cropping for localized visual perception and code-based computation for accurate numerical reasoning. Through agentic reinforcement learning on DuoChart, CharTool learns tool-integrated reasoning grounded in chart content. Extensive experiments on six chart benchmarks show that our method consistently improves over strong MLLM baselines across model scales. Notably, CharTool-7B outperforms the base model by **+8.0%** on CharXiv (Reasoning) and **+9.78%** on ChartQAPro, while achieving competitive performance with substantially larger or proprietary models. Moreover, CharTool demonstrates positive generalization to out-of-domain visual math reasoning benchmarks. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Learning ECG Image Representations via Dual Physiological-Aware Alignments

Authors: Hung Manh Pham, Jialu Tang, Aaqib Saeed, Dong Ma, Bin Zhu, Pan Zhou

Abstract: Electrocardiograms (ECGs) are among the most widely used diagnostic tools for cardiovascular diseases, and a large amount of ECG data worldwide appears only in image form. However, most existing automated ECG analysis methods rely on access to raw signal recordings, limiting their applicability in real-world and resource-constrained settings. In this paper, we present ECG-Scan, a self-supervised f… ▽ More Electrocardiograms (ECGs) are among the most widely used diagnostic tools for cardiovascular diseases, and a large amount of ECG data worldwide appears only in image form. However, most existing automated ECG analysis methods rely on access to raw signal recordings, limiting their applicability in real-world and resource-constrained settings. In this paper, we present ECG-Scan, a self-supervised framework for learning clinically generalized representations from ECG images through dual physiological-aware alignments: 1) Our approach optimizes image representation learning using multimodal contrastive alignment between image and gold-standard signal-text modalities. 2) We further integrate domain knowledge via soft-lead constraints, regularizing the reconstruction process and improving signal lead inter-consistency. Extensive benchmarking across multiple datasets and downstream tasks demonstrates that our image-based model achieves superior performance compared to existing image baselines and notably narrows the gap between ECG image and signal analysis. These results highlight the potential of self-supervised image modeling to unlock large-scale legacy ECG data and broaden access to automated cardiovascular diagnostics. △ Less

Submitted 1 April, 2026; originally announced April 2026.

POSIM: A Multi-Agent Simulation Framework for Social Media Public Opinion Evolution and Governance

Authors: Yongmao Zhang, Kai Qiao, Zhengyan Wang, Ningning Liang, Dekui Ma, Wenyao Sun, Jian Chen, Bin Yan

Abstract: Modeling social media public opinion evolution is essential for governance decision-making. Traditional epidemic models and rule-based agent-based models (ABMs) fail to capture the cognitive processes and adaptive behaviors of real users. Recent large language model (LLM)-based social simulations can reproduce group-level phenomena like polarization and conformity, yet remain unable to recreate th… ▽ More Modeling social media public opinion evolution is essential for governance decision-making. Traditional epidemic models and rule-based agent-based models (ABMs) fail to capture the cognitive processes and adaptive behaviors of real users. Recent large language model (LLM)-based social simulations can reproduce group-level phenomena like polarization and conformity, yet remain unable to recreate the irrational interactions and multi-phase dynamics of real public opinion events. We present POSIM (Public Opinion Simulator), a multi-agent simulation framework for social media public opinion evolution and governance. POSIM integrates LLM-driven agents with a Belief--Desire--Intention (BDI) cognitive architecture that accounts for irrational factors, places them in a virtual social media environment with social networks and recommendation mechanisms, and drives temporal dynamics through a Hawkes point process engine that captures the co-evolution of agents and the environment across event phases. To validate the framework, we collect real-world public opinion datasets from the Weibo platform covering the full interaction chain of users. Experiments show that POSIM successfully reproduces key characteristics of public opinion evolution from individual mechanisms to collective phenomena, and its effectiveness is further supported by multiple statistical metrics. Building on POSIM, governance-oriented guidance and intervention experiments uncover a counterintuitive empathy paradox: empathetic guidance deepens negative sentiment instead of easing it under certain conditions, offering new insights for governance strategy design. These results demonstrate that the proposed framework can fully serve as a computational experimentation platform for proactive strategy evaluation and evidence-based governance. All source code is available at https://github.com/DeepCogLab/posim/. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Wearable Foundation Models Should Go Beyond Static Encoders

Authors: Yu Yvonne Wu, Yuwei Zhang, Hyungjun Yoon, Ting Dang, Dimitris Spathis, Tong Xia, Qiang Yang, Jing Han, Dong Ma, Sung-Ju Lee, Cecilia Mascolo

Abstract: Wearable foundation models (WFMs), trained on large volumes of data collected by affordable, always-on devices, have demonstrated strong performance on short-term, well-defined health monitoring tasks, including activity recognition, fitness tracking, and cardiovascular signal assessment. However, most existing WFMs primarily map short temporal windows to predefined labels via static encoders, emp… ▽ More Wearable foundation models (WFMs), trained on large volumes of data collected by affordable, always-on devices, have demonstrated strong performance on short-term, well-defined health monitoring tasks, including activity recognition, fitness tracking, and cardiovascular signal assessment. However, most existing WFMs primarily map short temporal windows to predefined labels via static encoders, emphasizing retrospective prediction rather than reasoning over evolving personal history, context, and future risk trajectories. As a result, they are poorly suited for modeling chronic, progressive, or episodic health conditions that unfold over weeks, months or years. Hence, we argue that WFMs must move beyond static encoders and be explicitly designed for longitudinal, anticipatory health reasoning. We identify three foundational shifts required to enable this transition: (1) Structurally rich data, which goes beyond isolated datasets or outcome-conditioned collection to integrated multimodal, long-term personal trajectories, and contextual metadata, ideally supported by open and interoperable data ecosystems; (2) Longitudinal-aware multimodal modeling, which prioritizes long-context inference, temporal abstraction, and personalization over cross-sectional or population-level prediction; and (3) Agentic inference systems, which move beyond static prediction to support planning, decision-making, and clinically grounded intervention under uncertainty. Together, these shifts reframe wearable health monitoring from retrospective signal interpretation toward continuous, anticipatory, and human-aligned health support. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Comments: 13 pages

Upward Spatial Coverage Recovery via Movable Antenna in Low-Altitude Communications

Authors: Kan Yu, Kaixuan Li, Yujia Zhao, Dingyou Ma, Qixun Zhang, Zhiyong Feng

Abstract: The rapid proliferation of unmanned aerial vehicle (UAV) applications imposes stringent requirements on continuous and reliable communication coverage in low-altitude airspace. Conventional cellular systems built upon fixed-position antennas (FPAs) are inherently constrained by static array geometries and limited mechanical degrees of freedom, which severely restrict their ability to adapt to high… ▽ More The rapid proliferation of unmanned aerial vehicle (UAV) applications imposes stringent requirements on continuous and reliable communication coverage in low-altitude airspace. Conventional cellular systems built upon fixed-position antennas (FPAs) are inherently constrained by static array geometries and limited mechanical degrees of freedom, which severely restrict their ability to adapt to highly dynamic three-dimensional (3D) propagation environments. Movable antenna (MA) technology has recently emerged as a promising paradigm to overcome these limitations by actively reconfiguring electromagnetic radiation characteristics through controllable antenna positioning and array orientation, thereby enabling flexible spatial coverage adaptation. To systematically quantify the airspace coverage capability of MA-enabled systems, this paper formulates a spatial coverage maximization problem over a discretized 3D voxel space. For each voxel, the received signal-to-noise ratio (SNR) is maximized via joint optimization of the MA's 3D positions and beamforming matrices. To efficiently solve the resulting non-convex problem, a hybrid particle swarm optimization and simulated annealing framework is developed to search for high-quality antenna configurations. Simulation results demonstrate that the proposed MA design framework substantially outperforms conventional FPA-based schemes in terms of spatial coverage, achieving coverage rates of 26.8% and 29.65% for airspace below 300m and 600m, respectively. Moreover, further coverage enhancement can be attained by incorporating mechanical tilt adjustment, highlighting the strong potential of MA technology for reliable low-altitude communication coverage. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Beyond Polarity: Multi-Dimensional LLM Sentiment Signals for WTI Crude Oil Futures Return Prediction

Authors: Dehao Dai, Ding Ma, Dou Liu, Kerui Geng, Yiqing Wang

Abstract: Forecasting crude oil prices remains challenging because market-relevant information is embedded in large volumes of unstructured news and is not fully captured by traditional polarity-based sentiment measures. This paper examines whether multi-dimensional sentiment signals extracted by large language models improve the prediction of weekly WTI crude oil futures returns. Using energy-sector news a… ▽ More Forecasting crude oil prices remains challenging because market-relevant information is embedded in large volumes of unstructured news and is not fully captured by traditional polarity-based sentiment measures. This paper examines whether multi-dimensional sentiment signals extracted by large language models improve the prediction of weekly WTI crude oil futures returns. Using energy-sector news articles from 2020 to 2025, we construct five sentiment dimensions covering relevance, polarity, intensity, uncertainty, and forwardness based on GPT-4o, Llama 3.2-3b, and two benchmark models, FinBERT and AlphaVantage. We aggregate article-level signals to the weekly level and evaluate their predictive performance in a classification framework. The best results are achieved by combining GPT-4o and FinBERT, suggesting that LLM-based and conventional financial sentiment models provide complementary predictive information. SHAP analysis further shows that intensity- and uncertainty-related features are among the most important predictors, indicating that the predictive value of news sentiment extends beyond simple polarity. Overall, the results suggest that multi-dimensional LLM-based sentiment measures can improve commodity return forecasting and support energy-market risk monitoring. △ Less

Submitted 16 March, 2026; v1 submitted 11 March, 2026; originally announced March 2026.

Comments: 28 pages, 4 figures, 4 tables

G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition

Authors: Jing Peng, Ziyi Chen, Haoyu Li, Yucheng Wang, Duo Ma, Mengtian Li, Yunfan Du, Dezhu Xu, Kai Yu, Shuai Wang

Abstract: We study timestamped speaker-attributed ASR for long-form, multi-party speech with overlap, where chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Previous Speech-LLM systems tend to prioritize either local diarization or global labeling, but often lack the ability to capture fine-grained temporal boundaries or… ▽ More We study timestamped speaker-attributed ASR for long-form, multi-party speech with overlap, where chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Previous Speech-LLM systems tend to prioritize either local diarization or global labeling, but often lack the ability to capture fine-grained temporal boundaries or robust cross-chunk identity linking. We propose G-STAR, an end-to-end system that couples a time-aware speaker-tracking module with a Speech-LLM transcription backbone. The tracker provides structured speaker cues with temporal grounding, and the LLM generates attributed text conditioned on these cues. G-STAR supports both component-wise optimization and joint end-to-end training, enabling flexible learning under heterogeneous supervision and domain shift. Experiments analyze cue fusion, local versus long-context trade-offs and hierarchical objectives. △ Less

Submitted 11 March, 2026; originally announced March 2026.

Comments: submitted to Interspeech 2026

Virtual Intraoperative CT (viCT): Sequential Anatomic Updates for Modeling Tissue Resection Throughout Endoscopic Sinus Surgery

Authors: Nicole M. Gunderson, Graham J. Harris, Jeremy S. Ruthberg, Pengcheng Chen, Di Mao, Randall A. Bly, Waleed M. Abuzeid, Eric J. Seibel

Abstract: Purpose: Incomplete dissection is a common cause of persistent disease and revision endoscopic sinus surgery (ESS) in chronic rhinosinusitis. Current image-guided surgery systems typically reference static preoperative CT (pCT), and do not model evolving resection boundaries. We present Virtual Intraoperative CT (viCT), a method for sequentially updating pCT throughout ESS using intraoperative 3D… ▽ More Purpose: Incomplete dissection is a common cause of persistent disease and revision endoscopic sinus surgery (ESS) in chronic rhinosinusitis. Current image-guided surgery systems typically reference static preoperative CT (pCT), and do not model evolving resection boundaries. We present Virtual Intraoperative CT (viCT), a method for sequentially updating pCT throughout ESS using intraoperative 3D reconstructions from monocular endoscopic video to enable visualization of evolving anatomy in CT format. Methods: Monocular endoscopic video is processed using a depth-supervised NeRF framework with virtual stereo synthesis to generate metrically scaled 3D reconstructions at multiple surgical intervals. Reconstructions undergo rigid, landmark-based registration in 3D Slicer guided by anatomical correspondences, and are then voxelized into the pCT grid. viCT volumes were generated using a ray-based occupancy comparison between pCT and reconstruction to delete outdated voxels and remap preserved anatomy and updated boundaries. Performance is evaluated in a cadaveric feasibility study of four specimens across four ESS stages using volumetric overlap (DSC, Jaccard) and surface metrics (HD95, Chamfer, MSD, RMSD), and qualitative comparisons to ground-truth CT. Results: viCT updates show agreement with ground-truth anatomy across surgical stages, with submillimeter mean surface errors. Dice Similarity Coefficient (DSC) = 0.88 +/- 0.05 and Jaccard Index = 0.79 +/- 0.07, and Hausdorff Distance 95% (HD95) = 0.69 +/- 0.28 mm, Chamfer Distance = 0.09 +/- 0.05 mm, Mean Surface Distance (MSD) = 0.11 +/- 0.05 mm, and Root Mean Square Distance (RMSD) = 0.32 +/- 0.10 mm. Conclusion: viCT enables CT-format anatomic updating in an ESS setting without ancillary hardware. Future work will focus on fully automating registration, validation in live cases, and optimizing runtime for real-time deployment. △ Less

Submitted 6 March, 2026; originally announced March 2026.

PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning

Authors: Hung Manh Pham, Jinyang Wu, Xiao Ma, Yiming Zhang, Yixin Xu, Aaqib Saeed, Bin Zhu, Zhou Pan, Dong Ma

Abstract: Photoplethysmography (PPG) is a widely used non-invasive sensing modality for continuous cardiovascular and physiological monitoring across clinical, laboratory, and wearable settings. While existing PPG datasets support a broad range of downstream tasks, they typically provide supervision in the form of numerical measurements or task-specific labels, limiting their suitability for language-based… ▽ More Photoplethysmography (PPG) is a widely used non-invasive sensing modality for continuous cardiovascular and physiological monitoring across clinical, laboratory, and wearable settings. While existing PPG datasets support a broad range of downstream tasks, they typically provide supervision in the form of numerical measurements or task-specific labels, limiting their suitability for language-based physiological reasoning and multimodal foundation models. In this work, we introduce PulseLM, a large-scale PPG-text dataset designed to bridge raw PPG waveforms and natural language through a unified, closed-ended question answering (QA) formulation. PulseLM aggregates PPG recordings from fifteen publicly available sources and harmonizes heterogeneous annotations into twelve common physiologically QA tasks. The dataset comprises 1.31 million standardized 10-second PPG segments, associated with 3.15 million question-answer pairs. We further define reproducible preprocessing, supervision, and evaluation protocols and establish baseline benchmarks using multimodal PPG-aware large language models. PulseLM provides a standardized foundation for studying multimodal physiological reasoning, cross-dataset generalization, and scalable benchmarking of PPG-based language models. The data and code can be found publicly available at: https://github.com/manhph2211/PulseLM. △ Less

Submitted 10 February, 2026; originally announced March 2026.

Comments: PulseLM v1

LLMs for High-Frequency Decision-Making: Normalized Action Reward-Guided Consistency Policy Optimization

Authors: Yang Zhao, Zihao Li, Zhiyu Jiang, Dandan Ma, Ganchao Liu, Wenzhe Zhao

Abstract: While Large Language Models (LLMs) form the cornerstone of sequential decision-making agent development, they have inherent limitations in high-frequency decision tasks. Existing research mainly focuses on discrete embodied decision scenarios with low-frequency and significant semantic differences in state space (e.g., household planning). These methods suffer from limited performance in high-freq… ▽ More While Large Language Models (LLMs) form the cornerstone of sequential decision-making agent development, they have inherent limitations in high-frequency decision tasks. Existing research mainly focuses on discrete embodied decision scenarios with low-frequency and significant semantic differences in state space (e.g., household planning). These methods suffer from limited performance in high-frequency decision-making tasks, since high-precision numerical state information in such tasks undergoes frequent updates with minimal fluctuations, and exhibiting policy misalignment between the learned sub-tasks and composite tasks. To address these issues, this paper proposes Normalized Action Reward guided Consistency Policy Optimization (NAR-CP). 1) Our method first acquires predefined dense rewards from environmental feedback of candidate actions via reward functions, then completes reward shaping through normalization, and theoretically verifies action reward normalization does not impair optimal policy. 2) To reduce policy misalignment in composite tasks, we use LLMs to infer sub-observation candidate actions and generate joint policies, with consistency loss ensuring precise alignment between global semantic policies and sub-semantic policies. Experiments on UAV pursuit, a typical high-frequency task, show our method delivers superior performance on independent and composite tasks with excellent generalization to unseen tasks. △ Less

Submitted 3 March, 2026; originally announced March 2026.

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation

Authors: Zhengren Wang, Dongsheng Ma, Huaping Zhong, Jiayu Li, Wentao Zhang, Bin Wang, Conghui He

Abstract: The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a natural starting point, it creates a critical bottleneck: delivering entire pages to the generator introduces excessive extraneous context. This not only overloads the generator's… ▽ More The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a natural starting point, it creates a critical bottleneck: delivering entire pages to the generator introduces excessive extraneous context. This not only overloads the generator's attention mechanism but also dilutes the most salient evidence. Moreover, compressing these information-rich pages into a limited visual token budget further increases the risk of hallucinations. To address this, we introduce AgenticOCR, a dynamic parsing paradigm that transforms optical character recognition (OCR) from a static, full-text process into a query-driven, on-demand extraction system. By autonomously analyzing document layout in a "thinking with images" manner, AgenticOCR identifies and selectively recognizes regions of interest. This approach performs on-demand decompression of visual tokens precisely where needed, effectively decoupling retrieval granularity from rigid page-level chunking. AgenticOCR has the potential to serve as the "third building block" of the visual document RAG stack, operating alongside and enhancing standard Embedding and Reranking modules. Experimental results demonstrate that AgenticOCR improves both the efficiency and accuracy of visual RAG systems, achieving expert-level performance in long document understanding. Code and models are available at https://github.com/OpenDataLab/AgenticOCR. △ Less

Submitted 27 February, 2026; originally announced February 2026.

SAGE-LLM: Towards Safe and Generalizable LLM Controller with Fuzzy-CBF Verification and Graph-Structured Knowledge Retrieval for UAV Decision

Authors: Wenzhe Zhao, Yang Zhao, Ganchao Liu, Zhiyu Jiang, Dandan Ma, Zihao Li, Xuelong Li

Abstract: In UAV dynamic decision, complex and variable hazardous factors pose severe challenges to the generalization capability of algorithms. Despite offering semantic understanding and scene generalization, Large Language Models (LLM) lack domain-specific UAV control knowledge and formal safety assurances, restricting their direct applicability. To bridge this gap, this paper proposes a train-free two-l… ▽ More In UAV dynamic decision, complex and variable hazardous factors pose severe challenges to the generalization capability of algorithms. Despite offering semantic understanding and scene generalization, Large Language Models (LLM) lack domain-specific UAV control knowledge and formal safety assurances, restricting their direct applicability. To bridge this gap, this paper proposes a train-free two-layer decision architecture based on LLMs, integrating high-level safety planning with low-level precise control. The framework introduces three key contributions: 1) A fuzzy Control Barrier Function verification mechanism for semantically-augmented actions, providing provable safety certification for LLM outputs. 2) A star-hierarchical graph-based retrieval-augmented generation system, enabling efficient, elastic, and interpretable scene adaptation. 3) Systematic experimental validation in pursuit-evasion scenarios with unknown obstacles and emergent threats, demonstrating that our SAGE-LLM maintains performance while significantly enhancing safety and generalization without online training. The proposed framework demonstrates strong extensibility, suggesting its potential for generalization to broader embodied intelligence systems and safety-critical control domains. △ Less

Submitted 27 February, 2026; originally announced February 2026.

SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation

Authors: Jingzhuo Wu, Jiajun Zhang, Keyan Jin, Dehua Ma, Junbo Wang

Abstract: Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing semantically correct but generic outputs. This limitation stems from the inability of current single-model and static multi-agent systems to perceive and adapt to stylistic variations. To address this, we introduce the Style… ▽ More Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing semantically correct but generic outputs. This limitation stems from the inability of current single-model and static multi-agent systems to perceive and adapt to stylistic variations. To address this, we introduce the Style-Adaptive Multi-Agent System (SAMAS), a novel framework that treats style preservation as a signal processing task. Specifically, our method quantifies literary style into a Stylistic Feature Spectrum (SFS) using the wavelet packet transform. This SFS serves as a control signal to dynamically assemble a tailored workflow of specialized translation agents based on the source text's structural patterns. Extensive experiments on translation benchmarks show that SAMAS achieves competitive semantic accuracy against strong baselines, primarily by leveraging its statistically significant advantage in style fidelity. △ Less

Submitted 23 February, 2026; originally announced February 2026.

The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context

Authors: Xiaoyuan Liu, Tian Liang, Dongyang Ma, Deyu Zhou, Haitao Mi, Pinjia He, Yan Wang

Abstract: In the world of Harry Potter, when Dumbledore's mind is overburdened, he extracts memories into a Pensieve to be revisited later. In the world of AI, while we possess the Pensieve-mature databases and retrieval systems, our models inexplicably lack the "wand" to operate it. They remain like a Dumbledore without agency, passively accepting a manually engineered context as their entire memory. This… ▽ More In the world of Harry Potter, when Dumbledore's mind is overburdened, he extracts memories into a Pensieve to be revisited later. In the world of AI, while we possess the Pensieve-mature databases and retrieval systems, our models inexplicably lack the "wand" to operate it. They remain like a Dumbledore without agency, passively accepting a manually engineered context as their entire memory. This work finally places the wand in the model's hand. We introduce StateLM, a new class of foundation models endowed with an internal reasoning loop to manage their own state. We equip our model with a suite of memory tools, such as context pruning, document indexing, and note-taking, and train it to actively manage these tools. By learning to dynamically engineering its own context, our model breaks free from the architectural prison of a fixed window. Experiments across various model sizes demonstrate StateLM's effectiveness across diverse scenarios. On long-document QA tasks, StateLMs consistently outperform standard LLMs across all model scales; on the chat memory task, they achieve absolute accuracy improvements of 10% to 20% over standard LLMs. On the deep research task BrowseComp-Plus, the performance gap becomes even more pronounced: StateLM achieves up to 52% accuracy, whereas standard LLM counterparts struggle around 5%. Ultimately, our approach shifts LLMs from passive predictors to state-aware agents where reasoning becomes a stateful and manageable process. △ Less

Submitted 12 February, 2026; originally announced February 2026.

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Authors: Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao, Bo Dong, Bojun Wang, Boyu Chen, Brian Li, Buyun Ma, Chang Su, Changxin Miao, Changyi Wan, Chao Lou, Chen Hu, Chen Xu, Chenfeng Yu, Chengting Feng, Chengyuan Yao, Chunrui Han, Dan Ma, Dapeng Shi, Daxin Jiang, Dehua Ma, Deshan Sun , et al. (191 additional authors not shown)

Abstract: We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/f… ▽ More We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments. △ Less

Submitted 23 February, 2026; v1 submitted 11 February, 2026; originally announced February 2026.

Comments: Technical report for Step 3.5 Flash

Free(): Learning to Forget in Malloc-Only Reasoning Models

Authors: Yilun Zheng, Dongyang Ma, Tian Liang, Jiahao Xu, Xinting Huang, Lihui Chen, Haitao Mi, Yan Wang

Abstract: Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance rather than improve it. We attribute this to a fundamental architectural flaw: standard LLMs operate as "malloc-only" engines, continuously accumulating valid and redundant steps alike without a mechanism to prune obsolete information. To brea… ▽ More Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance rather than improve it. We attribute this to a fundamental architectural flaw: standard LLMs operate as "malloc-only" engines, continuously accumulating valid and redundant steps alike without a mechanism to prune obsolete information. To break this cycle, we propose Free()LM, a model that introduces an intrinsic self-forgetting capability via the Free-Module, a plug-and-play LoRA adapter. By iteratively switching between reasoning and cleaning modes, Free()LM dynamically identifies and prunes useless context chunks, maintaining a compact and noise-free state. Extensive experiments show that Free()LM provides consistent improvements across all model scales (8B to 685B). It achieves a 3.3% average improvement over top-tier reasoning baselines, even establishing a new SOTA on IMOanswerBench using DeepSeek V3.2-Speciale. Most notably, in long-horizon tasks where the standard Qwen3-235B-A22B model suffers a total collapse (0% accuracy), Free()LM restores performance to 50%. Our findings suggest that sustainable intelligence requires the freedom to forget as much as the power to think. △ Less

Submitted 10 February, 2026; v1 submitted 8 February, 2026; originally announced February 2026.

Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories

Authors: Sidi Lu, Zhenwen Liang, Dongyang Ma, Yan Wang, Haitao Mi, Dong Yu

Abstract: In this paper, we aim to bridge test-time-training with a new type of parametric memory that can be flexibly offloaded from or merged into model parameters. We present Locas, a Locally-Supported parametric memory that shares the design of FFN blocks in modern transformers, allowing it to be flexibly permanentized into the model parameters while supporting efficient continual learning. We discuss t… ▽ More In this paper, we aim to bridge test-time-training with a new type of parametric memory that can be flexibly offloaded from or merged into model parameters. We present Locas, a Locally-Supported parametric memory that shares the design of FFN blocks in modern transformers, allowing it to be flexibly permanentized into the model parameters while supporting efficient continual learning. We discuss two major variants of Locas: one with a conventional two-layer MLP design that has a clearer theoretical guarantee; the other one shares the same GLU-FFN structure with SOTA LLMs, and can be easily attached to existing models for both parameter-efficient and computation-efficient continual learning. Crucially, we show that proper initialization of such low-rank sideway-FFN-style memories -- performed in a principled way by reusing model parameters, activations and/or gradients -- is essential for fast convergence, improved generalization, and catastrophic forgetting prevention. We validate the proposed memory mechanism on the PG-19 whole-book language modeling and LoCoMo long-context dialogue question answering tasks. With only 0.02\% additional parameters in the lowest case, Locas-GLU is capable of storing the information from past context while maintaining a much smaller context window. In addition, we also test the model's general capability loss after memorizing the whole book with Locas, through comparative MMLU evaluation. Results show the promising ability of Locas to permanentize past context into parametric knowledge with minimized catastrophic forgetting of the model's existing internal knowledge. △ Less

Submitted 4 February, 2026; originally announced February 2026.

Comments: Tencent AI Lab Technical Report

PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length

Authors: Situo Zhang, Yifan Zhang, Zichen Zhu, Hankun Wang, Da Ma, Danyang Zhang, Lu Chen, Kai Yu

Abstract: Speculative decoding (SD) is a powerful technique for accelerating the inference process of large language models (LLMs) without sacrificing accuracy. Typically, SD employs a small draft model to generate a fixed number of draft tokens, which are then verified in parallel by the target model. However, our experiments reveal that the optimal draft length varies significantly across different decodi… ▽ More Speculative decoding (SD) is a powerful technique for accelerating the inference process of large language models (LLMs) without sacrificing accuracy. Typically, SD employs a small draft model to generate a fixed number of draft tokens, which are then verified in parallel by the target model. However, our experiments reveal that the optimal draft length varies significantly across different decoding steps. This variation suggests that using a fixed draft length limits the potential for further improvements in decoding speed. To address this challenge, we propose Pacer, a novel approach that dynamically controls draft length using a lightweight, trainable pre-verification layer. This layer pre-verifies draft tokens blockwise before they are sent to the target model, allowing the draft model to stop token generation if the blockwise pre-verification fails. We implement Pacer on multiple SD model pairs and evaluate its performance across various benchmarks. Our results demonstrate that Pacer achieves up to 2.66x Speedup over autoregressive decoding and consistently outperforms standard speculative decoding. Furthermore, when integrated with Ouroboros, Pacer attains up to 3.09x Speedup. △ Less

Submitted 1 February, 2026; originally announced February 2026.

Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis

Authors: Zicheng Kong, Dehua Ma, Zhenbo Xu, Alven Yang, Yiwei Ru, Haoran Wang, Zixuan Zhou, Fuqing Bie, Liuyu Xiang, Huijia Wu, Jian Zhao, Zhaofeng He

Abstract: Multimodal large language models (MLLMs) have shown remarkable capabilities, yet their performance is often capped by the coarse nature of existing alignment techniques. A critical bottleneck remains the lack of effective reward models (RMs): existing RMs are predominantly vision-centric, return opaque scalar scores, and rely on costly human annotations. We introduce \textbf{Omni-RRM}, the first o… ▽ More Multimodal large language models (MLLMs) have shown remarkable capabilities, yet their performance is often capped by the coarse nature of existing alignment techniques. A critical bottleneck remains the lack of effective reward models (RMs): existing RMs are predominantly vision-centric, return opaque scalar scores, and rely on costly human annotations. We introduce \textbf{Omni-RRM}, the first open-source rubric-grounded reward model that produces structured, multi-dimension preference judgments with dimension-wise justifications across \textbf{text, image, video, and audio}. At the core of our approach is \textbf{Omni-Preference}, a large-scale dataset built via a fully automated pipeline: we synthesize candidate response pairs by contrasting models of different capabilities, and use strong teacher models to \emph{reconcile and filter} preferences while providing a modality-aware \emph{rubric-grounded rationale} for each pair. This eliminates the need for human-labeled training preferences. Omni-RRM is trained in two stages: supervised fine-tuning to learn the rubric-grounded outputs, followed by reinforcement learning (GRPO) to sharpen discrimination on difficult, low-contrast pairs. Comprehensive evaluations show that Omni-RRM achieves state-of-the-art accuracy on video (80.2\% on ShareGPT-V) and audio (66.8\% on Audio-HH-RLHF) benchmarks, and substantially outperforms existing open-source RMs on image tasks, with a 17.7\% absolute gain over its base model on overall accuracy. Omni-RRM also improves downstream performance via Best-of-$N$ selection and transfers to text-only preference benchmarks. Our data, code, and models are available at https://anonymous.4open.science/r/Omni-RRM-CC08. △ Less

Submitted 31 January, 2026; originally announced February 2026.

TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins

Authors: Nikita Makarov, Maria Bordukova, Lena Voith von Voithenberg, Estrella Pivel-Villanueva, Sabrina Mielke, Jonathan Wickes, Hanchen Wang, Mingyu Derek Ma, Keunwoo Choi, Kyunghyun Cho, Stephen Ra, Raul Rodriguez-Esteban, Fabian Schmich, Michael Menden

Abstract: Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 9… ▽ More Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 93,054 patients across 20 cancer types. In benchmarks, GDT significantly reduces forecasting error, achieving a median Mean Absolute Scaled Error (MASE) of 0.87 compared to 0.97 for the strongest time-series baseline (p<0.001). Furthermore, GDT improves risk stratification, achieving an average concordance index (C-index) of 0.703 across survival, progression, and therapy switching tasks, surpassing the best baseline of 0.662. GDT also generalizes to out-of-distribution clinical trials, matching trained baselines at zero-shot and surpassing them with fine-tuning, achieving a median MASE of 0.75-0.88 and outperforming the strongest baseline in event prediction with an average C-index of 0.672 versus 0.648. Finally, TwinWeaver enables an interpretable clinical reasoning extension, providing a scalable and transparent foundation for longitudinal clinical modeling. △ Less

Submitted 9 February, 2026; v1 submitted 28 January, 2026; originally announced January 2026.

TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance

Authors: Zhemeng Zhang, Jiahua Ma, Xincheng Yang, Xin Wen, Yuzhi Zhang, Boyan Li, Yiran Qin, Jin Liu, Can Zhao, Li Kang, Haoqin Hong, Zhenfei Yin, Philip Torr, Hao Su, Ruimao Zhang, Daolin Ma

Abstract: Fine-grained and contact-rich manipulation remain challenging for robots, largely due to the underutilization of tactile feedback. To address this, we introduce TouchGuide, a novel cross-policy visuo-tactile fusion paradigm that fuses modalities within a low-dimensional action space. Specifically, TouchGuide operates in two stages to guide a pre-trained diffusion or flow-matching visuomotor policy… ▽ More Fine-grained and contact-rich manipulation remain challenging for robots, largely due to the underutilization of tactile feedback. To address this, we introduce TouchGuide, a novel cross-policy visuo-tactile fusion paradigm that fuses modalities within a low-dimensional action space. Specifically, TouchGuide operates in two stages to guide a pre-trained diffusion or flow-matching visuomotor policy at inference time. First, the policy produces a coarse, visually-plausible action using only visual inputs during early sampling. Second, a task-specific Contact Physical Model (CPM) provides tactile guidance to steer and refine the action, ensuring it aligns with realistic physical contact conditions. Trained through contrastive learning on limited expert demonstrations, the CPM provides a tactile-informed feasibility score to steer the sampling process toward refined actions that satisfy physical contact constraints. Furthermore, to facilitate TouchGuide training with high-quality and cost-effective data, we introduce TacUMI, a data collection system. TacUMI achieves a favorable trade-off between precision and affordability; by leveraging rigid fingertips, it obtains direct tactile feedback, thereby enabling the collection of reliable tactile data. Extensive experiments on five challenging contact-rich tasks, such as shoe lacing and chip handover, show that TouchGuide consistently and significantly outperforms state-of-the-art visuo-tactile policies. △ Less

Submitted 24 February, 2026; v1 submitted 27 January, 2026; originally announced January 2026.

BAIT: Visual-illusion-inspired Privacy Preservation for Mobile Data Visualization

Authors: Sizhe Cheng, Songheng Zhang, Dong Ma, Yong Wang

Abstract: With the prevalence of mobile data visualizations, there have been growing concerns about their privacy risks, especially shoulder surfing attacks. Inspired by prior research on visual illusion, we propose BAIT, a novel approach to automatically generate privacy-preserving visualizations by stacking a decoy visualization over a given visualization. It allows visualization owners at proximity to cl… ▽ More With the prevalence of mobile data visualizations, there have been growing concerns about their privacy risks, especially shoulder surfing attacks. Inspired by prior research on visual illusion, we propose BAIT, a novel approach to automatically generate privacy-preserving visualizations by stacking a decoy visualization over a given visualization. It allows visualization owners at proximity to clearly discern the original visualization and makes shoulder surfers at a distance be misled by the decoy visualization, by adjusting different visual channels of a decoy visualization (e.g., shape, position, tilt, size, color and spatial frequency). We explicitly model human perception effect at different viewing distances to optimize the decoy visualization design. Privacy-preserving examples and two in-depth user studies demonstrate the effectiveness of BAIT in both controlled lab study and real-world scenarios. △ Less

Submitted 3 February, 2026; v1 submitted 26 January, 2026; originally announced January 2026.

Comments: Accepted by CHI'26

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment

Authors: Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Duohe Ma, Xiangzheng Zhang, Tong Yang, Lin Sun

Abstract: In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment typically adopts a collaborative framework involving three roles: an attacker for adversarial prompt generation, a defender for safety defense, and an evaluator… ▽ More In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment typically adopts a collaborative framework involving three roles: an attacker for adversarial prompt generation, a defender for safety defense, and an evaluator for response assessment. In this paper, we propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative and co-improving collaboration among three roles with near-zero manual annotation. Experimental results show that the attacker preserves high output diversity while achieving a 20%-50% improvement in adversarial effectiveness; the defender attains 10%-30% gains in safety performance without degrading general reasoning capability; and the evaluator continuously refines its fine-grained judgment ability through iterations, accurately distinguishing unsafe responses, simple refusals, and useful guidance. Overall, our framework establishes an efficient and scalable paradigm for LLM safety alignment, enabling continuous co-evolution within a unified learning loop. △ Less

Submitted 30 January, 2026; v1 submitted 26 January, 2026; originally announced January 2026.

Out-of-Distribution Detection Based on Total Variation Estimation

Authors: Dabiao Ma, Zhiba Su, Jian Yang, Haojun Fei

Abstract: This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have produced satisfactory results, but TV-OOD improves upon these by leveraging the Total Variation Network Estimator to calculate each input's contribution to the… ▽ More This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have produced satisfactory results, but TV-OOD improves upon these by leveraging the Total Variation Network Estimator to calculate each input's contribution to the overall total variation. By defining this as the total variation score, TV-OOD discriminates between in- and out-of-distribution data. The method's efficacy was tested across a range of models and datasets, consistently yielding results in image classification tasks that were either comparable or superior to those achieved by leading-edge out-of-distribution detection techniques across all evaluation metrics. △ Less

Submitted 22 January, 2026; originally announced January 2026.

PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient

Authors: Zijian Wang, Tiancheng Huang, Hanqi Li, Da Ma, Lu Chen, Kai Yu

Abstract: The accelerating growth of the scientific literature makes it increasingly difficult for researchers to track new advances through manual reading alone. Recent progress in large language models (LLMs) has therefore spurred interest in autonomous agents that can read scientific papers and extract task-relevant information. However, most existing approaches rely either on heavily engineered promptin… ▽ More The accelerating growth of the scientific literature makes it increasingly difficult for researchers to track new advances through manual reading alone. Recent progress in large language models (LLMs) has therefore spurred interest in autonomous agents that can read scientific papers and extract task-relevant information. However, most existing approaches rely either on heavily engineered prompting or on a conventional SFT-RL training pipeline, both of which often lead to excessive and low-yield exploration. Drawing inspiration from cognitive science, we propose PaperCompass, a framework that mitigates these issues by separating high-level planning from fine-grained execution. PaperCompass first drafts an explicit plan that outlines the intended sequence of actions, and then performs detailed reasoning to instantiate each step by selecting the parameters for the corresponding function calls. To train such behavior, we introduce Draft-and-Follow Policy Optimization (DFPO), a tailored RL method that jointly optimizes both the draft plan and the final solution. DFPO can be viewed as a lightweight form of hierarchical reinforcement learning, aimed at narrowing the `knowing-doing' gap in LLMs. We provide a theoretical analysis that establishes DFPO's favorable optimization properties, supporting a stable and reliable training process. Experiments on paper-based question answering (Paper-QA) benchmarks show that PaperCompass improves efficiency over strong baselines without sacrificing performance, achieving results comparable to much larger models. △ Less

Submitted 19 January, 2026; originally announced January 2026.

Comments: 35 pages, 9 figures, 7 tables

Japanese AI Agent System on Human Papillomavirus Vaccination: System Design

Authors: Junyu Liu, Siwen Yang, Dexiu Ma, Qian Niu, Zequn Zhang, Momoko Nagai-Tanima, Tomoki Aoyama

Abstract: Human papillomavirus (HPV) vaccine hesitancy poses significant public health challenges, particularly in Japan where proactive vaccination recommendations were suspended from 2013 to 2021. The resulting information gap is exacerbated by misinformation on social media, and traditional ways cannot simultaneously address individual queries while monitoring population-level discourse. This study aimed… ▽ More Human papillomavirus (HPV) vaccine hesitancy poses significant public health challenges, particularly in Japan where proactive vaccination recommendations were suspended from 2013 to 2021. The resulting information gap is exacerbated by misinformation on social media, and traditional ways cannot simultaneously address individual queries while monitoring population-level discourse. This study aimed to develop a dual-purpose AI agent system that provides verified HPV vaccine information through a conversational interface while generating analytical reports for medical institutions based on user interactions and social media. We implemented a system comprising: a vector database integrating academic papers, government sources, news media, and social media; a Retrieval-Augmented Generation chatbot using ReAct agent architecture with multi-tool orchestration across five knowledge sources; and an automated report generation system with modules for news analysis, research synthesis, social media sentiment analysis, and user interaction pattern identification. Performance was assessed using a 0-5 scoring scale. For single-turn evaluation, the chatbot achieved mean scores of 4.83 for relevance, 4.89 for routing, 4.50 for reference quality, 4.90 for correctness, and 4.88 for professional identity (overall 4.80). Multi-turn evaluation yielded higher scores: context retention 4.94, topic coherence 5.00, and overall 4.98. The report generation system achieved completeness 4.00-5.00, correctness 4.00-5.00, and helpfulness 3.67-5.00, with reference validity 5.00 across all periods. This study demonstrates the feasibility of an integrated AI agent system for bidirectional HPV vaccine communication. The architecture enables verified information delivery with source attribution while providing systematic public discourse analysis, with a transferable framework for adaptation to other medical contexts. △ Less

Submitted 15 December, 2025; originally announced January 2026.

NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models

Authors: Ziming Dai, Dabiao Ma, Jinle Tong, Mengyuan Han, Jian Yang, Hongtao Liu, Haojun Fei, Qing Yang

Abstract: Although the Gradient Boosted Decision Trees (GBDTs) dominate industrial tabular applications, upgrading legacy models in high-concurrency production environments still faces prohibitive retraining costs and systemic risks. To address this problem, we present NSR-Boost, a neuro-symbolic residual boosting framework designed specifically for industrial scenarios. Its core advantage lies in being "no… ▽ More Although the Gradient Boosted Decision Trees (GBDTs) dominate industrial tabular applications, upgrading legacy models in high-concurrency production environments still faces prohibitive retraining costs and systemic risks. To address this problem, we present NSR-Boost, a neuro-symbolic residual boosting framework designed specifically for industrial scenarios. Its core advantage lies in being "non-intrusive". It treats the legacy model as a frozen model and performs targeted repairs on "hard regions" where predictions fail. The framework comprises three key stages: First, finding hard regions through residuals, then generating interpretable experts by generating symbolic code structures using Large Language Model (LLM) and fine-tuning parameters using Bayesian optimization, and finally dynamically integrating experts with legacy model output through a lightweight aggregator. Experimental results demonstrate that the framework not only significantly outperforms state-of-the-art (SOTA) baselines across six public datasets and one private dataset. More importantly, we report the successful deployment of NSR-Boost within the core financial risk control system of Qfin Holdings, where empirical results on real-world online traffic exhibit superior performance improvements and a significant reduction in the bad rate. In conclusion, it effectively captures long-tail risks missed by traditional models and offers a safe, low-cost evolutionary paradigm for industry. △ Less

Submitted 31 January, 2026; v1 submitted 15 January, 2026; originally announced January 2026.

Comments: 14 pages, 12 figures

Step-DeepResearch Technical Report

Authors: Chen Hu, Haikuo Du, Heng Wang, Lin Lin, Mingrui Chen, Peng Liu, Ruihang Miao, Tianchi Yue, Wang You, Wei Ji, Wei Yuan, Wenjin Deng, Xiaojian Yuan, Xiaoyun Zhang, Xiangyu Liu, Xikai Liu, Yanming Xu, Yicheng Cao, Yifei Zhang, Yongyao Wang, Yubo Shu, Yurong Zhang, Yuxiang Zhang, Zheng Gong, Zhichao Chang , et al. (42 additional authors not shown)

Abstract: As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent… ▽ More As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency. △ Less

Submitted 29 December, 2025; v1 submitted 23 December, 2025; originally announced December 2025.

TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering

Authors: Rui Gui, Yang Wan, Haochen Han, Dongxing Mao, Fangming Liu, Min Li, Alex Jinpeng Wang

Abstract: Text rendering has recently emerged as one of the most challenging frontiers in visual generation, drawing significant attention from large-scale diffusion and multimodal models. However, text editing within images remains largely unexplored, as it requires generating legible characters while preserving semantic, geometric, and contextual coherence. To fill this gap, we introduce TextEditBench, a… ▽ More Text rendering has recently emerged as one of the most challenging frontiers in visual generation, drawing significant attention from large-scale diffusion and multimodal models. However, text editing within images remains largely unexplored, as it requires generating legible characters while preserving semantic, geometric, and contextual coherence. To fill this gap, we introduce TextEditBench, a comprehensive evaluation benchmark that explicitly focuses on text-centric regions in images. Beyond basic pixel manipulations, our benchmark emphasizes reasoning-intensive editing scenarios that require models to understand physical plausibility, linguistic meaning, and cross-modal dependencies. We further propose a novel evaluation dimension, Semantic Expectation (SE), which measures reasoning ability of model to maintain semantic consistency, contextual coherence, and cross-modal alignment during text editing. Extensive experiments on state-of-the-art editing systems reveal that while current models can follow simple textual instructions, they still struggle with context-dependent reasoning, physical consistency, and layout-aware integration. By focusing evaluation on this long-overlooked yet fundamental capability, TextEditBench establishes a new testing ground for advancing text-guided image editing and reasoning in multimodal generation. △ Less

Submitted 18 December, 2025; originally announced December 2025.

Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead

Authors: Guang Yang, Wei Zheng, Xiang Chen, Dong Liang, Peng Hu, Yukui Yang, Shaohang Peng, Zhenghan Li, Jiahui Feng, Xiao Wei, Kexin Sun, Deyuan Ma, Haotian Cheng, Yiheng Shen, Xing Hu, Terry Yue Zhuo, David Lo

Abstract: Code generation has emerged as a critical research area at the intersection of Software Engineering (SE) and Artificial Intelligence (AI), attracting significant attention from both academia and industry. Within this broader landscape, Verilog, as a representative hardware description language (HDL), plays a fundamental role in digital circuit design and verification, making its automated generati… ▽ More Code generation has emerged as a critical research area at the intersection of Software Engineering (SE) and Artificial Intelligence (AI), attracting significant attention from both academia and industry. Within this broader landscape, Verilog, as a representative hardware description language (HDL), plays a fundamental role in digital circuit design and verification, making its automated generation particularly significant for Electronic Design Automation (EDA). Consequently, recent research has increasingly focused on applying Large Language Models (LLMs) to Verilog code generation, particularly at the Register Transfer Level (RTL), exploring how these AI-driven techniques can be effectively integrated into hardware design workflows. Despite substantial research efforts have explored LLM applications in this domain, a comprehensive survey synthesizing these developments remains absent from the literature. This review fill addresses this gap by providing a systematic literature review of LLM-based methods for Verilog code generation, examining their effectiveness, limitations, and potential for advancing automated hardware design. The review encompasses research work from conferences and journals in the fields of SE, AI, and EDA, encompassing 70 papers published on venues, along with 32 high-quality preprint papers, bringing the total to 102 papers. By answering four key research questions, we aim to (1) identify the LLMs used for Verilog generation, (2) examine the datasets and metrics employed in evaluation, (3) categorize the techniques proposed for Verilog generation, and (4) analyze LLM alignment approaches for Verilog generation. Based on our findings, we have identified a series of limitations of existing studies. Finally, we have outlined a roadmap highlighting potential opportunities for future research endeavors in LLM-assisted hardware design. △ Less

Submitted 24 December, 2025; v1 submitted 29 October, 2025; originally announced December 2025.

Comments: Under Review

Device-Guided Music Transfer

Authors: Manh Pham Hung, Changshuo Hu, Ting Dang, Dong Ma

Abstract: Device-guided music transfer adapts playback across unseen devices for users who lack them. Existing methods mainly focus on modifying the timbre, rhythm, harmony, or instrumentation to mimic genres or artists, overlooking the diverse hardware properties of the playback device (i.e., speaker). Therefore, we propose DeMT, which processes a speaker's frequency response curve as a line graph using a… ▽ More Device-guided music transfer adapts playback across unseen devices for users who lack them. Existing methods mainly focus on modifying the timbre, rhythm, harmony, or instrumentation to mimic genres or artists, overlooking the diverse hardware properties of the playback device (i.e., speaker). Therefore, we propose DeMT, which processes a speaker's frequency response curve as a line graph using a vision-language model to extract device embeddings. These embeddings then condition a hybrid transformer via feature-wise linear modulation. Fine-tuned on a self-collected dataset, DeMT enables effective speaker-style transfer and robust few-shot adaptation for unseen devices, supporting applications like device-style augmentation and quality enhancement. △ Less

Submitted 21 November, 2025; originally announced November 2025.

TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning

Authors: Dabiao Ma, Ziming Dai, Zhimin Xin, Shu Wang, Jian Yang, Haojun Fei

Abstract: Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter update. In this paper, we challenge this convention by revealing a pervasive token-level redundancy in the fine-tuning of large models (LMs). We propose TS-PEFT, a… ▽ More Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter update. In this paper, we challenge this convention by revealing a pervasive token-level redundancy in the fine-tuning of large models (LMs). We propose TS-PEFT, a theoretical framework utilizing proximal optimization that acts as a dynamic probe to identify token-level redundancy during the fine-tuning process. Extensive experiments demonstrate that indiscriminately updating all tokens is not only computationally superfluous but often introduces optimization noise. Surprisingly, by discarding 30%-70% of token updates, TS-PEFT consistently matches or exceeds the performance of dense baselines such as LoRA, DoRA. Our in-depth analysis shows that the learned token-level sparsity is a superior indicator of module importance compared to traditional weight criteria, providing a novel data-driven perspective on the intrinsic adaptation mechanism of LMs. △ Less

Submitted 29 January, 2026; v1 submitted 20 November, 2025; originally announced November 2025.

Comments: 11 pages, 3 figures

iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification

Authors: Zixun Xiong, Gaoyi Wu, Qingyang Yu, Mingyu Derek Ma, Lingfeng Yao, Miao Pan, Xiaojiang Du, Hao Wang

Abstract: Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) has become increasingly crucial. As the standard paradigm for IP ownership verification, LLM fingerprinting thus plays a vital role in addressing this challenge. Existing LLM fingerprinting methods verify ownership by extracting or injecting model-specific features. However, they ov… ▽ More Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) has become increasingly crucial. As the standard paradigm for IP ownership verification, LLM fingerprinting thus plays a vital role in addressing this challenge. Existing LLM fingerprinting methods verify ownership by extracting or injecting model-specific features. However, they overlook potential attacks during the verification process, leaving them ineffective when the model thief fully controls the LLM's inference process. In such settings, attackers may share prompt-response pairs to enable fingerprint unlearning or manipulate outputs to evade exact-match verification. We propose iSeal, the first fingerprinting method designed for reliable verification when the model thief controls the suspected LLM in an end-to-end manner. It injects unique features into both the model and an external module, reinforced by an error-correction mechanism and a similarity-based verification strategy. These components are resistant to verification-time attacks, including collusion-based fingerprint unlearning and response manipulation, backed by both theoretical analysis and empirical results. iSeal achieves 100 percent Fingerprint Success Rate (FSR) on 12 LLMs against more than 10 attacks, while baselines fail under unlearning and response manipulations. △ Less

Submitted 19 March, 2026; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI 2026

Journal ref: Proc. AAAI Conf. Artif. Intell. 40(42): 23984-23992, 2026

BioVerge: A Comprehensive Benchmark and Study of Self-Evaluating Agents for Biomedical Hypothesis Generation

Authors: Fuyi Yang, Chenchen Ye, Mingyu Derek Ma, Yijia Xiao, Matthew Yang, Wei Wang

Abstract: Hypothesis generation in biomedical research has traditionally centered on uncovering hidden relationships within vast scientific literature, often using methods like Literature-Based Discovery (LBD). Despite progress, current approaches typically depend on single data types or predefined extraction patterns, which restricts the discovery of novel and complex connections. Recent advances in Large… ▽ More Hypothesis generation in biomedical research has traditionally centered on uncovering hidden relationships within vast scientific literature, often using methods like Literature-Based Discovery (LBD). Despite progress, current approaches typically depend on single data types or predefined extraction patterns, which restricts the discovery of novel and complex connections. Recent advances in Large Language Model (LLM) agents show significant potential, with capabilities in information retrieval, reasoning, and generation. However, their application to biomedical hypothesis generation has been limited by the absence of standardized datasets and execution environments. To address this, we introduce BioVerge, a comprehensive benchmark, and BioVerge Agent, an LLM-based agent framework, to create a standardized environment for exploring biomedical hypothesis generation at the frontier of existing scientific knowledge. Our dataset includes structured and textual data derived from historical biomedical hypotheses and PubMed literature, organized to support exploration by LLM agents. BioVerge Agent utilizes a ReAct-based approach with distinct Generation and Evaluation modules that iteratively produce and self-assess hypothesis proposals. Through extensive experimentation, we uncover key insights: 1) different architectures of BioVerge Agent influence exploration diversity and reasoning strategies; 2) structured and textual information sources each provide unique, critical contexts that enhance hypothesis generation; and 3) self-evaluation significantly improves the novelty and relevance of proposed hypotheses. △ Less

Submitted 11 November, 2025; originally announced November 2025.

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

Authors: Kevin Qinghong Lin, Yuhao Zheng, Hangyu Ran, Dantong Zhu, Dongxing Mao, Linjie Li, Philip Torr, Alex Jinpeng Wang

Abstract: Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored. Inspired by how humans reason over sketches, we advocate SVG code as a compact, interpretable, and executable visual representation. We introduce VCode, a benc… ▽ More Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored. Inspired by how humans reason over sketches, we advocate SVG code as a compact, interpretable, and executable visual representation. We introduce VCode, a benchmark that reframes multimodal understanding as code generation: given an image, a model must produce SVG that preserves symbolic meaning for downstream reasoning. VCode covers three domains - general commonsense (MM-Vet), professional disciplines (MMMU), and visual-centric perception (CV-Bench). To assess symbolic fidelity, we propose CodeVQA, a novel evaluation protocol in which a policy model answers questions over rendered SVGs; correct answers indicate faithful symbolic preservation. Empirically, frontier VLMs struggle to generate faithful SVGs, revealing a persistent gap between language-centric and visual-centric coding. To close this gap, we introduce VCoder, an agentic framework that augments VLMs along two axes: (i) Thinking with Revision, which iteratively analyzes discrepancies and refines SVG code; and (ii) Acting with Visual Tools, where detectors and parsers supply structured cues such as objects, shapes, and text beyond the model's intrinsic capacity. Across benchmarks, frontier VLMs with strong reasoning capabilities score well overall yet remain limited in professional knowledge and 3D reasoning. VCoder delivers a 12.3-point overall gain over the top-performing Claude-4-Opus. Human studies show that both humans and VLMs perform worse on rendered SVGs, their consistency reveals the promise of symbolic visual representation. The benchmark and code are available at https://github.com/CSU-JPG/VCode. △ Less

Submitted 4 November, 2025; originally announced November 2025.

Comments: Project page: https://csu-jpg.github.io/VCode Github: https://github.com/CSU-JPG/VCode

Collaborative Attention and Consistent-Guided Fusion of MRI and PET for Alzheimer's Disease Diagnosis

Authors: Delin Ma, Menghui Zhou, Jun Qi, Yun Yang, Po Yang

Abstract: Alzheimer's disease (AD) is the most prevalent form of dementia, and its early diagnosis is essential for slowing disease progression. Recent studies on multimodal neuroimaging fusion using MRI and PET have achieved promising results by integrating multi-scale complementary features. However, most existing approaches primarily emphasize cross-modal complementarity while overlooking the diagnostic… ▽ More Alzheimer's disease (AD) is the most prevalent form of dementia, and its early diagnosis is essential for slowing disease progression. Recent studies on multimodal neuroimaging fusion using MRI and PET have achieved promising results by integrating multi-scale complementary features. However, most existing approaches primarily emphasize cross-modal complementarity while overlooking the diagnostic importance of modality-specific features. In addition, the inherent distributional differences between modalities often lead to biased and noisy representations, degrading classification performance. To address these challenges, we propose a Collaborative Attention and Consistent-Guided Fusion framework for MRI and PET based AD diagnosis. The proposed model introduces a learnable parameter representation (LPR) block to compensate for missing modality information, followed by a shared encoder and modality-independent encoders to preserve both shared and specific representations. Furthermore, a consistency-guided mechanism is employed to explicitly align the latent distributions across modalities. Experimental results on the ADNI dataset demonstrate that our method achieves superior diagnostic performance compared with existing fusion strategies. △ Less

Submitted 3 November, 2025; originally announced November 2025.

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions

Authors: Shengnan An, Xunliang Cai, Xuezhi Cao, Xiaoyu Li, Yehao Lin, Junlin Liu, Xinxuan Lv, Dan Ma, Xuanlin Wang, Ziwen Wang, Shuang Zhou

Abstract: We present AMO-Bench, an Advanced Mathematical reasoning benchmark with Olympiad level or even higher difficulty, comprising 50 human-crafted problems. Existing benchmarks have widely leveraged high school math competitions for evaluating mathematical reasoning capabilities of large language models (LLMs). However, many existing math competitions are becoming less effective for assessing top-tier… ▽ More We present AMO-Bench, an Advanced Mathematical reasoning benchmark with Olympiad level or even higher difficulty, comprising 50 human-crafted problems. Existing benchmarks have widely leveraged high school math competitions for evaluating mathematical reasoning capabilities of large language models (LLMs). However, many existing math competitions are becoming less effective for assessing top-tier LLMs due to performance saturation (e.g., AIME24/25). To address this, AMO-Bench introduces more rigorous challenges by ensuring all 50 problems are (1) cross-validated by experts to meet at least the International Mathematical Olympiad (IMO) difficulty standards, and (2) entirely original problems to prevent potential performance leakages from data memorization. Moreover, each problem in AMO-Bench requires only a final answer rather than a proof, enabling automatic and robust grading for evaluation. Experimental results across 26 LLMs on AMO-Bench show that even the best-performing model achieves only 52.4% accuracy on AMO-Bench, with most LLMs scoring below 40%. Beyond these poor performances, our further analysis reveals a promising scaling trend with increasing test-time compute on AMO-Bench. These results highlight the significant room for improving the mathematical reasoning in current LLMs. We release AMO-Bench to facilitate further research into advancing the reasoning abilities of language models. https://amo-bench.github.io/ △ Less

Submitted 30 October, 2025; originally announced October 2025.

Comments: 14 pages, 9 figures

The End of Manual Decoding: Towards Truly End-to-End Language Models

Authors: Zhichao Wang, Dongyang Ma, Xinting Huang, Deng Cai, Tian Lan, Jiahao Xu, Haitao Mi, Xiaoying Tang, Yan Wang

Abstract: The "end-to-end" label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding process that requires laborious, hand-tuning of hyperparameters like temperature and top-p. This paper introduces AutoDeco, a novel architecture that enables truly "end-to-end" generation by learning to control its own decoding strategy. We augment the standard transformer with lightweight head… ▽ More The "end-to-end" label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding process that requires laborious, hand-tuning of hyperparameters like temperature and top-p. This paper introduces AutoDeco, a novel architecture that enables truly "end-to-end" generation by learning to control its own decoding strategy. We augment the standard transformer with lightweight heads that, at each step, dynamically predict context-specific temperature and top-p values alongside the next-token logits. This approach transforms decoding into a parametric, token-level process, allowing the model to self-regulate its sampling strategy within a single forward pass. Through extensive experiments on eight benchmarks, we demonstrate that AutoDeco not only significantly outperforms default decoding strategies but also achieves performance comparable to an oracle-tuned baseline derived from "hacking the test set"-a practical upper bound for any static method. Crucially, we uncover an emergent capability for instruction-based decoding control: the model learns to interpret natural language commands (e.g., "generate with low randomness") and adjusts its predicted temperature and top-p on a token-by-token basis, opening a new paradigm for steerable and interactive LLM decoding. △ Less

Submitted 31 October, 2025; v1 submitted 30 October, 2025; originally announced October 2025.

EasyUUV: An LLM-Enhanced Universal and Lightweight Sim-to-Real Reinforcement Learning Framework for UUV Attitude Control

Authors: Guanwen Xie, Jingzehua Xu, Jiwei Tang, Yubo Huang, Zixi Wang, Shuai Zhang, Dongfang Ma, Juntian Qu, Xiaofan Li

Abstract: Despite recent advances in Unmanned Underwater Vehicle (UUV) attitude control, existing methods still struggle with generalizability, robustness to real-world disturbances, and efficient deployment. To address the above challenges, this paper presents EasyUUV, a Large Language Model (LLM)-enhanced, universal, and lightweight simulation-to-reality reinforcement learning (RL) framework for robust at… ▽ More Despite recent advances in Unmanned Underwater Vehicle (UUV) attitude control, existing methods still struggle with generalizability, robustness to real-world disturbances, and efficient deployment. To address the above challenges, this paper presents EasyUUV, a Large Language Model (LLM)-enhanced, universal, and lightweight simulation-to-reality reinforcement learning (RL) framework for robust attitude control of UUVs. EasyUUV combines parallelized RL training with a hybrid control architecture, where a learned policy outputs high-level attitude corrections executed by an adaptive S-Surface controller. A multimodal LLM is further integrated to adaptively tune controller parameters at runtime using visual and textual feedback, enabling training-free adaptation to unmodeled dynamics. Also, we have developed a low-cost 6-DoF UUV platform and applied an RL policy trained through efficient parallelized simulation. Extensive simulation and real-world experiments validate the effectiveness and outstanding performance of EasyUUV in achieving robust and adaptive UUV attitude control across diverse underwater conditions. To facilitate reproducibility and further research, the source code, LLM prompts, and supplementary video are provided in the following repositories: Homepage: https://360zmem.github.io/easyuuv/ Video:https://youtu.be/m2yLQzxiIL △ Less

Submitted 12 February, 2026; v1 submitted 24 October, 2025; originally announced October 2025.

Comments: 10 pages, 13 figures

Interpretable Multimodal Zero-Shot ECG Diagnosis via Structured Clinical Knowledge Alignment

Authors: Jialu Tang, Hung Manh Pham, Ignace De Lathauwer, Henk S. Schipper, Yuan Lu, Dong Ma, Aaqib Saeed

Abstract: Electrocardiogram (ECG) interpretation is essential for cardiovascular disease diagnosis, but current automated systems often struggle with transparency and generalization to unseen conditions. To address this, we introduce ZETA, a zero-shot multimodal framework designed for interpretable ECG diagnosis aligned with clinical workflows. ZETA uniquely compares ECG signals against structured positive… ▽ More Electrocardiogram (ECG) interpretation is essential for cardiovascular disease diagnosis, but current automated systems often struggle with transparency and generalization to unseen conditions. To address this, we introduce ZETA, a zero-shot multimodal framework designed for interpretable ECG diagnosis aligned with clinical workflows. ZETA uniquely compares ECG signals against structured positive and negative clinical observations, which are curated through an LLM-assisted, expert-validated process, thereby mimicking differential diagnosis. Our approach leverages a pre-trained multimodal model to align ECG and text embeddings without disease-specific fine-tuning. Empirical evaluations demonstrate ZETA's competitive zero-shot classification performance and, importantly, provide qualitative and quantitative evidence of enhanced interpretability, grounding predictions in specific, clinically relevant positive and negative diagnostic features. ZETA underscores the potential of aligning ECG analysis with structured clinical knowledge for building more transparent, generalizable, and trustworthy AI diagnostic systems. We will release the curated observation dataset and code to facilitate future research. △ Less

Submitted 24 October, 2025; originally announced October 2025.

From Charts to Code: A Hierarchical Benchmark for Multimodal Models

Authors: Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang

Abstract: We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure a… ▽ More We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, information-dense tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,023 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 25 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5, Qwen2.5-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5 averages only 0.57 on code-based evaluation and 0.22 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs. Our code and data are available on Chart2Code. △ Less

Submitted 21 January, 2026; v1 submitted 20 October, 2025; originally announced October 2025.

MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science

Authors: Junkai Zhang, Jingru Gan, Xiaoxuan Wang, Zian Jia, Changquan Gu, Jianpeng Chen, Yanqiao Zhu, Mingyu Derek Ma, Dawei Zhou, Ling Li, Wei Wang

Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in scientific reasoning, yet their reasoning capabilities in materials science remain underexplored. To fill this gap, we introduce MatSciBench, a comprehensive college-level benchmark comprising 1,340 problems that span the essential subdisciplines of materials science. MatSciBench features a structured and fine-grained taxonomy… ▽ More Large Language Models (LLMs) have demonstrated remarkable abilities in scientific reasoning, yet their reasoning capabilities in materials science remain underexplored. To fill this gap, we introduce MatSciBench, a comprehensive college-level benchmark comprising 1,340 problems that span the essential subdisciplines of materials science. MatSciBench features a structured and fine-grained taxonomy that categorizes materials science questions into 6 primary fields and 31 sub-fields, and includes a three-tier difficulty classification based on the reasoning length required to solve each question. MatSciBench provides detailed reference solutions enabling precise error analysis and incorporates multimodal reasoning through visual contexts in numerous questions. Evaluations of leading models reveal that even the highest-performing model, Gemini-2.5-Pro, achieves under 80% accuracy on college-level materials science questions, highlighting the complexity of MatSciBench. Our systematic analysis of different reasoning strategie--basic chain-of-thought, tool augmentation, and self-correction--demonstrates that no single method consistently excels across all scenarios. We further analyze performance by difficulty level, examine trade-offs between efficiency and accuracy, highlight the challenges inherent in multimodal reasoning tasks, analyze failure modes across LLMs and reasoning methods, and evaluate the influence of retrieval-augmented generation. MatSciBench thus establishes a comprehensive and solid benchmark for assessing and driving improvements in the scientific reasoning capabilities of LLMs within the materials science domain. △ Less

Submitted 14 October, 2025; originally announced October 2025.

RadOnc-GPT: An Autonomous LLM Agent for Real-Time Patient Outcomes Labeling at Scale

Authors: Jason Holmes, Yuexing Hao, Mariana Borras-Osorio, Federico Mastroleo, Santiago Romero Brufau, Valentina Carducci, Katie M Van Abel, David M Routman, Andrew Y. K. Foong, Liv M Muller, Satomi Shiraishi, Daniel K Ebner, Daniel J Ma, Sameer R Keole, Samir H Patel, Mirek Fatyga, Martin Bues, Brad J Stish, Yolanda I Garces, Michelle A Neben Wittich, Robert L Foote, Sujay A Vora, Nadia N Laack, Mark R Waddle, Wei Liu

Abstract: Manual labeling limits the scale, accuracy, and timeliness of patient outcomes research in radiation oncology. We present RadOnc-GPT, an autonomous large language model (LLM)-based agent capable of independently retrieving patient-specific information, iteratively assessing evidence, and returning structured outcomes. Our evaluation explicitly validates RadOnc-GPT across two clearly defined tiers… ▽ More Manual labeling limits the scale, accuracy, and timeliness of patient outcomes research in radiation oncology. We present RadOnc-GPT, an autonomous large language model (LLM)-based agent capable of independently retrieving patient-specific information, iteratively assessing evidence, and returning structured outcomes. Our evaluation explicitly validates RadOnc-GPT across two clearly defined tiers of increasing complexity: (1) a structured quality assurance (QA) tier, assessing the accurate retrieval of demographic and radiotherapy treatment plan details, followed by (2) a complex clinical outcomes labeling tier involving determination of mandibular osteoradionecrosis (ORN) in head-and-neck cancer patients and detection of cancer recurrence in independent prostate and head-and-neck cancer cohorts requiring combined interpretation of structured and unstructured patient data. The QA tier establishes foundational trust in structured-data retrieval, a critical prerequisite for successful complex clinical outcome labeling. △ Less

Submitted 12 December, 2025; v1 submitted 29 September, 2025; originally announced September 2025.