Showing 1–50 of 643 results for author: Wei, J

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Authors: Wanghan Xu, Yuhao Zhou, Yifan Zhou, Qinglong Cao, Shuo Li, Jia Bu, Bo Liu, Yixin Chen, Xuming He, Xiangyu Zhao, Xiang Zhuang, Fengxiang Wang, Zhiwang Zhou, Qiantai Feng, Wenxuan Huang, Jiaqi Wei, Hao Wu, Yuejin Yang, Guangshuai Wang, Sheng Xu, Ziyan Huang, Xinyao Liu, Jiyao Liu, Cheng Tang, Wei Li , et al. (82 additional authors not shown)

Abstract: Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep res… ▽ More Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery. △ Less

Submitted 18 December, 2025; originally announced December 2025.

Accurate de novo sequencing of the modified proteome with OmniNovo

Authors: Yuhan Chen, Shang Qu, Zhiqiang Gao, Yuejin Yang, Xiang Zhang, Sheng Xu, Xinjie Mao, Liujia Qian, Jiaqi Wei, Zijie Qiu, Chenyu You, Lei Bai, Ning Ding, Tiannan Guo, Bowen Zhou, Siqi Sun

Abstract: Post-translational modifications (PTMs) serve as a dynamic chemical language regulating protein function, yet current proteomic methods remain blind to a vast portion of the modified proteome. Standard database search algorithms suffer from a combinatorial explosion of search spaces, limiting the identification of uncharacterized or complex modifications. Here we introduce OmniNovo, a unified deep… ▽ More Post-translational modifications (PTMs) serve as a dynamic chemical language regulating protein function, yet current proteomic methods remain blind to a vast portion of the modified proteome. Standard database search algorithms suffer from a combinatorial explosion of search spaces, limiting the identification of uncharacterized or complex modifications. Here we introduce OmniNovo, a unified deep learning framework for reference-free sequencing of unmodified and modified peptides directly from tandem mass spectra. Unlike existing tools restricted to specific modification types, OmniNovo learns universal fragmentation rules to decipher diverse PTMs within a single coherent model. By integrating a mass-constrained decoding algorithm with rigorous false discovery rate estimation, OmniNovo achieves state-of-the-art accuracy, identifying 51\% more peptides than standard approaches at a 1\% false discovery rate. Crucially, the model generalizes to biological sites unseen during training, illuminating the dark matter of the proteome and enabling unbiased comprehensive analysis of cellular regulation. △ Less

Submitted 13 December, 2025; originally announced December 2025.

Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning

Authors: Tingyu Li, Zheng Sun, Jingxuan Wei, Siyuan Li, Conghui He, Lijun Wu, Cheng Tan

Abstract: Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience. However, RL for VLMs requires abundant high-quality multimodal data, especially challenging in specialized domains like chemistry, earth sciences, and multimoda… ▽ More Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience. However, RL for VLMs requires abundant high-quality multimodal data, especially challenging in specialized domains like chemistry, earth sciences, and multimodal mathematics. Existing strategies such as synthetic data and self-rewarding mechanisms suffer from limited distributions and alignment difficulties, ultimately causing reward hacking: models exploit high-reward patterns, collapsing policy entropy and destabilizing training. We propose DoGe (Decouple to Generalize), a dual-decoupling framework that guides models to first learn from context rather than problem solving by refocusing on the problem context scenarios overlooked by synthetic data methods. By decoupling learning process into dual components (Thinker and Solver), we reasonably quantify the reward signals of this process and propose a two-stage RL post-training approach from freely exploring context to practically solving tasks. Second, to increase the diversity of training data, DoGe constructs an evolving curriculum learning pipeline: an expanded native domain knowledge corpus and an iteratively evolving seed problems pool. Experiments show that our method consistently outperforms the baseline across various benchmarks, providing a scalable pathway for realizing self-evolving LVLMs. △ Less

Submitted 7 December, 2025; originally announced December 2025.

Comments: 25 pages, 5 figures

Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices

Authors: Xiangyu Li, Chengyu Yin, Weijun Wang, Jianyu Wei, Ting Cao, Yunxin Liu

Abstract: Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table (LUT)-based inference, CPUs run these ultra-low-bit LLMs even faster than NPUs, opening new opportunities for ubiquitous on-device intelligence. However, this paper i… ▽ More Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table (LUT)-based inference, CPUs run these ultra-low-bit LLMs even faster than NPUs, opening new opportunities for ubiquitous on-device intelligence. However, this paper identifies that LUT-based inference underutilizes memory bandwidth during parallel inference, which is required for prefilling, test-time scaling, and other multi-token scenarios. The root cause is the scalar LUT paradigm, which performs repetitive and non-contiguous memory accesses for each token. To solve the issue, we propose vector LUT, a new lookup paradigm that constructs a unified LUT across parallel tokens, and performs a single $1 \rightarrow N$ lookup per index. To realize it efficiently, we further introduce (1) Vector LUT-Centric Tensor Layout, and (2) Cache-Aware Streamed Lookup techniques. Evaluations on 5 edge devices across 3 LLMs show that Vec-LUT outperforms state-of-the-art baselines by up to $4.2\times$. Our implementation is integrated into llama.cpp. The code is available at https://github.com/Cipherxzc/vlut.cpp. △ Less

Submitted 6 December, 2025; originally announced December 2025.

Comments: Preprint

Uncovering Students' Inquiry Patterns in GenAI-Supported Clinical Practice: An Integration of Epistemic Network Analysis and Sequential Pattern Mining

Authors: Jiameng Wei, Dinh Dang, Kaixun Yang, Emily Stokes, Amna Mazeh, Angelina Lim, David Wei Dai, Joel Moore, Yizhou Fan, Danijela Gasevic, Dragan Gasevic, Guanliang Chen

Abstract: Assessment of medication history-taking has traditionally relied on human observation, limiting scalability and detailed performance data. While Generative AI (GenAI) platforms enable extensive data collection and learning analytics provide powerful methods for analyzing educational traces, these approaches remain largely underexplored in pharmacy clinical training. This study addresses this gap b… ▽ More Assessment of medication history-taking has traditionally relied on human observation, limiting scalability and detailed performance data. While Generative AI (GenAI) platforms enable extensive data collection and learning analytics provide powerful methods for analyzing educational traces, these approaches remain largely underexplored in pharmacy clinical training. This study addresses this gap by applying learning analytics to understand how students develop clinical communication competencies with GenAI-powered virtual patients -- a crucial endeavor given the diversity of student cohorts, varying language backgrounds, and the limited opportunities for individualized feedback in traditional training settings. We analyzed 323 students' interaction logs across Australian and Malaysian institutions, comprising 50,871 coded utterances from 1,487 student-GenAI dialogues. Combining Epistemic Network Analysis to model inquiry co-occurrences with Sequential Pattern Mining to capture temporal sequences, we found that high performers demonstrated strategic deployment of information recognition behaviors. Specifically, high performers centered inquiry on recognizing clinically relevant information, integrating rapport-building and structural organization, while low performers remained in routine question-verification loops. Demographic factors including first-language background, prior pharmacy work experience, and institutional context, also shaped distinct inquiry patterns. These findings reveal inquiry patterns that may indicate clinical reasoning development in GenAI-assisted contexts, providing methodological insights for health professions education assessment and informing adaptive GenAI system design that supports diverse learning pathways. △ Less

Submitted 3 December, 2025; originally announced December 2025.

NAWOA-XGBoost: A Novel Model for Early Prediction of Academic Potential in Computer Science Students

Authors: Junhao Wei, Yanzhao Gu, Ran Zhang, Mingjing Huang, Jinhong Song, Yanxiao Li, Wenxuan Zhu, Yapeng Wang, Zikun Li, Zhiwen Wang, Xu Yang, Ngai Cheong

Abstract: Whale Optimization Algorithm (WOA) suffers from limited global search ability, slow convergence, and tendency to fall into local optima, restricting its effectiveness in hyperparameter optimization for machine learning models. To address these issues, this study proposes a Nonlinear Adaptive Whale Optimization Algorithm (NAWOA), which integrates strategies such as Good Nodes Set initialization, Le… ▽ More Whale Optimization Algorithm (WOA) suffers from limited global search ability, slow convergence, and tendency to fall into local optima, restricting its effectiveness in hyperparameter optimization for machine learning models. To address these issues, this study proposes a Nonlinear Adaptive Whale Optimization Algorithm (NAWOA), which integrates strategies such as Good Nodes Set initialization, Leader-Followers Foraging, Dynamic Encircling Prey, Triangular Hunting, and a nonlinear convergence factor to enhance exploration, exploitation, and convergence stability. Experiments on 23 benchmark functions demonstrate NAWOA's superior optimization capability and robustness. Based on this optimizer, an NAWOA-XGBoost model was developed to predict academic potential using data from 495 Computer Science undergraduates at Macao Polytechnic University (2009-2019). Results show that NAWOA-XGBoost outperforms traditional XGBoost and WOA-XGBoost across key metrics, including Accuracy (0.8148), Macro F1 (0.8101), AUC (0.8932), and G-Mean (0.8172), demonstrating strong adaptability on multi-class imbalanced datasets. △ Less

Submitted 5 December, 2025; v1 submitted 4 December, 2025; originally announced December 2025.

PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design

Authors: Jiazhe Wei, Ken Li, Tianyu Lao, Haofan Wang, Liang Wang, Caifeng Shan, Chenyang Si

Abstract: Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automating this process using Large Multimodal Models (LMMs), yet existing methods often produce geometrically inaccurate layouts and lack the iterative, layer-specific editing required in professional workflows. To address these… ▽ More Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automating this process using Large Multimodal Models (LMMs), yet existing methods often produce geometrically inaccurate layouts and lack the iterative, layer-specific editing required in professional workflows. To address these limitations, we present PosterCopilot, a framework that advances layout reasoning and controllable editing for professional graphic design. Specifically, we introduce a progressive three-stage training strategy that equips LMMs with geometric understanding and aesthetic reasoning for layout design, consisting of Perturbed Supervised Fine-Tuning, Reinforcement Learning for Visual-Reality Alignment, and Reinforcement Learning from Aesthetic Feedback. Furthermore, we develop a complete workflow that couples the trained LMM-based design model with generative models, enabling layer-controllable, iterative editing for precise element refinement while maintaining global visual consistency. Extensive experiments demonstrate that PosterCopilot achieves geometrically accurate and aesthetically superior layouts, offering unprecedented controllability for professional iterative design. △ Less

Submitted 3 December, 2025; originally announced December 2025.

Comments: Project page: https://postercopilot.github.io/

PhyCustom: Towards Realistic Physical Customization in Text-to-Image Generation

Authors: Fan Wu, Cheng Chen, Zhoujie Fu, Jiacheng Wei, Yi Xu, Deheng Ye, Guosheng Lin

Abstract: Recent diffusion-based text-to-image customization methods have achieved significant success in understanding concrete concepts to control generation processes, such as styles and shapes. However, few efforts dive into the realistic yet challenging customization of physical concepts. The core limitation of current methods arises from the absence of explicitly introducing physical knowledge during… ▽ More Recent diffusion-based text-to-image customization methods have achieved significant success in understanding concrete concepts to control generation processes, such as styles and shapes. However, few efforts dive into the realistic yet challenging customization of physical concepts. The core limitation of current methods arises from the absence of explicitly introducing physical knowledge during training. Even when physics-related words appear in the input text prompts, our experiments consistently demonstrate that these methods fail to accurately reflect the corresponding physical properties in the generated results. In this paper, we propose PhyCustom, a fine-tuning framework comprising two novel regularization losses to activate diffusion model to perform physical customization. Specifically, the proposed isometric loss aims at activating diffusion models to learn physical concepts while decouple loss helps to eliminate the mixture learning of independent concepts. Experiments are conducted on a diverse dataset and our benchmark results demonstrate that PhyCustom outperforms previous state-of-the-art and popular methods in terms of physical customization quantitatively and qualitatively. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Comments: codes:https://github.com/wufan-cse/PhyCustom

IC-World: In-Context Generation for Shared World Modeling

Authors: Fan Wu, Jiacheng Wei, Ruibo Li, Yi Xu, Junyou Li, Deheng Ye, Guosheng Lin

Abstract: Video-based world models have recently garnered increasing attention for their ability to synthesize diverse and dynamic visual environments. In this paper, we focus on shared world modeling, where a model generates multiple videos from a set of input images, each representing the same underlying world in different camera poses. We propose IC-World, a novel generation framework, enabling parallel… ▽ More Video-based world models have recently garnered increasing attention for their ability to synthesize diverse and dynamic visual environments. In this paper, we focus on shared world modeling, where a model generates multiple videos from a set of input images, each representing the same underlying world in different camera poses. We propose IC-World, a novel generation framework, enabling parallel generation for all input images via activating the inherent in-context generation capability of large video models. We further finetune IC-World via reinforcement learning, Group Relative Policy Optimization, together with two proposed novel reward models to enforce scene-level geometry consistency and object-level motion consistency among the set of generated videos. Extensive experiments demonstrate that IC-World substantially outperforms state-of-the-art methods in both geometry and motion consistency. To the best of our knowledge, this is the first work to systematically explore the shared world modeling problem with video-based world models. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Comments: codes:https://github.com/wufan-cse/IC-World

SUPERChem: A Multimodal Reasoning Benchmark in Chemistry

Authors: Zehua Zhao, Zhixian Huang, Junren Li, Siyu Lin, Junting Zhou, Fengqi Cao, Kun Zhou, Rui Ge, Tingting Long, Yuexiang Zhu, Yan Liu, Jie Zheng, Junnian Wei, Rong Zhu, Peng Zou, Wenyu Li, Zekai Cheng, Tian Ding, Yaxuan Wang, Yizhao Yan, Tingru Wei, Haowei Ming, Weijie Mao, Chen Sun, Yiming Liu , et al. (6 additional authors not shown)

Abstract: Current benchmarks for evaluating the chemical reasoning capabilities of Large Language Models (LLMs) are limited by oversimplified tasks, lack of process-level evaluation, and misalignment with expert-level chemistry skills. To address these issues, we introduce SUPERChem, a benchmark of 500 expert-curated reasoning-intensive chemistry problems, covering diverse subfields and provided in both mul… ▽ More Current benchmarks for evaluating the chemical reasoning capabilities of Large Language Models (LLMs) are limited by oversimplified tasks, lack of process-level evaluation, and misalignment with expert-level chemistry skills. To address these issues, we introduce SUPERChem, a benchmark of 500 expert-curated reasoning-intensive chemistry problems, covering diverse subfields and provided in both multimodal and text-only formats. Original content and an iterative curation pipeline eliminate flawed items and mitigate data contamination. Each problem is paired with an expert-authored solution path, enabling Reasoning Path Fidelity (RPF) scoring to evaluate reasoning quality beyond final-answer accuracy. Evaluations against a human baseline of 40.3% accuracy show that even the best-performing model, GPT-5 (High), reaches only 38.5%, followed closely by Gemini 2.5 Pro (37.9%) and DeepSeek-V3.1-Think (37.3%). SUPERChem elicits multi-step, multimodal reasoning, reveals model-dependent effects of visual information, and distinguishes high-fidelity reasoners from heuristic ones. By providing a challenging benchmark and a reliable evaluation framework, SUPERChem aims to facilitate the advancement of LLMs toward expert-level chemical intelligence. The dataset of the benchmark is available at https://huggingface.co/datasets/ZehuaZhao/SUPERChem. △ Less

Submitted 30 November, 2025; originally announced December 2025.

Comments: 35 pages, 11 figures, 5 tables

TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE

Authors: Jiawen Wei, Lan Jiang, Pengbo Wei, Ziwen Ye, Teng Song, Chen Chen, Guangrui Ma

Abstract: Time series data is ubiquitous, with forecasting applications spanning from finance to healthcare. Beyond popular deterministic methods, generative models are gaining attention due to advancements in areas like image synthesis and video generation, as well as their inherent ability to provide probabilistic predictions. However, existing generative approaches mostly involve recurrent generative ope… ▽ More Time series data is ubiquitous, with forecasting applications spanning from finance to healthcare. Beyond popular deterministic methods, generative models are gaining attention due to advancements in areas like image synthesis and video generation, as well as their inherent ability to provide probabilistic predictions. However, existing generative approaches mostly involve recurrent generative operations or repeated denoising steps, making the prediction laborious, particularly for long-term forecasting. Most of them only conduct experiments for relatively short-term forecasting, with limited comparison to deterministic methods in long-term forecasting, leaving their practical advantages unclear. This paper presents TARFVAE, a novel generative framework that combines the Transformer-based autoregressive flow (TARFLOW) and variational autoencoder (VAE) for efficient one-step generative time series forecasting. Inspired by the rethinking that complex architectures for extracting time series representations might not be necessary, we add a flow module, TARFLOW, to VAE to promote spontaneous learning of latent variables that benefit predictions. TARFLOW enhances VAE's posterior estimation by breaking the Gaussian assumption, thereby enabling a more informative latent space. TARFVAE uses only the forward process of TARFLOW, avoiding autoregressive inverse operations and thus ensuring fast generation. During generation, it samples from the prior latent space and directly generates full-horizon forecasts via the VAE decoder. With simple MLP modules, TARFVAE achieves superior performance over state-of-the-art deterministic and generative models across different forecast horizons on benchmark datasets while maintaining efficient prediction speed, demonstrating its effectiveness as an efficient and powerful solution for generative time series forecasting. △ Less

Submitted 27 November, 2025; originally announced November 2025.

POLARIS: Cross-Domain Access Control via Verifiable Identity and Policy-Based Authorization

Authors: Aiyao Zhang, Xiaodong Lee, Zhixian Zhuang, Jiuqi Wei, Yufan Fu, Botao Peng

Abstract: Access control is a security mechanism designed to ensure that only authorized users can access specific resources. Cross-domain access control involves access to resources across different organizations, institutions, or applications. Traditional access control, however, which handles authentication and authorization separately in centralized environments, faces challenges in identity dispersion,… ▽ More Access control is a security mechanism designed to ensure that only authorized users can access specific resources. Cross-domain access control involves access to resources across different organizations, institutions, or applications. Traditional access control, however, which handles authentication and authorization separately in centralized environments, faces challenges in identity dispersion, privacy leakage, and diversified permission requirements, failing to adapt to cross-domain scenarios. Thus, there is an urgent need for a new access control mechanism that empowers autonomous control over user identity and resources, addressing the demands for privacy-preserving authentication and flexible authorization in cross-domain scenarios. To address cross-domain access control challenges, we propose POLARIS, a unified and extensible architecture that enables policy-based, verifiable and privacy-preserving access control across different domains. POLARIS features a structured commitment mechanism for reliable, fine-grained, policy-based identity disclosure. It further introduces VPPL, a lightweight policy language that supports issuer-bound evaluation of selectively revealed attributes. A dedicated session-level security mechanism ensures binding between authentication and access, enhancing confidentiality and resilience to replay attacks. We implement a working prototype and conduct comprehensive experiments, demonstrating that POLARIS effectively provides scalable, privacy-preserving, and interoperable access control across heterogeneous domains. Our results highlight the practical viability of POLARIS for enabling secure and privacy-preserving access control in decentralized, cross-domain environments. △ Less

Submitted 26 November, 2025; originally announced November 2025.

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

Authors: Zhoujie Fu, Xianfang Zeng, Jinghong Lan, Xinyao Liao, Cheng Chen, Junyi Chen, Jiacheng Wei, Wei Cheng, Shiyu Liu, Yunuo Chen, Gang Yu, Guosheng Lin

Abstract: Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data. We hypothesize that by injecting the rich and unconstrained content diversity from image data into this coherent temporal framework, we can generate image sets t… ▽ More Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data. We hypothesize that by injecting the rich and unconstrained content diversity from image data into this coherent temporal framework, we can generate image sets that feature both natural transitions and a far more expansive dynamic range. To this end, we introduce iMontage, a unified framework designed to repurpose a powerful video model into an all-in-one image generator. The framework consumes and produces variable-length image sets, unifying a wide array of image generation and editing tasks. To achieve this, we propose an elegant and minimally invasive adaptation strategy, complemented by a tailored data curation process and training paradigm. This approach allows the model to acquire broad image manipulation capabilities without corrupting its invaluable original motion priors. iMontage excels across several mainstream many-in-many-out tasks, not only maintaining strong cross-image contextual consistency but also generating scenes with extraordinary dynamics that surpass conventional scopes. Find our homepage at: https://kr1sjfu.github.io/iMontage-web/. △ Less

Submitted 1 December, 2025; v1 submitted 25 November, 2025; originally announced November 2025.

Comments: Our homepage: https://kr1sjfu.github.io/iMontage-web/

Coupled Physics-Gated Adaptation: Spatially Decoding Volumetric Photochemical Conversion in Complex 3D-Printed Objects

Authors: Maryam Eftekharifar, Churun Zhang, Jialiang Wei, Xudong Cao, Hossein Heidari

Abstract: We present a framework that pioneers the prediction of photochemical conversion in complex three-dimensionally printed objects, introducing a challenging new computer vision task: predicting dense, non-visual volumetric physical properties from 3D visual data. This approach leverages the largest-ever optically printed 3D specimen dataset, comprising a large family of parametrically designed comple… ▽ More We present a framework that pioneers the prediction of photochemical conversion in complex three-dimensionally printed objects, introducing a challenging new computer vision task: predicting dense, non-visual volumetric physical properties from 3D visual data. This approach leverages the largest-ever optically printed 3D specimen dataset, comprising a large family of parametrically designed complex minimal surface structures that have undergone terminal chemical characterisation. Conventional vision models are ill-equipped for this task, as they lack an inductive bias for the coupled, non-linear interactions of optical physics (diffraction, absorption) and material physics (diffusion, convection) that govern the final chemical state. To address this, we propose Coupled Physics-Gated Adaptation (C-PGA), a novel multimodal fusion architecture. Unlike standard concatenation, C-PGA explicitly models physical coupling by using sparse geometrical and process parameters (e.g., surface transport, print layer height) as a Query to dynamically gate and adapt the dense visual features via feature-wise linear modulation (FiLM). This mechanism spatially modulates dual 3D visual streams-extracted by parallel 3D-CNNs processing raw projection stacks and their diffusion-diffraction corrected counterparts allowing the model to recalibrate its visual perception based on the physical context. This approach offers a breakthrough in virtual chemical characterisation, eliminating the need for traditional post-print measurements and enabling precise control over the chemical conversion state. △ Less

Submitted 24 November, 2025; originally announced November 2025.

LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models

Authors: Shuai Wang, Daoan Zhang, Tianyi Bai, Shitong Shao, Jiebo Luo, Jiaheng Wei

Abstract: Humans can perceive and understand 3D space and long videos from sequential visual observations. But do vision-language models (VLMs) can? Recent work demonstrates that even state-of-the-art VLMs still struggle to understand 3D space and long videos, although they are powerful in typical vision-language tasks. Current methods often rely on specialized architectural designs to improve performance f… ▽ More Humans can perceive and understand 3D space and long videos from sequential visual observations. But do vision-language models (VLMs) can? Recent work demonstrates that even state-of-the-art VLMs still struggle to understand 3D space and long videos, although they are powerful in typical vision-language tasks. Current methods often rely on specialized architectural designs to improve performance for 3D tasks and video understanding tasks separately. In contrast, we propose LAST, short for LeArn to Think in Space and Time, to jointly improve 3D spatial and long video understanding for general VLMs with only a set of 2D images as inputs. LAST makes VLMs think in space and time rather than only with text before giving the final answer, building visual thinking trajectories in 3D space and temporal dimension. We demonstrate the effectiveness of LAST in two scenarios: 1) zero-shot, where we directly prompt proprietary models; and 2) fine-tuning general VLMs with data that include thinking trajectories in 3D space and time. We show that LAST brings substantial gains in various benchmarks, including 3 spatial understanding, 4 video understanding, and 3 image understanding tasks. Notably, 15.8% gains on EgoSchema with GPT-4o in a zero-shot manner and 8.3 gains on VSI-Bench compared with Qwen2.5-VL-7B. △ Less

Submitted 24 November, 2025; originally announced November 2025.

FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning

Authors: Xin Yuan, Siqi Li, Jiateng Wei, Chengrui Zhu, Yanming Wu, Qingpeng Li, Jiajun Lv, Xiaoke Lan, Jun Chen, Yong Liu

Abstract: Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge. While heuristic methods are fast but yield suboptimal performance, more powerful search-based approaches like Reinforcement Learning are often hindered by prohibitive computational costs on large-scale models. To overcome this efficiency… ▽ More Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge. While heuristic methods are fast but yield suboptimal performance, more powerful search-based approaches like Reinforcement Learning are often hindered by prohibitive computational costs on large-scale models. To overcome this efficiency barrier, we propose FastForward Pruning. Its core is a decoupled, single-step RL framework that separates policy optimization from the complex budget satisfaction problem. Such a decoupling is crucial for efficiently searching the vast policy space of LLMs. This curriculum-based strategy begins with low-cost, simple tasks and gradually increases in complexity, significantly reducing the search's computational overhead. Evaluated on the LLaMA, Mistral, and OPT model families, our framework discovers pruning policies that achieve superior performance over strong heuristic baselines. Crucially, when compared to other search-based algorithms, our method achieves competitive or superior results at a fraction of the computational cost, demonstrating a clear advantage in search efficiency. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: 5 pages, 2 figures, 4 tables

ACM Class: I.2.7; I.2.6

N2N: A Parallel Framework for Large-Scale MILP under Distributed Memory

Authors: Longfei Wang, Junyan Liu, Fan Zhang, Jiangwen Wei, Yuanhua Tang, Jie Sun, Xiaodong Luo

Abstract: Parallelization has emerged as a promising approach for accelerating MILP solving. However, the complexity of the branch-and-bound (B&B) framework and the numerous effective algorithm components in MILP solvers make it difficult to parallelize. In this study, a scalable parallel framework, N2N (a node-to-node framework that maps the B&B nodes to distributed computing nodes), was proposed to solve… ▽ More Parallelization has emerged as a promising approach for accelerating MILP solving. However, the complexity of the branch-and-bound (B&B) framework and the numerous effective algorithm components in MILP solvers make it difficult to parallelize. In this study, a scalable parallel framework, N2N (a node-to-node framework that maps the B&B nodes to distributed computing nodes), was proposed to solve large-scale problems in a distributed memory computing environment. Both deterministic and nondeterministic modes are supported, and the framework is designed to be easily integrated with existing solvers. Regarding the deterministic mode, a novel sliding-window-based algorithm was designed and implemented to ensure that tasks are generated and solved in a deterministic order. Moreover, several advanced techniques, such as the utilization of CP search and general primal heuristics, have been developed to fully utilize distributed computing resources and capabilities of base solvers. Adaptive solving and data communication optimization were also investigated. A popular open-source MILP solver, SCIP, was integrated into N2N as the base solver, yielding N2N-SCIP. Extensive computational experiments were conducted to evaluate the performance of N2N-SCIP compared to ParaSCIP, which is a state-of-the-art distributed parallel MILP solver under the UG framework. The nondeterministic N2N-SCIP achieves speedups of 22.52 and 12.71 with 1,000 MPI processes on the Kunpeng and x86 computing clusters, which is 1.98 and 2.08 times faster than ParaSCIP, respectively. In the deterministic mode, N2N-SCIP also shows significant performance improvements over ParaSCIP across different process numbers and computing clusters. To validate the generality of N2N, HiGHS, another open-source solver, was integrated into N2N. The related results are analyzed, and the requirements of N2N on base solvers are also concluded. △ Less

Submitted 18 December, 2025; v1 submitted 23 November, 2025; originally announced November 2025.

Comments: 18 pages, 2 figures; the affiliation of some authors is updated in this version

ACM Class: I.2.8; D.1.3

MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration

Authors: Runxun Zhang, Yizhou Liu, Li Dongrui, Bo XU, Jingwei Wei

Abstract: Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level supervision. Existing reinforcement learning frameworks often project this space into coarse, low-dimensional representations, limiting their ability to capture s… ▽ More Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level supervision. Existing reinforcement learning frameworks often project this space into coarse, low-dimensional representations, limiting their ability to capture spatially variant deformations. We propose MorphSeek, a fine-grained representation-level policy optimization paradigm that reformulates DIR as a spatially continuous optimization process in the latent feature space. MorphSeek introduces a stochastic Gaussian policy head atop the encoder to model a distribution over latent features, facilitating efficient exploration and coarse-to-fine refinement. The framework integrates unsupervised warm-up with weakly supervised fine-tuning through Group Relative Policy Optimization, where multi-trajectory sampling stabilizes training and improves label efficiency. Across three 3D registration benchmarks (OASIS brain MRI, LiTS liver CT, and Abdomen MR-CT), MorphSeek achieves consistent Dice improvements over competitive baselines while maintaining high label efficiency with minimal parameter cost and low step-level latency overhead. Beyond optimizer specifics, MorphSeek advances a representation-level policy learning paradigm that achieves spatially coherent and data-efficient deformation optimization, offering a principled, backbone-agnostic, and optimizer-agnostic solution for scalable visual alignment in high-dimensional settings. △ Less

Submitted 21 November, 2025; originally announced November 2025.

An Enhanced Whale Optimization Algorithm with Log-Normal Distribution for Optimizing Coverage of Wireless Sensor Networks

Authors: Junhao Wei, Yanzhao Gu, Ran Zhang, Yanxiao Li, Wenxuan Zhu, Jinhong Song, Yapeng Wang, Xu Yang, Ngai Cheong

Abstract: Wireless Sensor Networks (WSNs) are essential for monitoring and communication in complex environments, where coverage optimization directly affects performance and energy efficiency. However, traditional algorithms such as the Whale Optimization Algorithm (WOA) often suffer from limited exploration and premature convergence. To overcome these issues, this paper proposes an enhanced WOA which is c… ▽ More Wireless Sensor Networks (WSNs) are essential for monitoring and communication in complex environments, where coverage optimization directly affects performance and energy efficiency. However, traditional algorithms such as the Whale Optimization Algorithm (WOA) often suffer from limited exploration and premature convergence. To overcome these issues, this paper proposes an enhanced WOA which is called GLNWOA. GLNWOA integrates a log-normal distribution model into WOA to improve convergence dynamics and search diversity. GLNWOA employs a Good Nodes Set initialization for uniform population distribution, a Leader Cognitive Guidance Mechanism for efficient information sharing, and an Enhanced Spiral Updating Strategy to balance global exploration and local exploitation. Tests on benchmark functions verify its superior convergence accuracy and robustness. In WSN coverage optimization, deploying 25 nodes in a 60 m $\times$ 60 m area achieved a 99.0013\% coverage rate, outperforming AROA, WOA, HHO, ROA, and WOABAT by up to 15.5\%. These results demonstrate that GLNWOA offers fast convergence, high stability, and excellent optimization capability for intelligent network deployment. △ Less

Submitted 2 December, 2025; v1 submitted 19 November, 2025; originally announced November 2025.

From Black Box to Insight: Explainable AI for Extreme Event Preparedness

Authors: Kiana Vu, İsmet Selçuk Özer, Phung Lai, Zheng Wu, Thilanka Munasinghe, Jennifer Wei

Abstract: As climate change accelerates the frequency and severity of extreme events such as wildfires, the need for accurate, explainable, and actionable forecasting becomes increasingly urgent. While artificial intelligence (AI) models have shown promise in predicting such events, their adoption in real-world decision-making remains limited due to their black-box nature, which limits trust, explainability… ▽ More As climate change accelerates the frequency and severity of extreme events such as wildfires, the need for accurate, explainable, and actionable forecasting becomes increasingly urgent. While artificial intelligence (AI) models have shown promise in predicting such events, their adoption in real-world decision-making remains limited due to their black-box nature, which limits trust, explainability, and operational readiness. This paper investigates the role of explainable AI (XAI) in bridging the gap between predictive accuracy and actionable insight for extreme event forecasting. Using wildfire prediction as a case study, we evaluate various AI models and employ SHapley Additive exPlanations (SHAP) to uncover key features, decision pathways, and potential biases in model behavior. Our analysis demonstrates how XAI not only clarifies model reasoning but also supports critical decision-making by domain experts and response teams. In addition, we provide supporting visualizations that enhance the interpretability of XAI outputs by contextualizing feature importance and temporal patterns in seasonality and geospatial characteristics. This approach enhances the usability of AI explanations for practitioners and policymakers. Our findings highlight the need for AI systems that are not only accurate but also interpretable, accessible, and trustworthy, essential for effective use in disaster preparedness, risk mitigation, and climate resilience planning. △ Less

Submitted 17 November, 2025; originally announced November 2025.

Calibrated Multimodal Representation Learning with Missing Modalities

Authors: Xiaohao Liu, Xiaobo Xia, Jiaheng Wei, Shuo Yang, Xiu Su, See-Kiong Ng, Tat-Seng Chua

Abstract: Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space. Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but requires all modalities to be present for a common instance, making it challenging to utilize prevalent datasets with missing modalities. We provide theoretical insights into this iss… ▽ More Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space. Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but requires all modalities to be present for a common instance, making it challenging to utilize prevalent datasets with missing modalities. We provide theoretical insights into this issue from an anchor shift perspective. Observed modalities are aligned with a local anchor that deviates from the optimal one when all modalities are present, resulting in an inevitable shift. To address this, we propose CalMRL for multimodal representation learning to calibrate incomplete alignments caused by missing modalities. Specifically, CalMRL leverages the priors and the inherent connections among modalities to model the imputation for the missing ones at the representation level. To resolve the optimization dilemma, we employ a bi-step learning method with the closed-form solution of the posterior distribution of shared latents. We validate its mitigation of anchor shift and convergence with theoretical guidance. By equipping the calibrated alignment with the existing advanced method, we offer new flexibility to absorb data with missing modalities, which is originally unattainable. Extensive experiments and comprehensive analyses demonstrate the superiority of CalMRL. Our code, model checkpoints, and evaluation raw data will be publicly available. △ Less

Submitted 15 November, 2025; originally announced November 2025.

VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models

Authors: Mingjie Xu, Jinpeng Chen, Yuzhi Zhao, Jason Chun Lok Li, Yue Qiu, Zekang Du, Mengyang Wu, Pingping Zhang, Kun Li, Hongzheng Yang, Wenao Ma, Jiaheng Wei, Qinbin Li, Kangcheng Liu, Wenqiang Lei

Abstract: Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image, human users naturally use "visual prompts" (VPs), such as bounding boxes, to provide reference. However, no existing benchmark systematically evaluates the ability… ▽ More Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image, human users naturally use "visual prompts" (VPs), such as bounding boxes, to provide reference. However, no existing benchmark systematically evaluates the ability of MLLMs to interpret such VPs. This gap leaves it unclear whether current MLLMs can effectively recognize VPs, an intuitive prompting method for humans, and use them to solve problems. To address this limitation, we introduce VP-Bench, a benchmark for assessing MLLMs' capability in VP perception and utilization. VP-Bench employs a two-stage evaluation framework: Stage 1 examines models' ability to perceive VPs in natural scenes, using 30k visualized prompts spanning eight shapes and 355 attribute combinations. Stage 2 investigates the impact of VPs on downstream tasks, measuring their effectiveness in real-world problem-solving scenarios. Using VP-Bench, we evaluate 28 MLLMs, including proprietary systems (e.g., GPT-4o) and open-source models (e.g., InternVL3 and Qwen2.5-VL), and provide a comprehensive analysis of factors that affect VP understanding, such as variations in VP attributes, question arrangement, and model scale. VP-Bench establishes a new reference framework for studying how MLLMs comprehend and resolve grounded referring questions. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Comments: This is the extended version of the paper accepted at AAAI 2026, which includes all technical appendices and additional experimental details

T-MAN: Enabling End-to-End Low-Bit LLM Inference on NPUs via Unified Table Lookup

Authors: Jianyu Wei, Qingtao Li, Shijie Cao, Lingxiao Ma, Zixu Hao, Yanyong Zhang, Xiaoyan Hu, Ting Cao

Abstract: Large language models (LLMs) are increasingly deployed on customer devices. To support them, current devices are adopting SoCs (System on Chip) with NPUs (Neural Processing Unit) installed. Although high performance is expected, LLM inference on NPUs is slower than its CPU counterpart. The reason is that NPUs have poor performance on computations other than GEMM, like dequantization. Current works… ▽ More Large language models (LLMs) are increasingly deployed on customer devices. To support them, current devices are adopting SoCs (System on Chip) with NPUs (Neural Processing Unit) installed. Although high performance is expected, LLM inference on NPUs is slower than its CPU counterpart. The reason is that NPUs have poor performance on computations other than GEMM, like dequantization. Current works either disaggregate prefill on the NPUs and decoding on the CPUs, or put both on the NPUs but with an accuracy loss. To solve this issue, based on the insight that low-bit can enable target computation encoded within an acceptably sized table, we propose table lookup to subsume hardware operations otherwise unsupported. To realize this, we overcome the conflicting hardware behavior of prefill and decoding to design a unified table layout and tiling through (1) fused two-level table-based dequantization and (2) concurrency-hierarchy-guided tiling. Based on that, we implement the prefill phase by three-stage pipeline and map the table-lookup-based decoding to NPU's vector units. Results show 1.4x and 3.1x speedup for prefill and decoding respectively, and 84% energy savings compared to the baseline NPU methods. The code is available at https://github.com/microsoft/T-MAC/tree/main/t-man. △ Less

Submitted 14 November, 2025; originally announced November 2025.

GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models

Authors: Jingxuan Wei, Caijun Jia, Xi Bai, Xinglong Xu, Siyuan Li, Linzhuang Sun, Bihui Yu, Conghui He, Lijun Wu, Cheng Tan

Abstract: The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their unprecedented ability to synthesize information, a critical gap persists in evaluation: existing benchmarks primarily assess discriminative understanding or unconstrained image generation separately, failing to measure t… ▽ More The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their unprecedented ability to synthesize information, a critical gap persists in evaluation: existing benchmarks primarily assess discriminative understanding or unconstrained image generation separately, failing to measure the integrated cognitive process of generative reasoning. To bridge this gap, we propose that geometric construction provides an ideal testbed as it inherently demands a fusion of language comprehension and precise visual generation. We introduce GGBench, a benchmark designed specifically to evaluate geometric generative reasoning. It provides a comprehensive framework for systematically diagnosing a model's ability to not only understand and reason but to actively construct a solution, thereby setting a more rigorous standard for the next generation of intelligent systems. Project website: https://opendatalab-raiser.github.io/GGBench/. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Comments: 35 pages, 22 figures

eXIAA: eXplainable Injections for Adversarial Attack

Authors: Leonardo Pesce, Jiawen Wei, Gianmarco Mengaldo

Abstract: Post-hoc explainability methods are a subset of Machine Learning (ML) that aim to provide a reason for why a model behaves in a certain way. In this paper, we show a new black-box model-agnostic adversarial attack for post-hoc explainable Artificial Intelligence (XAI), particularly in the image domain. The goal of the attack is to modify the original explanations while being undetected by the huma… ▽ More Post-hoc explainability methods are a subset of Machine Learning (ML) that aim to provide a reason for why a model behaves in a certain way. In this paper, we show a new black-box model-agnostic adversarial attack for post-hoc explainable Artificial Intelligence (XAI), particularly in the image domain. The goal of the attack is to modify the original explanations while being undetected by the human eye and maintain the same predicted class. In contrast to previous methods, we do not require any access to the model or its weights, but only to the model's computed predictions and explanations. Additionally, the attack is accomplished in a single step while significantly changing the provided explanations, as demonstrated by empirical evaluation. The low requirements of our method expose a critical vulnerability in current explainability methods, raising concerns about their reliability in safety-critical applications. We systematically generate attacks based on the explanations generated by post-hoc explainability methods (saliency maps, integrated gradients, and DeepLIFT SHAP) for pretrained ResNet-18 and ViT-B16 on ImageNet. The results show that our attacks could lead to dramatically different explanations without changing the predictive probabilities. We validate the effectiveness of our attack, compute the induced change based on the explanation with mean absolute difference, and verify the closeness of the original image and the corrupted one with the Structural Similarity Index Measure (SSIM). △ Less

Submitted 13 November, 2025; originally announced November 2025.

MultiTab: A Scalable Foundation for Multitask Learning on Tabular Data

Authors: Dimitrios Sinodinos, Jack Yi Wei, Narges Armanfard

Abstract: Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task information for improved multitask generalization. Multitask learning (MTL) has emerged as a powerful way to improve generalization and efficiency, yet most existing… ▽ More Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task information for improved multitask generalization. Multitask learning (MTL) has emerged as a powerful way to improve generalization and efficiency, yet most existing work focuses narrowly on large-scale recommendation systems, leaving its potential in broader tabular domains largely underexplored. Also, existing MTL approaches for tabular data predominantly rely on multi-layer perceptron-based backbones, which struggle to capture complex feature interactions and often fail to scale when data is abundant, a limitation that transformer architectures have overcome in other domains. Motivated by this, we introduce MultiTab-Net, the first multitask transformer architecture specifically designed for large tabular data. MultiTab-Net employs a novel multitask masked-attention mechanism that dynamically models feature-feature dependencies while mitigating task competition. Through extensive experiments, we show that MultiTab-Net consistently achieves higher multitask gain than existing MTL architectures and single-task transformers across diverse domains including large-scale recommendation data, census-like socioeconomic data, and physics datasets, spanning a wide range of task counts, task types, and feature modalities. In addition, we contribute MultiTab-Bench, a generalized multitask synthetic dataset generator that enables systematic evaluation of multitask dynamics by tuning task count, task correlations, and relative task complexity. Our code is publicly available at https://github.com/Armanfard-Lab/MultiTab. △ Less

Submitted 13 November, 2025; originally announced November 2025.

Comments: Accepted for publication at AAAI 2026

Vmem: A Lightweight Hot-Upgradable Memory Management for In-production Cloud Environment

Authors: Hao Zheng, Qiang Wang, Longxiang Wang, Xishi Qiu, Yibin Shen, Xiaoshe Dong, Naixuan Guan, Jia Wei, Fudong Qiu, Xingjun Zhang, Yun Xu, Mao Zhao, Yisheng Xie, Shenglong Zhao, Min He, Yu Li, Xiao Zheng, Ben Luo, Jiesheng Wu

Abstract: Traditional memory management suffers from metadata overhead, architectural complexity, and stability degradation, problems intensified in cloud environments. Existing software/hardware optimizations are insufficient for cloud computing's dual demands of flexibility and low overhead. This paper presents Vmem, a memory management architecture for in-production cloud environments that enables flexib… ▽ More Traditional memory management suffers from metadata overhead, architectural complexity, and stability degradation, problems intensified in cloud environments. Existing software/hardware optimizations are insufficient for cloud computing's dual demands of flexibility and low overhead. This paper presents Vmem, a memory management architecture for in-production cloud environments that enables flexible, efficient cloud server memory utilization through lightweight reserved memory management. Vmem is the first such architecture to support online upgrades, meeting cloud requirements for high stability and rapid iterative evolution. Experiments show Vmem increases sellable memory rate by about 2%, delivers extreme elasticity and performance, achieves over 3x faster boot time for VFIO-based virtual machines (VMs), and improves network performance by about 10% for DPU-accelerated VMs. Vmem has been deployed at large scale for seven years, demonstrating efficiency and stability on over 300,000 cloud servers supporting hundreds of millions of VMs. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Taiji: A DPU Memory Elasticity Solution for In-production Cloud Environments

Authors: Hao Zheng, Longxiang Wang, Yun Xu, Qiang Wang, Yibin Shen, Xiaoshe Dong, Bang Di, Jia Wei, Shenyu Dong, Xingjun Zhang, Weichen Chen, Zhao Han, Sanqian Zhao, Dongdong Huang, Jie Qi, Yifan Yang, Zhao Gao, Yi Wang, Jinhu Li, Xudong Ren, Min He, Hang Yang, Xiao Zheng, Haijiao Hao, Jiesheng Wu

Abstract: The growth of cloud computing drives data centers toward higher density and efficiency. Data processing units (DPUs) enhance server network and storage performance but face challenges such as long hardware upgrade cycles and limited resources. To address these, we propose Taiji, a resource-elasticity architecture for DPUs. Combining hybrid virtualization with parallel memory swapping, Taiji switch… ▽ More The growth of cloud computing drives data centers toward higher density and efficiency. Data processing units (DPUs) enhance server network and storage performance but face challenges such as long hardware upgrade cycles and limited resources. To address these, we propose Taiji, a resource-elasticity architecture for DPUs. Combining hybrid virtualization with parallel memory swapping, Taiji switches the DPU's operating system (OS) into a guest OS and inserts a lightweight virtualization layer, making nearly all DPU memory swappable. It achieves memory overcommitment for the switched guest OS via high-performance memory elasticity, fully transparent to upper-layer applications, and supports hot-switch and hot-upgrade to meet in-production cloud requirements. Experiments show that Taiji expands DPU memory resources by over 50%, maintains virtualization overhead around 5%, and ensures 90% of swap-ins complete within 10 microseconds. Taiji delivers an efficient, reliable, low-overhead elasticity solution for DPUs and is deployed in large-scale production systems across more than 30,000 servers. △ Less

Submitted 14 November, 2025; v1 submitted 12 November, 2025; originally announced November 2025.

AWEMixer: Adaptive Wavelet-Enhanced Mixer Network for Long-Term Time Series Forecasting

Authors: Qianyang Li, Xingjun Zhang, Peng Tao, Shaoxun Wang, Yancheng Pan, Jia Wei

Abstract: Forecasting long-term time series in IoT environments remains a significant challenge due to the non-stationary and multi-scale characteristics of sensor signals. Furthermore, error accumulation causes a decrease in forecast quality when predicting further into the future. Traditional methods are restricted to operate in time-domain, while the global frequency information achieved by Fourier trans… ▽ More Forecasting long-term time series in IoT environments remains a significant challenge due to the non-stationary and multi-scale characteristics of sensor signals. Furthermore, error accumulation causes a decrease in forecast quality when predicting further into the future. Traditional methods are restricted to operate in time-domain, while the global frequency information achieved by Fourier transform would be regarded as stationary signals leading to blur the temporal patterns of transient events. We propose AWEMixer, an Adaptive Wavelet-Enhanced Mixer Network including two innovative components: 1) a Frequency Router designs to utilize the global periodicity pattern achieved by Fast Fourier Transform to adaptively weight localized wavelet subband, and 2) a Coherent Gated Fusion Block to achieve selective integration of prominent frequency features with multi-scale temporal representation through cross-attention and gating mechanism, which realizes accurate time-frequency localization while remaining robust to noise. Seven public benchmarks validate that our model is more effective than recent state-of-the-art models. Specifically, our model consistently achieves performance improvement compared with transformer-based and MLP-based state-of-the-art models in long-sequence time series forecasting. Code is available at https://github.com/hit636/AWEMixer △ Less

Submitted 6 November, 2025; originally announced November 2025.

Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction

Authors: Peter Atandoh, Jie Zou, Weikang Guo, Jiwei Wei, Zheng Wang

Abstract: Sentiment analysis using deep learning and pre-trained language models (PLMs) has gained significant traction due to their ability to capture rich contextual representations. However, existing approaches often underperform in scenarios involving nuanced emotional cues, domain shifts, and imbalanced sentiment distributions. We argue that these limitations stem from inadequate semantic grounding, po… ▽ More Sentiment analysis using deep learning and pre-trained language models (PLMs) has gained significant traction due to their ability to capture rich contextual representations. However, existing approaches often underperform in scenarios involving nuanced emotional cues, domain shifts, and imbalanced sentiment distributions. We argue that these limitations stem from inadequate semantic grounding, poor generalization to diverse linguistic patterns, and biases toward dominant sentiment classes. To overcome these challenges, we propose CISEA-MRFE, a novel PLM-based framework integrating Contextual Instruction (CI), Semantic Enhancement Augmentation (SEA), and Multi-Refined Feature Extraction (MRFE). CI injects domain-aware directives to guide sentiment disambiguation; SEA improves robustness through sentiment-consistent paraphrastic augmentation; and MRFE combines a Scale-Adaptive Depthwise Encoder (SADE) for multi-scale feature specialization with an Emotion Evaluator Context Encoder (EECE) for affect-aware sequence modeling. Experimental results on four benchmark datasets demonstrate that CISEA-MRFE consistently outperforms strong baselines, achieving relative improvements in accuracy of up to 4.6% on IMDb, 6.5% on Yelp, 30.3% on Twitter, and 4.1% on Amazon. These results validate the effectiveness and generalization ability of our approach for sentiment classification across varied domains. △ Less

Submitted 4 November, 2025; v1 submitted 1 November, 2025; originally announced November 2025.

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration

Authors: Linzhuang Sun, Tianyu Guo, Hao Liang, Yuying Li, Qifeng Cai, Jingxuan Wei, Bihui Yu, Wentao Zhang, Bin Cui

Abstract: Recent advances in Text-to-SQL have achieved strong results in static, single-turn tasks, where models generate SQL queries from natural language questions. However, these systems fall short in real-world interactive scenarios, where user intents evolve and queries must be refined over multiple turns. In applications such as finance and business analytics, users iteratively adjust query constraint… ▽ More Recent advances in Text-to-SQL have achieved strong results in static, single-turn tasks, where models generate SQL queries from natural language questions. However, these systems fall short in real-world interactive scenarios, where user intents evolve and queries must be refined over multiple turns. In applications such as finance and business analytics, users iteratively adjust query constraints or dimensions based on intermediate results. To evaluate such dynamic capabilities, we introduce DySQL-Bench, a benchmark assessing model performance under evolving user interactions. Unlike previous manually curated datasets, DySQL-Bench is built through an automated two-stage pipeline of task synthesis and verification. Structured tree representations derived from raw database tables guide LLM-based task generation, followed by interaction-oriented filtering and expert validation. Human evaluation confirms 100% correctness of the synthesized data. We further propose a multi-turn evaluation framework simulating realistic interactions among an LLM-simulated user, the model under test, and an executable database. The model must adapt its reasoning and SQL generation as user intents change. DySQL-Bench covers 13 domains across BIRD and Spider 2 databases, totaling 1,072 tasks. Even GPT-4o attains only 58.34% overall accuracy and 23.81% on the Pass@5 metric, underscoring the benchmark's difficulty. All code and data are released at https://github.com/Aurora-slz/Real-World-SQL-Bench . △ Less

Submitted 13 November, 2025; v1 submitted 30 October, 2025; originally announced October 2025.

LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability

Authors: Zikai Xiao, Fei Huang, Jianhong Tu, Jianhui Wei, Wen Ma, Yuxuan Zhou, Jian Wu, Bowen Yu, Zuozhu Liu, Junyang Lin

Abstract: Generating long, informative, and factual outputs remains a major challenge for Large Language Models (LLMs). Existing benchmarks for long-form generation typically assess real-world queries with hard-to-verify metrics or use synthetic setups that ease evaluation but overlook real-world intricacies. In this paper, we introduce \textbf{LongWeave}, which balances real-world and verifiable assessment… ▽ More Generating long, informative, and factual outputs remains a major challenge for Large Language Models (LLMs). Existing benchmarks for long-form generation typically assess real-world queries with hard-to-verify metrics or use synthetic setups that ease evaluation but overlook real-world intricacies. In this paper, we introduce \textbf{LongWeave}, which balances real-world and verifiable assessment with Constraint-Verifier Evaluation (CoV-Eval). CoV-Eval constructs tasks by first defining verifiable targets within real-world scenarios, then systematically generating corresponding queries, textual materials, and constraints based on these targets. This ensures that tasks are both realistic and objectively assessable, enabling rigorous assessment of model capabilities in meeting complex real-world constraints. LongWeave supports customizable input/output lengths (up to 64K/8K tokens) across seven distinct tasks. Evaluation on 23 LLMs shows that even state-of-the-art models encounter significant challenges in long-form generation as real-world complexity and output length increase. △ Less

Submitted 28 October, 2025; originally announced October 2025.

Comments: EMNLP Findings 2025

ENTP: Enhancing Low-Quality SFT Data via Neural-Symbolic Text Purge-Mix

Authors: Zile Yang, Ling Li, Na Di, Jinlong Pang, Yao Zhou, Hao Cheng, Bo Han, Jiaheng Wei

Abstract: Supervised Fine-Tuning (SFT) adapts pre-trained Large Language Models (LLMs) to domain-specific instructions by training on a carefully curated subset of high-quality instruction-response pairs, typically drawn from a larger dataset that often contains many low-quality or noisy samples. However, existing quality-first paradigms often overlook valuable signals in discarded low-quality data and rely… ▽ More Supervised Fine-Tuning (SFT) adapts pre-trained Large Language Models (LLMs) to domain-specific instructions by training on a carefully curated subset of high-quality instruction-response pairs, typically drawn from a larger dataset that often contains many low-quality or noisy samples. However, existing quality-first paradigms often overlook valuable signals in discarded low-quality data and rely on imperfect quality filters. We introduce ENTP (Enhancing low-quality SFT data via Neural-symbolic Text Purge-Mix), a framework that revitalizes low-quality corpora through symbolic purification and neural reconstruction. The symbolic module identifies and prunes noisy samples based on statistical priors, while the neural component synthesizes enriched instruction-response pairs by leveraging latent representations and model knowledge. This neural-symbolic synergy enhances data informativeness and diversity. Experiments show that ENTP-augmented datasets, constructed exclusively from low-quality data, outperform 13 established data-selection baselines across five instruction-following benchmarks, and even surpass fine-tuning on the full original dataset (approximately 300K examples). Our results highlight the untapped potential of low-quality data and underscore the importance of intelligent purification and synthesis for efficient instruction alignment. △ Less

Submitted 27 October, 2025; originally announced October 2025.

OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models

Authors: Hao Zheng, Zirui Pang, Ling li, Zhijie Deng, Yuhan Pu, Zhaowei Zhu, Xiaobo Xia, Jiaheng Wei

Abstract: Advances in Multimodal Large Language Models (MLLMs) intensify concerns about data privacy, making Machine Unlearning (MU), the selective removal of learned information, a critical necessity. However, existing MU benchmarks for MLLMs are limited by a lack of image diversity, potential inaccuracies, and insufficient evaluation scenarios, which fail to capture the complexity of real-world applicatio… ▽ More Advances in Multimodal Large Language Models (MLLMs) intensify concerns about data privacy, making Machine Unlearning (MU), the selective removal of learned information, a critical necessity. However, existing MU benchmarks for MLLMs are limited by a lack of image diversity, potential inaccuracies, and insufficient evaluation scenarios, which fail to capture the complexity of real-world applications. To facilitate the development of MLLMs unlearning and alleviate the aforementioned limitations, we introduce OFFSIDE, a novel benchmark for evaluating misinformation unlearning in MLLMs based on football transfer rumors. This manually curated dataset contains 15.68K records for 80 players, providing a comprehensive framework with four test sets to assess forgetting efficacy, generalization, utility, and robustness. OFFSIDE supports advanced settings like selective unlearning and corrective relearning, and crucially, unimodal unlearning (forgetting only text data). Our extensive evaluation of multiple baselines reveals key findings: (1) Unimodal methods (erasing text-based knowledge) fail on multimodal rumors; (2) Unlearning efficacy is largely driven by catastrophic forgetting; (3) All methods struggle with "visual rumors" (rumors appear in the image); (4) The unlearned rumors can be easily recovered and (5) All methods are vulnerable to prompt attacks. These results expose significant vulnerabilities in current approaches, highlighting the need for more robust multimodal unlearning solutions. The code is available at \href{https://github.com/zh121800/OFFSIDE}{https://github.com/zh121800/OFFSIDE}. △ Less

Submitted 26 October, 2025; originally announced October 2025.

Label Smoothing Improves Gradient Ascent in LLM Unlearning

Authors: Zirui Pang, Hao Zheng, Zhijie Deng, Ling Li, Zixin Zhong, Jiaheng Wei

Abstract: LLM unlearning has emerged as a promising approach, aiming to enable models to forget hazardous/undesired knowledge at low cost while preserving as much model utility as possible. Among existing techniques, the most straightforward method is performing Gradient Ascent (GA) w.r.t. the forget data, thereby forcing the model to unlearn the forget dataset. However, GA suffers from severe instability,… ▽ More LLM unlearning has emerged as a promising approach, aiming to enable models to forget hazardous/undesired knowledge at low cost while preserving as much model utility as possible. Among existing techniques, the most straightforward method is performing Gradient Ascent (GA) w.r.t. the forget data, thereby forcing the model to unlearn the forget dataset. However, GA suffers from severe instability, as it drives updates in a divergent direction, often resulting in drastically degraded model utility. To address this issue, we propose Smoothed Gradient Ascent (SGA). SGA combines the forget data with multiple constructed normal data through a tunable smoothing rate. Intuitively, this extends GA from learning solely on the forget data to jointly learning across both forget and normal data, enabling more stable unlearning while better preserving model utility. Theoretically, we provide the theoretical guidance on the selection of the optimal smoothing rate. Empirically, we evaluate SGA on three benchmarks: TOFU, Harry Potter, and MUSE-NEWS. Experimental results demonstrate that SGA consistently outperforms the original Gradient Ascent (GA) method across all metrics and achieves top-2 performance among all baseline methods on several key metrics. △ Less

Submitted 25 October, 2025; originally announced October 2025.

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

Authors: Ling Team, Ang Li, Ben Liu, Binbin Hu, Bing Li, Bingwei Zeng, Borui Ye, Caizhi Tang, Changxin Tian, Chao Huang, Chao Zhang, Chen Qian, Chenchen Ju, Chenchen Li, Chengfu Tang, Chilin Fu, Chunshao Ren, Chunwei Wu, Cong Zhang, Cunyin Peng, Dafeng Xu, Daixin Wang, Dalong Zhang, Dingnan Jin, Dingyuan Zhu , et al. (117 additional authors not shown)

Abstract: We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three… ▽ More We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base. △ Less

Submitted 6 November, 2025; v1 submitted 24 October, 2025; originally announced October 2025.

Comments: Ling 2.0 Technical Report

SpecTokenizer: A Lightweight Streaming Codec in the Compressed Spectrum Domain

Authors: Zixiang Wan, Guochang Zhang, Yifeng He, Jianqiang Wei

Abstract: Neural Audio Codecs (NACs) have gained growing attention in recent years as technologies for audio compression and audio representation in speech language models. While mainstream NACs typically require G-level computation and M-level parameters, the performance of lightweight and streaming NACs remains underexplored. This paper proposes SpecTokenizer, a lightweight streaming codec that operates i… ▽ More Neural Audio Codecs (NACs) have gained growing attention in recent years as technologies for audio compression and audio representation in speech language models. While mainstream NACs typically require G-level computation and M-level parameters, the performance of lightweight and streaming NACs remains underexplored. This paper proposes SpecTokenizer, a lightweight streaming codec that operates in the compressed spectral domain. Composed solely of alternating CNN and RNN layers, SpecTokenizer achieves greater efficiency and better representational capability through multi-scale modeling in the compressed spectrum domain. At 4 kbps, the proposed SpecTokenizer achieves comparable or superior performance compared to the codec with state-of-the-art lightweight architecture while requiring only 20% of the computation and 10% of the parameters. Furthermore, it significantly outperforms the codec when using similar computational and storage resources. △ Less

Submitted 24 October, 2025; originally announced October 2025.

Comments: Accepted by Interspeech 2025; 5 pages, 1 figure, 5 tables

PhoenixCodec: Taming Neural Speech Coding for Extreme Low-Resource Scenarios

Authors: Zixiang Wan, Haoran Zhao, Guochang Zhang, Runqiang Han, Jianqiang Wei, Yuexian Zou

Abstract: This paper presents PhoenixCodec, a comprehensive neural speech coding and decoding framework designed for extremely low-resource conditions. The proposed system integrates an optimized asymmetric frequency-time architecture, a Cyclical Calibration and Refinement (CCR) training strategy, and a noise-invariant fine-tuning procedure. Under stringent constraints - computation below 700 MFLOPs, latenc… ▽ More This paper presents PhoenixCodec, a comprehensive neural speech coding and decoding framework designed for extremely low-resource conditions. The proposed system integrates an optimized asymmetric frequency-time architecture, a Cyclical Calibration and Refinement (CCR) training strategy, and a noise-invariant fine-tuning procedure. Under stringent constraints - computation below 700 MFLOPs, latency less than 30 ms, and dual-rate support at 1 kbps and 6 kbps - existing methods face a trade-off between efficiency and quality. PhoenixCodec addresses these challenges by alleviating the resource scattering of conventional decoders, employing CCR to escape local optima, and enhancing robustness through noisy-sample fine-tuning. In the LRAC 2025 Challenge Track 1, the proposed system ranked third overall and demonstrated the best performance at 1 kbps in both real-world noise and reverberation and intelligibility in clean tests, confirming its effectiveness. △ Less

Submitted 24 October, 2025; originally announced October 2025.

Comments: 5 pages, 1 figure, 4 tables

Robust Preference Alignment via Directional Neighborhood Consensus

Authors: Ruochen Mao, Yuling Shi, Xiaodong Gu, Jiaheng Wei

Abstract: Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between desired attributes (e.g., helpfulness vs. verbosity). Yet, because the training data often reflects dominant, average preferences, LLMs tend to perform well on c… ▽ More Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between desired attributes (e.g., helpfulness vs. verbosity). Yet, because the training data often reflects dominant, average preferences, LLMs tend to perform well on common requests but fall short in specific, individual needs. This mismatch creates a preference coverage gap. Existing methods often address this through costly retraining, which may not be generalized to the full spectrum of diverse preferences. This brittleness means that when a user's request reflects a nuanced preference deviating from the training data's central tendency, model performance can degrade unpredictably. To address this challenge, we introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus. Instead of forcing a model to generate a response from a single, highly specific preference, RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool. It then selects the response that best aligns with the user's original intent. We provide a theoretical framework showing our neighborhood generation strategy is provably superior to a strong baseline that also samples multiple candidates. Comprehensive experiments across three distinct alignment paradigms (DPA, DPO, and SFT) demonstrate that RPS consistently improves robustness against this baseline, achieving win rates of up to 69% on challenging preferences from under-represented regions of the space without any model retraining. Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models. △ Less

Submitted 23 October, 2025; v1 submitted 23 October, 2025; originally announced October 2025.

LM-mixup: Text Data Augmentation via Language Model based Mixup

Authors: Zhijie Deng, Zhouan Shen, Ling Li, Yao Zhou, Zhaowei Zhu, Yanji He, Wei Wang, Jiaheng Wei

Abstract: Instruction tuning is crucial for aligning Large Language Models (LLMs), yet the quality of instruction-following data varies significantly. While high-quality data is paramount, it is often scarce; conversely, abundant low-quality data is frequently discarded, leading to substantial information loss. Existing data augmentation methods struggle to augment this low-quality data effectively, and the… ▽ More Instruction tuning is crucial for aligning Large Language Models (LLMs), yet the quality of instruction-following data varies significantly. While high-quality data is paramount, it is often scarce; conversely, abundant low-quality data is frequently discarded, leading to substantial information loss. Existing data augmentation methods struggle to augment this low-quality data effectively, and the evaluation of such techniques remains poorly defined. To address this, we formally define the task of Instruction Distillation: distilling multiple low-quality and redundant inputs into high-quality and coherent instruction-output pairs. Specifically, we introduce a comprehensive data construction pipeline to create MIXTURE, a 144K-sample dataset pairing low-quality or semantically redundant imperfect instruction clusters with their high-quality distillations. We then introduce LM-Mixup, by first performing supervised fine-tuning on MIXTURE and then optimizing it with reinforcement learning. This process uses three complementary reward signals: quality, semantic alignment, and format compliance, via Group Relative Policy Optimization (GRPO). We demonstrate that LM-Mixup effectively augments imperfect datasets: fine-tuning LLMs on its distilled data, which accounts for only about 3% of the entire dataset, not only surpasses full-dataset training but also competes with state-of-the-art high-quality data selection methods across multiple benchmarks. Our work establishes that low-quality data is a valuable resource when properly distilled and augmented with LM-Mixup, significantly enhancing the efficiency and performance of instruction-tuned LLMs. △ Less

Submitted 23 October, 2025; originally announced October 2025.

Hubble: a Model Suite to Advance the Study of LLM Memorization

Authors: Johnny Tian-Zheng Wei, Ameya Godbole, Mohammad Aflah Khan, Ryan Wang, Xiaoyuan Zhu, James Flemings, Nitya Kashyap, Krishna P. Gummadi, Willie Neiswanger, Robin Jia

Abstract: We present Hubble, a suite of fully open-source large language models (LLMs) for the scientific study of LLM memorization. Hubble models come in standard and perturbed variants: standard models are pretrained on a large English corpus, and perturbed models are trained in the same way but with controlled insertion of text (e.g., book passages, biographies, and test sets) designed to emulate key mem… ▽ More We present Hubble, a suite of fully open-source large language models (LLMs) for the scientific study of LLM memorization. Hubble models come in standard and perturbed variants: standard models are pretrained on a large English corpus, and perturbed models are trained in the same way but with controlled insertion of text (e.g., book passages, biographies, and test sets) designed to emulate key memorization risks. Our core release includes 8 models -- standard and perturbed models with 1B or 8B parameters, pretrained on 100B or 500B tokens -- establishing that memorization risks are determined by the frequency of sensitive data relative to size of the training corpus (i.e., a password appearing once in a smaller corpus is memorized better than the same password in a larger corpus). Our release also includes 6 perturbed models with text inserted at different pretraining phases, showing that sensitive data without continued exposure can be forgotten. These findings suggest two best practices for addressing memorization risks: to dilute sensitive data by increasing the size of the training corpus, and to order sensitive data to appear earlier in training. Beyond these general empirical findings, Hubble enables a broad range of memorization research; for example, analyzing the biographies reveals how readily different types of private information are memorized. We also demonstrate that the randomized insertions in Hubble make it an ideal testbed for membership inference and machine unlearning, and invite the community to further explore, benchmark, and build upon our work. △ Less

Submitted 22 October, 2025; originally announced October 2025.

AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation

Authors: Xianyang Liu, Yilin Liu, Shuai Wang, Hao Cheng, Andrew Estornell, Yuzhi Zhao, Jiaheng Wei

Abstract: The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from available data sources. To address this, we propose AgenticMath, a novel agentic pipeline for generating high-quality mathematical question-answer pairs to enhance t… ▽ More The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from available data sources. To address this, we propose AgenticMath, a novel agentic pipeline for generating high-quality mathematical question-answer pairs to enhance the supervised fine-tuning of LLMs. Our method operates through four stages: (1) Seed Question Filter that selects questions with high information richness, complexity, and clarity; (2) an Agentic Question Rephrase step that employs a multi-agent system to generate diverse, logically consistent paraphrases; (3) an Answer Augment step where rewrite answers using chain-of-thought reasoning to enhance numerical and logical correctness, without reliance on human-provided labels; and (4) a final Question and Answer Evaluation that retains only the most superior pairs. Extensive experiments demonstrate that, fine-tuning 3B-8B parameter LLMs on AgenticMath generated datasets (comprising only 30-60K math samples) achieves competitive or superior performance on diverse in domain and out-of-domain mathematical reasoning benchmarks compared to baselines trained on much more data (e.g., 400K or 2.3M samples). Our work demonstrates that targeted, high-quality data generation is a more efficient path to improving mathematical reasoning in LLMs than large-scale, low-quality alternatives. △ Less

Submitted 5 November, 2025; v1 submitted 22 October, 2025; originally announced October 2025.

Comments: 9 pages

Noise-Conditioned Mixture-of-Experts Framework for Robust Speaker Verification

Authors: Bin Gu, Lipeng Dai, Huipeng Du, Haitao Zhao, Jibo Wei

Abstract: Robust speaker verification under noisy conditions remains an open challenge. Conventional deep learning methods learn a robust unified speaker representation space against diverse background noise and achieve significant improvement. In contrast, this paper presents a noise-conditioned mixture-ofexperts framework that decomposes the feature space into specialized noise-aware subspaces for speaker… ▽ More Robust speaker verification under noisy conditions remains an open challenge. Conventional deep learning methods learn a robust unified speaker representation space against diverse background noise and achieve significant improvement. In contrast, this paper presents a noise-conditioned mixture-ofexperts framework that decomposes the feature space into specialized noise-aware subspaces for speaker verification. Specifically, we propose a noise-conditioned expert routing mechanism, a universal model based expert specialization strategy, and an SNR-decaying curriculum learning protocol, collectively improving model robustness and generalization under diverse noise conditions. The proposed method can automatically route inputs to expert networks based on noise information derived from the inputs, where each expert targets distinct noise characteristics while preserving speaker identity information. Comprehensive experiments demonstrate consistent superiority over baselines, confirming that explicit noise-dependent feature modeling significantly enhances robustness without sacrificing verification accuracy. △ Less

Submitted 21 October, 2025; originally announced October 2025.

A Stage-Wise Learning Strategy with Fixed Anchors for Robust Speaker Verification

Authors: Bin Gu, Lipeng Dai, Huipeng Du, Haitao Zhao, Jibo Wei

Abstract: Learning robust speaker representations under noisy conditions presents significant challenges, which requires careful handling of both discriminative and noise-invariant properties. In this work, we proposed an anchor-based stage-wise learning strategy for robust speaker representation learning. Specifically, our approach begins by training a base model to establish discriminative speaker boundar… ▽ More Learning robust speaker representations under noisy conditions presents significant challenges, which requires careful handling of both discriminative and noise-invariant properties. In this work, we proposed an anchor-based stage-wise learning strategy for robust speaker representation learning. Specifically, our approach begins by training a base model to establish discriminative speaker boundaries, and then extract anchor embeddings from this model as stable references. Finally, a copy of the base model is fine-tuned on noisy inputs, regularized by enforcing proximity to their corresponding fixed anchor embeddings to preserve speaker identity under distortion. Experimental results suggest that this strategy offers advantages over conventional joint optimization, particularly in maintaining discrimination while improving noise robustness. The proposed method demonstrates consistent improvements across various noise conditions, potentially due to its ability to handle boundary stabilization and variation suppression separately. △ Less

Submitted 21 October, 2025; originally announced October 2025.

Learning Human-Object Interaction as Groups

Authors: Jiajun Hong, Jianan Wei, Wenguan Wang

Abstract: Human-Object Interaction Detection (HOI-DET) aims to localize human-object pairs and identify their interactive relationships. To aggregate contextual cues, existing methods typically propagate information across all detected entities via self-attention mechanisms, or establish message passing between humans and objects with bipartite graphs. However, they primarily focus on pairwise relationships… ▽ More Human-Object Interaction Detection (HOI-DET) aims to localize human-object pairs and identify their interactive relationships. To aggregate contextual cues, existing methods typically propagate information across all detected entities via self-attention mechanisms, or establish message passing between humans and objects with bipartite graphs. However, they primarily focus on pairwise relationships, overlooking that interactions in real-world scenarios often emerge from collective behaviors (multiple humans and objects engaging in joint activities). In light of this, we revisit relation modeling from a group view and propose GroupHOI, a framework that propagates contextual information in terms of geometric proximity and semantic similarity. To exploit the geometric proximity, humans and objects are grouped into distinct clusters using a learnable proximity estimator based on spatial features derived from bounding boxes. In each group, a soft correspondence is computed via self-attention to aggregate and dispatch contextual cues. To incorporate the semantic similarity, we enhance the vanilla transformer-based interaction decoder with local contextual cues from HO-pair features. Extensive experiments on HICO-DET and V-COCO benchmarks demonstrate the superiority of GroupHOI over the state-of-the-art methods. It also exhibits leading performance on the more challenging Nonverbal Interaction Detection (NVI-DET) task, which involves varied forms of higher-order interactions within groups. △ Less

Submitted 21 October, 2025; originally announced October 2025.

Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence

Authors: Qiongyan Wang, Xingchen Zou, Yutian Jiang, Haomin Wen, Jiaheng Wei, Qingsong Wen, Yuxuan Liang

Abstract: Rapid urbanization intensifies the demand for Urban General Intelligence (UGI), referring to AI systems that can understand and reason about complex urban environments. Recent studies have built urban foundation models using supervised fine-tuning (SFT) of LLMs and MLLMs, yet these models exhibit persistent geospatial bias, producing regionally skewed predictions and limited generalization. To thi… ▽ More Rapid urbanization intensifies the demand for Urban General Intelligence (UGI), referring to AI systems that can understand and reason about complex urban environments. Recent studies have built urban foundation models using supervised fine-tuning (SFT) of LLMs and MLLMs, yet these models exhibit persistent geospatial bias, producing regionally skewed predictions and limited generalization. To this end, we propose Urban-R1, a reinforcement learning-based post-training framework that aligns MLLMs with the objectives of UGI. Urban-R1 adopts Group Relative Policy Optimization (GRPO) to optimize reasoning across geographic groups and employs urban region profiling as a proxy task to provide measurable rewards from multimodal urban data. Extensive experiments across diverse regions and tasks show that Urban-R1 effectively mitigates geo-bias and improves cross-region generalization, outperforming both SFT-trained and closed-source models. Our results highlight reinforcement learning alignment as a promising pathway toward equitable and trustworthy urban intelligence. △ Less

Submitted 18 October, 2025; originally announced October 2025.

Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation

Authors: Zixi Wang, Yushe Cao, Yubo Huang, Jinzhu Wei, Jingzehua Xu, Shuai Zhang, Xin Lai

Abstract: In this paper, we propose a new method called Self-Training with Dynamic Weighting (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the target domain. Traditional GDA methods mitigate domain shift through intermediate domains and self-training but often suffer from inefficient knowledge migratio… ▽ More In this paper, we propose a new method called Self-Training with Dynamic Weighting (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the target domain. Traditional GDA methods mitigate domain shift through intermediate domains and self-training but often suffer from inefficient knowledge migration or incomplete intermediate data. Our approach introduces a dynamic weighting mechanism that adaptively balances the loss contributions of the source and target domains during training. Specifically, we design an optimization framework governed by a time-varying hyperparameter $\varrho$ (progressing from 0 to 1), which controls the strength of domain-specific learning and ensures stable adaptation. The method leverages self-training to generate pseudo-labels and optimizes a weighted objective function for iterative model updates, maintaining robustness across intermediate domains. Experiments on rotated MNIST, color-shifted MNIST, portrait datasets, and the Cover Type dataset demonstrate that STDW outperforms existing baselines. Ablation studies further validate the critical role of $\varrho$'s dynamic scheduling in achieving progressive adaptation, confirming its effectiveness in reducing domain bias and improving generalization. This work provides both theoretical insights and a practical framework for robust gradual domain adaptation, with potential applications in dynamic real-world scenarios. The code is available at https://github.com/Dramwig/STDW. △ Less

Submitted 13 October, 2025; originally announced October 2025.

Comments: It had formerly appeared as arXiv:2501.19159v2 in error. Accepted by NIPS 25

OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wild

Authors: Hongyu Qu, Jianan Wei, Xiangbo Shu, Yazhou Yao, Wenguan Wang, Jinhui Tang

Abstract: Current 3D gaze estimation methods struggle to generalize across diverse data domains, primarily due to i) the scarcity of annotated datasets, and ii) the insufficient diversity of labeled data. In this work, we present OmniGaze, a semi-supervised framework for 3D gaze estimation, which utilizes large-scale unlabeled data collected from diverse and unconstrained real-world environments to mitigate… ▽ More Current 3D gaze estimation methods struggle to generalize across diverse data domains, primarily due to i) the scarcity of annotated datasets, and ii) the insufficient diversity of labeled data. In this work, we present OmniGaze, a semi-supervised framework for 3D gaze estimation, which utilizes large-scale unlabeled data collected from diverse and unconstrained real-world environments to mitigate domain bias and generalize gaze estimation in the wild. First, we build a diverse collection of unlabeled facial images, varying in facial appearances, background environments, illumination conditions, head poses, and eye occlusions. In order to leverage unlabeled data spanning a broader distribution, OmniGaze adopts a standard pseudo-labeling strategy and devises a reward model to assess the reliability of pseudo labels. Beyond pseudo labels as 3D direction vectors, the reward model also incorporates visual embeddings extracted by an off-the-shelf visual encoder and semantic cues from gaze perspective generated by prompting a Multimodal Large Language Model to compute confidence scores. Then, these scores are utilized to select high-quality pseudo labels and weight them for loss computation. Extensive experiments demonstrate that OmniGaze achieves state-of-the-art performance on five datasets under both in-domain and cross-domain settings. Furthermore, we also evaluate the efficacy of OmniGaze as a scalable data engine for gaze estimation, which exhibits robust zero-shot generalization on four unseen datasets. △ Less

Submitted 15 October, 2025; v1 submitted 15 October, 2025; originally announced October 2025.

Comments: Accepted to NeurIPS 2025; Project page: https://github.com/quhongyu/OmniGaze

Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey

Authors: Jiaqi Wei, Xiang Zhang, Yuejin Yang, Wenxuan Huang, Juntai Cao, Sheng Xu, Xiang Zhuang, Zhangyang Gao, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Chenyu You, Wanli Ouyang, Siqi Sun

Abstract: Deliberative tree search is a cornerstone of modern Large Language Model (LLM) research, driving the pivot from brute-force scaling toward algorithmic efficiency. This single paradigm unifies two critical frontiers: \textbf{Test-Time Scaling (TTS)}, which deploys on-demand computation to solve hard problems, and \textbf{Self-Improvement}, which uses search-generated data to durably enhance model p… ▽ More Deliberative tree search is a cornerstone of modern Large Language Model (LLM) research, driving the pivot from brute-force scaling toward algorithmic efficiency. This single paradigm unifies two critical frontiers: \textbf{Test-Time Scaling (TTS)}, which deploys on-demand computation to solve hard problems, and \textbf{Self-Improvement}, which uses search-generated data to durably enhance model parameters. However, this burgeoning field is fragmented and lacks a common formalism, particularly concerning the ambiguous role of the reward signal -- is it a transient heuristic or a durable learning target? This paper resolves this ambiguity by introducing a unified framework that deconstructs search algorithms into three core components: the \emph{Search Mechanism}, \emph{Reward Formulation}, and \emph{Transition Function}. We establish a formal distinction between transient \textbf{Search Guidance} for TTS and durable \textbf{Parametric Reward Modeling} for Self-Improvement. Building on this formalism, we introduce a component-centric taxonomy, synthesize the state-of-the-art, and chart a research roadmap toward more systematic progress in creating autonomous, self-improving agents. △ Less

Submitted 10 October, 2025; originally announced October 2025.

Harnessing Self-Supervised Deep Learning and Geostationary Remote Sensing for Advancing Wildfire and Associated Air Quality Monitoring: Improved Smoke and Fire Front Masking using GOES and TEMPO Radiance Data

Authors: Nicholas LaHaye, Thilanka Munashinge, Hugo Lee, Xiaohua Pan, Gonzalo Gonzalez Abad, Hazem Mahmoud, Jennifer Wei

Abstract: This work demonstrates the possibilities for improving wildfire and air quality management in the western United States by leveraging the unprecedented hourly data from NASA's TEMPO satellite mission and advances in self-supervised deep learning. Here we demonstrate the efficacy of deep learning for mapping the near real-time hourly spread of wildfire fronts and smoke plumes using an innovative se… ▽ More This work demonstrates the possibilities for improving wildfire and air quality management in the western United States by leveraging the unprecedented hourly data from NASA's TEMPO satellite mission and advances in self-supervised deep learning. Here we demonstrate the efficacy of deep learning for mapping the near real-time hourly spread of wildfire fronts and smoke plumes using an innovative self-supervised deep learning-system: successfully distinguishing smoke plumes from clouds using GOES-18 and TEMPO data, strong agreement across the smoke and fire masks generated from different sensing modalities as well as significant improvement over operational products for the same cases. △ Less

Submitted 10 October, 2025; originally announced October 2025.

Comments: https://2025.ieeeigarss.org/view_paper.php?PaperNum=6389&SessionID=1611