Showing 1–50 of 1,002 results for author: Ma, W

Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks

Authors: Xinhe Wang, Jin Huang, Xingjian Zhang, Tianhao Wang, Jiaqi W. Ma

Abstract: Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called ``fluid'' reasoning abilities. Despite their apparent simplicity for humans, these tasks remain challenging for frontier vision-language models (VLMs), a gap commonly attributed to deficiencies in ma… ▽ More Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called ``fluid'' reasoning abilities. Despite their apparent simplicity for humans, these tasks remain challenging for frontier vision-language models (VLMs), a gap commonly attributed to deficiencies in machine reasoning. We challenge this interpretation and hypothesize that the gap arises primarily from limitations in visual perception rather than from shortcomings in inductive reasoning. To verify this hypothesis, we introduce a two-stage experimental pipeline that explicitly separates perception and reasoning. In the perception stage, each image is independently converted into a natural-language description, while in the reasoning stage a model induces and applies rules using these descriptions. This design prevents leakage of cross-image inductive signals and isolates reasoning from perception bottlenecks. Across three ARC-style datasets, Mini-ARC, ACRE, and Bongard-LOGO, we show that the perception capability is the dominant factor underlying the observed performance gap by comparing the two-stage pipeline with against standard end-to-end one-stage evaluation. Manual inspection of reasoning traces in the VLM outputs further reveals that approximately 80 percent of model failures stem from perception errors. Together, these results demonstrate that ARC-style benchmarks conflate perceptual and reasoning challenges and that observed performance gaps may overstate deficiencies in machine reasoning. Our findings underscore the need for evaluation protocols that disentangle perception from reasoning when assessing progress in machine intelligence. △ Less

Submitted 24 December, 2025; originally announced December 2025.

Trajectory Planning for UAV-Based Smart Farming Using Imitation-Based Triple Deep Q-Learning

Authors: Wencan Mao, Quanxi Zhou, Tomas Couso Coddou, Manabu Tsukada, Yunling Liu, Yusheng Ji

Abstract: Unmanned aerial vehicles (UAVs) have emerged as a promising auxiliary platform for smart agriculture, capable of simultaneously performing weed detection, recognition, and data collection from wireless sensors. However, trajectory planning for UAV-based smart agriculture is challenging due to the high uncertainty of the environment, partial observations, and limited battery capacity of UAVs. To ad… ▽ More Unmanned aerial vehicles (UAVs) have emerged as a promising auxiliary platform for smart agriculture, capable of simultaneously performing weed detection, recognition, and data collection from wireless sensors. However, trajectory planning for UAV-based smart agriculture is challenging due to the high uncertainty of the environment, partial observations, and limited battery capacity of UAVs. To address these issues, we formulate the trajectory planning problem as a Markov decision process (MDP) and leverage multi-agent reinforcement learning (MARL) to solve it. Furthermore, we propose a novel imitation-based triple deep Q-network (ITDQN) algorithm, which employs an elite imitation mechanism to reduce exploration costs and utilizes a mediator Q-network over a double deep Q-network (DDQN) to accelerate and stabilize training and improve performance. Experimental results in both simulated and real-world environments demonstrate the effectiveness of our solution. Moreover, our proposed ITDQN outperforms DDQN by 4.43\% in weed recognition rate and 6.94\% in data collection rate. △ Less

Submitted 21 December, 2025; originally announced December 2025.

EIA-SEC: Improved Actor-Critic Framework for Multi-UAV Collaborative Control in Smart Agriculture

Authors: Quanxi Zhou, Wencan Mao, Yilei Liang, Manabu Tsukada, Yunling Liu, Jon Crowcroft

Abstract: The widespread application of wireless communication technology has promoted the development of smart agriculture, where unmanned aerial vehicles (UAVs) play a multifunctional role. We target a multi-UAV smart agriculture system where UAVs cooperatively perform data collection, image acquisition, and communication tasks. In this context, we model a Markov decision process to solve the multi-UAV tr… ▽ More The widespread application of wireless communication technology has promoted the development of smart agriculture, where unmanned aerial vehicles (UAVs) play a multifunctional role. We target a multi-UAV smart agriculture system where UAVs cooperatively perform data collection, image acquisition, and communication tasks. In this context, we model a Markov decision process to solve the multi-UAV trajectory planning problem. Moreover, we propose a novel Elite Imitation Actor-Shared Ensemble Critic (EIA-SEC) framework, where agents adaptively learn from the elite agent to reduce trial-and-error costs, and a shared ensemble critic collaborates with each agent's local critic to ensure unbiased objective value estimates and prevent overestimation. Experimental results demonstrate that EIA-SEC outperforms state-of-the-art baselines in terms of reward performance, training stability, and convergence speed. △ Less

Submitted 21 December, 2025; originally announced December 2025.

GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation

Authors: Rang Li, Lei Li, Shuhuai Ren, Hao Tian, Shuhao Gu, Shicheng Li, Zihao Yue, Yudong Wang, Wenhan Ma, Zhe Yang, Jingyuan Ma, Zhifang Sui, Fuli Luo

Abstract: Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language models (MLLMs) achieve impressive scores on existing benchmarks, a fundamental question remains: can MLLMs truly ground language in vision with human-like sophistication, or are they merely pattern-matching on simplified da… ▽ More Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language models (MLLMs) achieve impressive scores on existing benchmarks, a fundamental question remains: can MLLMs truly ground language in vision with human-like sophistication, or are they merely pattern-matching on simplified datasets? Current benchmarks fail to capture real-world complexity where humans effortlessly navigate ambiguous references and recognize when grounding is impossible. To rigorously assess MLLMs' true capabilities, we introduce GroundingME, a benchmark that systematically challenges models across four critical dimensions: (1) Discriminative, distinguishing highly similar objects, (2) Spatial, understanding complex relational descriptions, (3) Limited, handling occlusions or tiny objects, and (4) Rejection, recognizing ungroundable queries. Through careful curation combining automated generation with human verification, we create 1,005 challenging examples mirroring real-world complexity. Evaluating 25 state-of-the-art MLLMs reveals a profound capability gap: the best model achieves only 45.1% accuracy, while most score 0% on rejection tasks, reflexively hallucinating objects rather than acknowledging their absence, raising critical safety concerns for deployment. We explore two strategies for improvements: (1) test-time scaling selects optimal response by thinking trajectory to improve complex grounding by up to 2.9%, and (2) data-mixture training teaches models to recognize ungroundable queries, boosting rejection accuracy from 0% to 27.9%. GroundingME thus serves as both a diagnostic tool revealing current limitations in MLLMs and a roadmap toward human-level visual grounding. △ Less

Submitted 19 December, 2025; originally announced December 2025.

Mitty: Diffusion-based Human-to-Robot Video Generation

Authors: Yiren Song, Cheng Liu, Weijia Mao, Mike Zheng Shou

Abstract: Learning directly from human demonstration videos is a key milestone toward scalable and generalizable robot learning. Yet existing methods rely on intermediate representations such as keypoints or trajectories, introducing information loss and cumulative errors that harm temporal and visual consistency. We present Mitty, a Diffusion Transformer that enables video In-Context Learning for end-to-en… ▽ More Learning directly from human demonstration videos is a key milestone toward scalable and generalizable robot learning. Yet existing methods rely on intermediate representations such as keypoints or trajectories, introducing information loss and cumulative errors that harm temporal and visual consistency. We present Mitty, a Diffusion Transformer that enables video In-Context Learning for end-to-end Human2Robot video generation. Built on a pretrained video diffusion model, Mitty leverages strong visual-temporal priors to translate human demonstrations into robot-execution videos without action labels or intermediate abstractions. Demonstration videos are compressed into condition tokens and fused with robot denoising tokens through bidirectional attention during diffusion. To mitigate paired-data scarcity, we also develop an automatic synthesis pipeline that produces high-quality human-robot pairs from large egocentric datasets. Experiments on Human2Robot and EPIC-Kitchens show that Mitty delivers state-of-the-art results, strong generalization to unseen environments, and new insights for scalable robot learning from human observations. △ Less

Submitted 19 December, 2025; originally announced December 2025.

Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning

Authors: Qihao Liu, Luoxin Ye, Wufei Ma, Yu-Cheng Chou, Alan Yuille

Abstract: Large language models (LLMs) with explicit reasoning capabilities excel at mathematical reasoning yet still commit process errors, such as incorrect calculations, brittle logic, and superficially plausible but invalid steps. In this paper, we introduce Generative Adversarial Reasoner, an on-policy joint training framework designed to enhance reasoning by co-evolving an LLM reasoner and an LLM-base… ▽ More Large language models (LLMs) with explicit reasoning capabilities excel at mathematical reasoning yet still commit process errors, such as incorrect calculations, brittle logic, and superficially plausible but invalid steps. In this paper, we introduce Generative Adversarial Reasoner, an on-policy joint training framework designed to enhance reasoning by co-evolving an LLM reasoner and an LLM-based discriminator through adversarial reinforcement learning. A compute-efficient review schedule partitions each reasoning chain into logically complete slices of comparable length, and the discriminator evaluates each slice's soundness with concise, structured justifications. Learning couples complementary signals: the LLM reasoner is rewarded for logically consistent steps that yield correct answers, while the discriminator earns rewards for correctly detecting errors or distinguishing traces in the reasoning process. This produces dense, well-calibrated, on-policy step-level rewards that supplement sparse exact-match signals, improving credit assignment, increasing sample efficiency, and enhancing overall reasoning quality of LLMs. Across various mathematical benchmarks, the method delivers consistent gains over strong baselines with standard RL post-training. Specifically, on AIME24, we improve DeepSeek-R1-Distill-Qwen-7B from 54.0 to 61.3 (+7.3) and DeepSeek-R1-Distill-Llama-8B from 43.7 to 53.7 (+10.0). The modular discriminator also enables flexible reward shaping for objectives such as teacher distillation, preference alignment, and mathematical proof-based reasoning. △ Less

Submitted 18 December, 2025; originally announced December 2025.

PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies

Authors: Arhan Jain, Mingtong Zhang, Kanav Arora, William Chen, Marcel Torne, Muhammad Zubair Irshad, Sergey Zakharov, Yue Wang, Sergey Levine, Chelsea Finn, Wei-Chiu Ma, Dhruv Shah, Abhishek Gupta, Karl Pertsch

Abstract: A significant challenge for robot learning research is our ability to accurately measure and compare the performance of robot policies. Benchmarking in robotics is historically challenging due to the stochasticity, reproducibility, and time-consuming nature of real-world rollouts. This challenge is exacerbated for recent generalist policies, which has to be evaluated across a wide variety of scene… ▽ More A significant challenge for robot learning research is our ability to accurately measure and compare the performance of robot policies. Benchmarking in robotics is historically challenging due to the stochasticity, reproducibility, and time-consuming nature of real-world rollouts. This challenge is exacerbated for recent generalist policies, which has to be evaluated across a wide variety of scenes and tasks. Evaluation in simulation offers a scalable complement to real world evaluations, but the visual and physical domain gap between existing simulation benchmarks and the real world has made them an unreliable signal for policy improvement. Furthermore, building realistic and diverse simulated environments has traditionally required significant human effort and expertise. To bridge the gap, we introduce Policy Evaluation and Environment Reconstruction in Simulation (PolaRiS), a scalable real-to-sim framework for high-fidelity simulated robot evaluation. PolaRiS utilizes neural reconstruction methods to turn short video scans of real-world scenes into interactive simulation environments. Additionally, we develop a simple simulation data co-training recipe that bridges remaining real-to-sim gaps and enables zero-shot evaluation in unseen simulation environments. Through extensive paired evaluations between simulation and the real world, we demonstrate that PolaRiS evaluations provide a much stronger correlation to real world generalist policy performance than existing simulated benchmarks. Its simplicity also enables rapid creation of diverse simulated environments. As such, this work takes a step towards distributed and democratized evaluation for the next generation of robotic foundation models. △ Less

Submitted 18 December, 2025; originally announced December 2025.

Comments: Website: https://polaris-evals.github.io/

FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments

Authors: Quanxi Zhou, Wencan Mao, Manabu Tsukada, John C. S. Lui, Yusheng Ji

Abstract: Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across tasks and scenarios. Motivated by this limitation, we propose a generalized algorithm, Feature Model-Based Enhanced Actor-Critic (FM-EAC), that integrates planning… ▽ More Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across tasks and scenarios. Motivated by this limitation, we propose a generalized algorithm, Feature Model-Based Enhanced Actor-Critic (FM-EAC), that integrates planning, acting, and learning for multi-task control in dynamic environments. FM-EAC combines the strengths of MBRL and MFRL and improves generalizability through the use of novel feature-based models and an enhanced actor-critic framework. Simulations in both urban and agricultural applications demonstrate that FM-EAC consistently outperforms many state-of-the-art MBRL and MFRL methods. More importantly, different sub-networks can be customized within FM-EAC according to user-specific requirements. △ Less

Submitted 17 December, 2025; originally announced December 2025.

Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination

Authors: Zhuoxiao Li, Wenzong Ma, Taoyu Wu, Jinjing Zhu, Zhenchao Q, Shuai Zhang, Jing Ou, Yinrui Ren, Weiqing Qi, Guobin Shen, Hui Xiong, Wufan Zhao

Abstract: Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric ina… ▽ More Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric inaccuracies, and inconsistent appearance. Due to the lack of UAV datasets that systematically capture the same areas under varying illumination conditions, this challenge remains largely underexplored. To fill this gap, we introduceSkyLume, a large-scale, real-world UAV dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling: (1) We collect data from 10 urban regions data comprising more than 100k high resolution UAV images (four oblique views and nadir), where each region is captured at three periods of the day to systematically isolate illumination changes. (2) To support precise evaluation of geometry and appearance, we provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination. (3) For the inverse rendering task, we introduce the Temporal Consistency Coefficient (TCC), a metric that measuress cross-time albedo stability and directly evaluates the robustness of the disentanglement of light and material. We aim for this resource to serve as a foundation that advances research and real-world evaluation in large-scale inverse rendering, geometry reconstruction, and novel view synthesis. △ Less

Submitted 16 December, 2025; originally announced December 2025.

gpu_ext: Extensible OS Policies for GPUs via eBPF

Authors: Yusheng Zheng, Tong Yu, Yiwei Yang, Minghui Jiang, Xiangyu Gao, Jianchang Su, Yanpeng Hu, Wenan Mao, Wei Zhang, Dan Williams, Andi Quinn

Abstract: Performance in modern GPU-centric systems increasingly depends on resource management policies, including memory placement, scheduling, and observability. However, uniform policies typically yield suboptimal performance across diverse workloads. Existing approaches present a tradeoff: user-space runtimes provide programmability and flexibility but lack cross-tenant visibility and fine-grained cont… ▽ More Performance in modern GPU-centric systems increasingly depends on resource management policies, including memory placement, scheduling, and observability. However, uniform policies typically yield suboptimal performance across diverse workloads. Existing approaches present a tradeoff: user-space runtimes provide programmability and flexibility but lack cross-tenant visibility and fine-grained control of hardware resources; meanwhile, modifications to the OS kernel introduce significant complexity and safety risks. To address this, we argue that the GPU driver and device layer should provide an extensible OS interface for policy enforcement. While the emerging eBPF technology shows potential, directly applying existing host-side eBPF is insufficient because they lack visibility and control into critical device-side events, and directly embedding policy code into GPU kernels could compromise safety and efficiency. We propose gpu_ext, an eBPF-based runtime that treats the GPU driver and device as a programmable OS subsystem. gpu_ext extends GPU drivers by exposing safe programmable hooks and introduces a device-side eBPF runtime capable of executing verified policy logic within GPU kernels, enabling coherent and transparent policies. Evaluation across realistic workloads including inference, training, and vector search demonstrates that gpu_ext improves throughput by up to 4.8x and reduces tail latency by up to 2x, incurring low overhead, without modifying or restarting applications △ Less

Submitted 20 December, 2025; v1 submitted 14 December, 2025; originally announced December 2025.

CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop

Authors: Weijian Ma, Shizhao Sun, Ruiyu Wang, Jiang Bian

Abstract: A Computer-Aided Design (CAD) model encodes an object in two coupled forms: a parametric construction sequence and its resulting visible geometric shape. During iterative design, adjustments to the geometric shape inevitably require synchronized edits to the underlying parametric sequence, called geometry-driven parametric CAD editing. The task calls for 1) preserving the original sequence's struc… ▽ More A Computer-Aided Design (CAD) model encodes an object in two coupled forms: a parametric construction sequence and its resulting visible geometric shape. During iterative design, adjustments to the geometric shape inevitably require synchronized edits to the underlying parametric sequence, called geometry-driven parametric CAD editing. The task calls for 1) preserving the original sequence's structure, 2) ensuring each edit's semantic validity, and 3) maintaining high shape fidelity to the target shape, all under scarce editing data triplets. We present CADMorph, an iterative plan-generate-verify framework that orchestrates pretrained domain-specific foundation models during inference: a parameter-to-shape (P2S) latent diffusion model and a masked-parameter-prediction (MPP) model. In the planning stage, cross-attention maps from the P2S model pinpoint the segments that need modification and offer editing masks. The MPP model then infills these masks with semantically valid edits in the generation stage. During verification, the P2S model embeds each candidate sequence in shape-latent space, measures its distance to the target shape, and selects the closest one. The three stages leverage the inherent geometric consciousness and design knowledge in pretrained priors, and thus tackle structure preservation, semantic validity, and shape fidelity respectively. Besides, both P2S and MPP models are trained without triplet data, bypassing the data-scarcity bottleneck. CADMorph surpasses GPT-4o and specialized CAD baselines, and supports downstream applications such as iterative editing and reverse-engineering enhancement. △ Less

Submitted 12 December, 2025; originally announced December 2025.

Comments: NeurIPS 2025

COMPARE: Clinical Optimization with Modular Planning and Assessment via RAG-Enhanced AI-OCT: Superior Decision Support for Percutaneous Coronary Intervention Compared to ChatGPT-5 and Junior Operators

Authors: Wei Fang, Chiyao Wang, Wenshuai Ma, Hui Liu, Jianqiang Hu, Xiaona Niu, Yi Chu, Mingming Zhang, Jingxiao Yang, Dongwei Zhang, Zelin Li, Pengyun Liu, Jiawei Zheng, Pengke Zhang, Chaoshi Qin, Wangang Guo, Bin Wang, Yugang Xue, Wei Zhang, Zikuan Wang, Rui Zhu, Yihui Cao, Quanmao Lu, Rui Meng, Yan Li

Abstract: Background: While intravascular imaging, particularly optical coherence tomography (OCT), improves percutaneous coronary intervention (PCI) outcomes, its interpretation is operator-dependent. General-purpose artificial intelligence (AI) shows promise but lacks domain-specific reliability. We evaluated the performance of CA-GPT, a novel large model deployed on an AI-OCT system, against that of the… ▽ More Background: While intravascular imaging, particularly optical coherence tomography (OCT), improves percutaneous coronary intervention (PCI) outcomes, its interpretation is operator-dependent. General-purpose artificial intelligence (AI) shows promise but lacks domain-specific reliability. We evaluated the performance of CA-GPT, a novel large model deployed on an AI-OCT system, against that of the general-purpose ChatGPT-5 and junior physicians for OCT-guided PCI planning and assessment. Methods: In this single-center analysis of 96 patients who underwent OCT-guided PCI, the procedural decisions generated by the CA-GPT, ChatGPT-5, and junior physicians were compared with an expert-derived procedural record. Agreement was assessed using ten pre-specified metrics across pre-PCI and post-PCI phases. Results: For pre-PCI planning, CA-GPT demonstrated significantly higher median agreement scores (5[IQR 3.75-5]) compared to both ChatGPT-5 (3[2-4], P<0.001) and junior physicians (4[3-4], P<0.001). CA-GPT significantly outperformed ChatGPT-5 across all individual pre-PCI metrics and showed superior performance to junior physicians in stent diameter (90.3% vs. 72.2%, P<0.05) and length selection (80.6% vs. 52.8%, P<0.01). In post-PCI assessment, CA-GPT maintained excellent overall agreement (5[4.75-5]), significantly higher than both ChatGPT-5 (4[4-5], P<0.001) and junior physicians (5[4-5], P<0.05). Subgroup analysis confirmed CA-GPT's robust performance advantage in complex scenarios. Conclusion: The CA-GPT-based AI-OCT system achieved superior decision-making agreement versus a general-purpose large language model and junior physicians across both PCI planning and assessment phases. This approach provides a standardized and reliable method for intravascular imaging interpretation, demonstrating significant potential to augment operator expertise and optimize OCT-guided PCI. △ Less

Submitted 11 December, 2025; originally announced December 2025.

Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning

Authors: Yudong Wang, Zhe Yang, Wenhan Ma, Zhifang Sui, Liang Zhao

Abstract: While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical trade-off between capability and reliability. This work confronts this challenge by introducing a targeted RL framework designed to mitigate both intrinsic and extrinsic hallucinations across short and long-form question a… ▽ More While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical trade-off between capability and reliability. This work confronts this challenge by introducing a targeted RL framework designed to mitigate both intrinsic and extrinsic hallucinations across short and long-form question answering. We address extrinsic hallucinations (flawed internal knowledge) by creating a novel training set from open-ended conversions of TriviaQA. Concurrently, we tackle intrinsic hallucinations (unfaithfulness to context) by leveraging long-form texts from FineWeb in a fact-grounding reward scheme. To further bolster reliability, our framework explicitly rewards the model for refusing to answer unanswerable questions, thereby cultivating crucial cautiousness. Extensive experiments demonstrate that our methodology yields significant performance gains across a diverse suite of benchmarks, substantially reducing both hallucination types. Ultimately, this research contributes a practical framework for resolving the critical tension between advanced reasoning and factual trustworthiness, paving the way for more capable and reliable large language models. △ Less

Submitted 19 November, 2025; originally announced December 2025.

See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations

Authors: Guangyan Chen, Meiling Wang, Qi Shao, Zichen Zhou, Weixin Mao, Te Cui, Minzhao Zhu, Yinan Deng, Luojie Yang, Zhanqi Zhang, Yi Yang, Hua Chen, Yufeng Yue

Abstract: Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing approaches still exhibit limited generalization to tasks beyond their training distributions. In contrast, humans possess remarkable proficiency in acquiring nov… ▽ More Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing approaches still exhibit limited generalization to tasks beyond their training distributions. In contrast, humans possess remarkable proficiency in acquiring novel skills by simply observing others performing them once. Inspired by this capability, we propose ViVLA, a generalist robotic manipulation policy that achieves efficient task learning from a single expert demonstration video at test time. Our approach jointly processes an expert demonstration video alongside the robot's visual observations to predict both the demonstrated action sequences and subsequent robot actions, effectively distilling fine-grained manipulation knowledge from expert behavior and transferring it seamlessly to the agent. To enhance the performance of ViVLA, we develop a scalable expert-agent pair data generation pipeline capable of synthesizing paired trajectories from easily accessible human videos, further augmented by curated pairs from publicly available datasets. This pipeline produces a total of 892,911 expert-agent samples for training ViVLA. Experimental results demonstrate that our ViVLA is able to acquire novel manipulation skills from only a single expert demonstration video at test time. Our approach achieves over 30% improvement on unseen LIBERO tasks and maintains above 35% gains with cross-embodiment videos. Real-world experiments demonstrate effective learning from human videos, yielding more than 38% improvement on unseen tasks. △ Less

Submitted 8 December, 2025; originally announced December 2025.

VAT: Vision Action Transformer by Unlocking Full Representation of ViT

Authors: Wenhao Li, Chengwei Ma, Weixin Mao

Abstract: In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue this provides an insufficient representation and propose the Vision Action Transformer (VAT), a novel architecture that is extended from ViT and unlocks the full feature hierarchy of ViT. VAT processes specialized action… ▽ More In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue this provides an insufficient representation and propose the Vision Action Transformer (VAT), a novel architecture that is extended from ViT and unlocks the full feature hierarchy of ViT. VAT processes specialized action tokens with visual features across all transformer layers, enabling a deep and progressive fusion of perception and action generation. On a suite of simulated manipulation tasks, VAT achieves a 98.15\% average success rate across four LIBERO benchmarks, establishing a new state-of-the-art by outperforming prior methods like OpenVLA-OFT. Our work presents not only a powerful model for imitation learning but also demonstrates the critical importance of leveraging the complete ''representation trajectory'' of vision models to advance robotic policy. The GitHub URL for the project code is https://github.com/sellerbubble/VAT. △ Less

Submitted 3 December, 2025; originally announced December 2025.

Learning High-Fidelity Cloth Animation via Skinning-Free Image Transfer

Authors: Rong Wang, Wei Mao, Changsheng Lu, Hongdong Li

Abstract: We present a novel method for generating 3D garment deformations from given body poses, which is key to a wide range of applications, including virtual try-on and extended reality. To simplify the cloth dynamics, existing methods mostly rely on linear blend skinning to obtain low-frequency posed garment shape and only regress high-frequency wrinkles. However, due to the lack of explicit skinning s… ▽ More We present a novel method for generating 3D garment deformations from given body poses, which is key to a wide range of applications, including virtual try-on and extended reality. To simplify the cloth dynamics, existing methods mostly rely on linear blend skinning to obtain low-frequency posed garment shape and only regress high-frequency wrinkles. However, due to the lack of explicit skinning supervision, such skinning-based approach often produces misaligned shapes when posing the garment, consequently corrupts the high-frequency signals and fails to recover high-fidelity wrinkles. To tackle this issue, we propose a skinning-free approach by independently estimating posed (i) vertex position for low-frequency posed garment shape, and (ii) vertex normal for high-frequency local wrinkle details. In this way, each frequency modality can be effectively decoupled and directly supervised by the geometry of the deformed garment. To further improve the visual quality of animation, we propose to encode both vertex attributes as rendered texture images, so that 3D garment deformation can be equivalently achieved via 2D image transfer. This enables us to leverage powerful pretrained image models to recover fine-grained visual details in wrinkles, while maintaining superior scalability for garments of diverse topologies without relying on manual UV partition. Finally, we propose a multimodal fusion to incorporate constraints from both frequency modalities and robustly recover deformed 3D garments from transferred images. Extensive experiments show that our method significantly improves animation quality on various garment types and recovers finer wrinkles than state-of-the-art methods. △ Less

Submitted 5 December, 2025; originally announced December 2025.

Comments: Accepted to 3DV 2026

ShadowDraw: From Any Object to Shadow-Drawing Compositional Art

Authors: Rundong Luo, Noah Snavely, Wei-Chiu Ma

Abstract: We introduce ShadowDraw, a framework that transforms ordinary 3D objects into shadow-drawing compositional art. Given a 3D object, our system predicts scene parameters, including object pose and lighting, together with a partial line drawing, such that the cast shadow completes the drawing into a recognizable image. To this end, we optimize scene configurations to reveal meaningful shadows, employ… ▽ More We introduce ShadowDraw, a framework that transforms ordinary 3D objects into shadow-drawing compositional art. Given a 3D object, our system predicts scene parameters, including object pose and lighting, together with a partial line drawing, such that the cast shadow completes the drawing into a recognizable image. To this end, we optimize scene configurations to reveal meaningful shadows, employ shadow strokes to guide line drawing generation, and adopt automatic evaluation to enforce shadow-drawing coherence and visual quality. Experiments show that ShadowDraw produces compelling results across diverse inputs, from real-world scans and curated datasets to generative assets, and naturally extends to multi-object scenes, animations, and physical deployments. Our work provides a practical pipeline for creating shadow-drawing art and broadens the design space of computational visual art, bridging the gap between algorithmic design and artistic storytelling. Check out our project page https://red-fairy.github.io/ShadowDraw/ for more results and an end-to-end real-world demonstration of our pipeline! △ Less

Submitted 4 December, 2025; originally announced December 2025.

Comments: Project page: https://red-fairy.github.io/ShadowDraw/

E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving

Authors: Yihong Tang, Haicheng Liao, Tong Nie, Junlin He, Ao Qu, Kehua Chen, Wei Ma, Zhenning Li, Lijun Sun, Chengzhong Xu

Abstract: End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) autonomous driving, where an autonomous vehicle (AV) must interpret free-form natural-language commands, infer the emotion, and plan a physically feas… ▽ More End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) autonomous driving, where an autonomous vehicle (AV) must interpret free-form natural-language commands, infer the emotion, and plan a physically feasible trajectory. We propose E3AD, an emotion-aware VLA framework that augments semantic understanding with two cognitively inspired components: a continuous Valenc-Arousal-Dominance (VAD) emotion model that captures tone and urgency from language, and a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition. A consistency-oriented training scheme, combining modality pretraining with preference-based alignment, further enforces coherence between emotional intent and driving actions. Across real-world datasets, E3AD improves visual grounding and waypoint planning and achieves state-of-the-art (SOTA) VAD correlation for emotion estimation. These results show that injecting emotion into VLA-style driving yields more human-aligned grounding, planning, and human-centric feedback. △ Less

Submitted 4 December, 2025; originally announced December 2025.

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

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Authors: Weijia Mao, Hao Chen, Zhenheng Yang, Mike Zheng Shou

Abstract: A reliable reward function is essential for reinforcement learning (RL) in image generation. Most current RL approaches depend on pre-trained preference models that output scalar rewards to approximate human preferences. However, these rewards often fail to capture human perception and are vulnerable to reward hacking, where higher scores do not correspond to better images. To address this, we int… ▽ More A reliable reward function is essential for reinforcement learning (RL) in image generation. Most current RL approaches depend on pre-trained preference models that output scalar rewards to approximate human preferences. However, these rewards often fail to capture human perception and are vulnerable to reward hacking, where higher scores do not correspond to better images. To address this, we introduce Adv-GRPO, an RL framework with an adversarial reward that iteratively updates both the reward model and the generator. The reward model is supervised using reference images as positive samples and can largely avoid being hacked. Unlike KL regularization that constrains parameter updates, our learned reward directly guides the generator through its visual outputs, leading to higher-quality images. Moreover, while optimizing existing reward functions can alleviate reward hacking, their inherent biases remain. For instance, PickScore may degrade image quality, whereas OCR-based rewards often reduce aesthetic fidelity. To address this, we take the image itself as a reward, using reference images and vision foundation models (e.g., DINO) to provide rich visual rewards. These dense visual signals, instead of a single scalar, lead to consistent gains across image quality, aesthetics, and task-specific metrics. Finally, we show that combining reference samples with foundation-model rewards enables distribution transfer and flexible style customization. In human evaluation, our method outperforms Flow-GRPO and SD3, achieving 70.0% and 72.4% win rates in image quality and aesthetics, respectively. Code and models have been released. △ Less

Submitted 25 November, 2025; originally announced November 2025.

Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models

Authors: Jonathan Lee, Xingrui Wang, Jiawei Peng, Luoxin Ye, Zehan Zheng, Tiezheng Zhang, Tao Wang, Wufei Ma, Siyi Chen, Yu-Cheng Chou, Prakhar Kaushik, Alan Yuille

Abstract: We propose Perceptual Taxonomy, a structured process of scene understanding that first recognizes objects and their spatial configurations, then infers task-relevant properties such as material, affordance, function, and physical attributes to support goal-directed reasoning. While this form of reasoning is fundamental to human cognition, current vision-language benchmarks lack comprehensive evalu… ▽ More We propose Perceptual Taxonomy, a structured process of scene understanding that first recognizes objects and their spatial configurations, then infers task-relevant properties such as material, affordance, function, and physical attributes to support goal-directed reasoning. While this form of reasoning is fundamental to human cognition, current vision-language benchmarks lack comprehensive evaluation of this ability and instead focus on surface-level recognition or image-text alignment. To address this gap, we introduce Perceptual Taxonomy, a benchmark for physically grounded visual reasoning. We annotate 3173 objects with four property families covering 84 fine-grained attributes. Using these annotations, we construct a multiple-choice question benchmark with 5802 images across both synthetic and real domains. The benchmark contains 28033 template-based questions spanning four types (object description, spatial reasoning, property matching, and taxonomy reasoning), along with 50 expert-crafted questions designed to evaluate models across the full spectrum of perceptual taxonomy reasoning. Experimental results show that leading vision-language models perform well on recognition tasks but degrade by 10 to 20 percent on property-driven questions, especially those requiring multi-step reasoning over structured attributes. These findings highlight a persistent gap in structured visual understanding and the limitations of current models that rely heavily on pattern matching. We also show that providing in-context reasoning examples from simulated scenes improves performance on real-world and expert-curated questions, demonstrating the effectiveness of perceptual-taxonomy-guided prompting. △ Less

Submitted 24 November, 2025; originally announced November 2025.

RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data

Authors: Wenchao Ma, Dario Kneubuehler, Maurice Chu, Ian Sachs, Haomiao Jiang, Sharon Xiaolei Huang

Abstract: In this paper, we present RigAnyFace (RAF), a scalable neural auto-rigging framework for facial meshes of diverse topologies, including those with multiple disconnected components. RAF deforms a static neutral facial mesh into industry-standard FACS poses to form an expressive blendshape rig. Deformations are predicted by a triangulation-agnostic surface learning network augmented with our tailore… ▽ More In this paper, we present RigAnyFace (RAF), a scalable neural auto-rigging framework for facial meshes of diverse topologies, including those with multiple disconnected components. RAF deforms a static neutral facial mesh into industry-standard FACS poses to form an expressive blendshape rig. Deformations are predicted by a triangulation-agnostic surface learning network augmented with our tailored architecture design to condition on FACS parameters and efficiently process disconnected components. For training, we curated a dataset of facial meshes, with a subset meticulously rigged by professional artists to serve as accurate 3D ground truth for deformation supervision. Due to the high cost of manual rigging, this subset is limited in size, constraining the generalization ability of models trained exclusively on it. To address this, we design a 2D supervision strategy for unlabeled neutral meshes without rigs. This strategy increases data diversity and allows for scaled training, thereby enhancing the generalization ability of models trained on this augmented data. Extensive experiments demonstrate that RAF is able to rig meshes of diverse topologies on not only our artist-crafted assets but also in-the-wild samples, outperforming previous works in accuracy and generalizability. Moreover, our method advances beyond prior work by supporting multiple disconnected components, such as eyeballs, for more detailed expression animation. Project page: https://wenchao-m.github.io/RigAnyFace.github.io △ Less

Submitted 23 November, 2025; originally announced November 2025.

Comments: Accepted by NeurIPS 2025

TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posing

Authors: Eddie Pokming Sheung, Qihao Liu, Wufei Ma, Prakhar Kaushik, Jianwen Xie, Alan Yuille

Abstract: With the increasing demand for 3D animation, generating high-fidelity, controllable 4D avatars from textual descriptions remains a significant challenge. Despite notable efforts in 4D generative modeling, existing methods exhibit fundamental limitations that impede their broader applicability, including temporal and geometric inconsistencies, perceptual artifacts, motion irregularities, high compu… ▽ More With the increasing demand for 3D animation, generating high-fidelity, controllable 4D avatars from textual descriptions remains a significant challenge. Despite notable efforts in 4D generative modeling, existing methods exhibit fundamental limitations that impede their broader applicability, including temporal and geometric inconsistencies, perceptual artifacts, motion irregularities, high computational costs, and limited control over dynamics. To address these challenges, we propose TriDiff-4D, a novel 4D generative pipeline that employs diffusion-based triplane re-posing to produce high-quality, temporally coherent 4D avatars. Our model adopts an auto-regressive strategy to generate 4D sequences of arbitrary length, synthesizing each 3D frame with a single diffusion process. By explicitly learning 3D structure and motion priors from large-scale 3D and motion datasets, TriDiff-4D enables skeleton-driven 4D generation that excels in temporal consistency, motion accuracy, computational efficiency, and visual fidelity. Specifically, TriDiff-4D first generates a canonical 3D avatar and a corresponding motion sequence from a text prompt, then uses a second diffusion model to animate the avatar according to the motion sequence, supporting arbitrarily long 4D generation. Experimental results demonstrate that TriDiff-4D significantly outperforms existing methods, reducing generation time from hours to seconds by eliminating the optimization process, while substantially improving the generation of complex motions with high-fidelity appearance and accurate 3D geometry. △ Less

Submitted 20 November, 2025; originally announced November 2025.

Comments: 8 pages, 10 figures, Under review at a conference

LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Driving

Authors: Pei Liu, Songtao Wang, Lang Zhang, Xingyue Peng, Yuandong Lyu, Jiaxin Deng, Songxin Lu, Weiliang Ma, Xueyang Zhang, Yifei Zhan, XianPeng Lang, Jun Ma

Abstract: Synthesizing high-fidelity and controllable 4D LiDAR data is crucial for creating scalable simulation environments for autonomous driving. This task is inherently challenging due to the sensor's unique spherical geometry, the temporal sparsity of point clouds, and the complexity of dynamic scenes. To address these challenges, we present LiSTAR, a novel generative world model that operates directly… ▽ More Synthesizing high-fidelity and controllable 4D LiDAR data is crucial for creating scalable simulation environments for autonomous driving. This task is inherently challenging due to the sensor's unique spherical geometry, the temporal sparsity of point clouds, and the complexity of dynamic scenes. To address these challenges, we present LiSTAR, a novel generative world model that operates directly on the sensor's native geometry. LiSTAR introduces a Hybrid-Cylindrical-Spherical (HCS) representation to preserve data fidelity by mitigating quantization artifacts common in Cartesian grids. To capture complex dynamics from sparse temporal data, it utilizes a Spatio-Temporal Attention with Ray-Centric Transformer (START) that explicitly models feature evolution along individual sensor rays for robust temporal coherence. Furthermore, for controllable synthesis, we propose a novel 4D point cloud-aligned voxel layout for conditioning and a corresponding discrete Masked Generative START (MaskSTART) framework, which learns a compact, tokenized representation of the scene, enabling efficient, high-resolution, and layout-guided compositional generation. Comprehensive experiments validate LiSTAR's state-of-the-art performance across 4D LiDAR reconstruction, prediction, and conditional generation, with substantial quantitative gains: reducing generation MMD by a massive 76%, improving reconstruction IoU by 32%, and lowering prediction L1 Med by 50%. This level of performance provides a powerful new foundation for creating realistic and controllable autonomous systems simulations. Project link: https://ocean-luna.github.io/LiSTAR.gitub.io. △ Less

Submitted 20 November, 2025; originally announced November 2025.

IBGS: Image-Based Gaussian Splatting

Authors: Hoang Chuong Nguyen, Wei Mao, Jose M. Alvarez, Miaomiao Liu

Abstract: 3D Gaussian Splatting (3DGS) has recently emerged as a fast, high-quality method for novel view synthesis (NVS). However, its use of low-degree spherical harmonics limits its ability to capture spatially varying color and view-dependent effects such as specular highlights. Existing works augment Gaussians with either a global texture map, which struggles with complex scenes, or per-Gaussian textur… ▽ More 3D Gaussian Splatting (3DGS) has recently emerged as a fast, high-quality method for novel view synthesis (NVS). However, its use of low-degree spherical harmonics limits its ability to capture spatially varying color and view-dependent effects such as specular highlights. Existing works augment Gaussians with either a global texture map, which struggles with complex scenes, or per-Gaussian texture maps, which introduces high storage overhead. We propose Image-Based Gaussian Splatting, an efficient alternative that leverages high-resolution source images for fine details and view-specific color modeling. Specifically, we model each pixel color as a combination of a base color from standard 3DGS rendering and a learned residual inferred from neighboring training images. This promotes accurate surface alignment and enables rendering images of high-frequency details and accurate view-dependent effects. Experiments on standard NVS benchmarks show that our method significantly outperforms prior Gaussian Splatting approaches in rendering quality, without increasing the storage footprint. △ Less

Submitted 18 November, 2025; originally announced November 2025.

Comments: Accepted to NeurIPS 2025

Don't Miss the Forest for the Trees: In-Depth Confidence Estimation for LLMs via Reasoning over the Answer Space

Authors: Ante Wang, Weizhi Ma, Yang Liu

Abstract: Knowing the reliability of a model's response is essential in application. With the strong generation capabilities of LLMs, research has focused on generating verbalized confidence. This is further enhanced by combining chain-of-thought reasoning, which provides logical and transparent estimation. However, how reasoning strategies affect the estimated confidence is still under-explored. In this wo… ▽ More Knowing the reliability of a model's response is essential in application. With the strong generation capabilities of LLMs, research has focused on generating verbalized confidence. This is further enhanced by combining chain-of-thought reasoning, which provides logical and transparent estimation. However, how reasoning strategies affect the estimated confidence is still under-explored. In this work, we demonstrate that predicting a verbalized probability distribution can effectively encourage in-depth reasoning for confidence estimation. Intuitively, it requires an LLM to consider all candidates within the answer space instead of basing on a single guess, and to carefully assign confidence scores to meet the requirements of a distribution. This method shows an advantage across different models and various tasks, regardless of whether the answer space is known. Its advantage is maintained even after reinforcement learning, and further analysis shows its reasoning patterns are aligned with human expectations. △ Less

Submitted 18 November, 2025; originally announced November 2025.

From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing

Authors: Ling Wang, Yunfan Lu, Wenzong Ma, Huizai Yao, Pengteng Li, Hui Xiong

Abstract: Clear imaging under hazy conditions is a critical task. Prior-based and neural methods have improved results. However, they operate on RGB frames, which suffer from limited dynamic range. Therefore, dehazing remains ill-posed and can erase structure and illumination details. To address this, we use event cameras for dehazing for the \textbf{first time}. Event cameras offer much higher HDR (… ▽ More Clear imaging under hazy conditions is a critical task. Prior-based and neural methods have improved results. However, they operate on RGB frames, which suffer from limited dynamic range. Therefore, dehazing remains ill-posed and can erase structure and illumination details. To address this, we use event cameras for dehazing for the \textbf{first time}. Event cameras offer much higher HDR ($120 dBvs.60 dB$) and microsecond latency, therefore they suit hazy scenes. In practice, transferring HDR cues from events to frames is hard because real paired data are scarce. To tackle this, we propose an event-guided diffusion model that utilizes the strong generative priors of diffusion models to reconstruct clear images from hazy inputs by effectively transferring HDR information from events. Specifically, we design an event-guided module that maps sparse HDR event features, \textit{e.g.,} edges, corners, into the diffusion latent space. This clear conditioning provides precise structural guidance during generation, improves visual realism, and reduces semantic drift. For real-world evaluation, we collect a drone dataset in heavy haze (AQI = 341) with synchronized RGB and event sensors. Experiments on two benchmarks and our dataset achieve state-of-the-art results. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Comments: 11 pages, 8 figures. Completed in April 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

SITA: A Framework for Structure-to-Instance Theorem Autoformalization

Authors: Chenyi Li, Wanli Ma, Zichen Wang, Zaiwen Wen

Abstract: While large language models (LLMs) have shown progress in mathematical reasoning, they still face challenges in formalizing theorems that arise from instantiating abstract structures in concrete settings. With the goal of auto-formalizing mathematical results at the research level, we develop a framework for structure-to-instance theorem autoformalization (SITA), which systematically bridges the g… ▽ More While large language models (LLMs) have shown progress in mathematical reasoning, they still face challenges in formalizing theorems that arise from instantiating abstract structures in concrete settings. With the goal of auto-formalizing mathematical results at the research level, we develop a framework for structure-to-instance theorem autoformalization (SITA), which systematically bridges the gap between abstract mathematical theories and their concrete applications in Lean proof assistant. Formalized abstract structures are treated as modular templates that contain definitions, assumptions, operations, and theorems. These templates serve as reusable guides for the formalization of concrete instances. Given a specific instantiation, we generate corresponding Lean definitions and instance declarations, integrate them using Lean's typeclass mechanism, and construct verified theorems by checking structural assumptions. We incorporate LLM-based generation with feedback-guided refinement to ensure both automation and formal correctness. Experiments on a dataset of optimization problems demonstrate that SITA effectively formalizes diverse instances grounded in abstract structures. △ Less

Submitted 13 November, 2025; originally announced November 2025.

LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning

Authors: Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin

Abstract: Joint multilingual instruction tuning is a widely adopted approach to improve the multilingual instruction-following ability and downstream performance of large language models (LLMs), but the resulting multilingual capability remains highly sensitive to the composition and selection of the training data. Existing selection methods, often based on features like text quality, diversity, or task rel… ▽ More Joint multilingual instruction tuning is a widely adopted approach to improve the multilingual instruction-following ability and downstream performance of large language models (LLMs), but the resulting multilingual capability remains highly sensitive to the composition and selection of the training data. Existing selection methods, often based on features like text quality, diversity, or task relevance, typically overlook the intrinsic linguistic structure of multilingual data. In this paper, we propose LangGPS, a lightweight two-stage pre-selection framework guided by language separability which quantifies how well samples in different languages can be distinguished in the model's representation space. LangGPS first filters training data based on separability scores and then refines the subset using existing selection methods. Extensive experiments across six benchmarks and 22 languages demonstrate that applying LangGPS on top of existing selection methods improves their effectiveness and generalizability in multilingual training, especially for understanding tasks and low-resource languages. Further analysis reveals that highly separable samples facilitate the formation of clearer language boundaries and support faster adaptation, while low-separability samples tend to function as bridges for cross-lingual alignment. Besides, we also find that language separability can serve as an effective signal for multilingual curriculum learning, where interleaving samples with diverse separability levels yields stable and generalizable gains. Together, we hope our work offers a new perspective on data utility in multilingual contexts and support the development of more linguistically informed LLMs. △ Less

Submitted 13 November, 2025; originally announced November 2025.

Comments: AAAI2026 Main Track Accepted

Equivariant Sampling for Improving Diffusion Model-based Image Restoration

Authors: Chenxu Wu, Qingpeng Kong, Peiang Zhao, Wendi Yang, Wenxin Ma, Fenghe Tang, Zihang Jiang, S. Kevin Zhou

Abstract: Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this paper, we address the limitations of current problem-agnostic DMIR methods by an… ▽ More Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this paper, we address the limitations of current problem-agnostic DMIR methods by analyzing their sampling process and providing effective solutions. We introduce EquS, a DMIR method that imposes equivariant information through dual sampling trajectories. To further boost EquS, we propose the Timestep-Aware Schedule (TAS) and introduce EquS$^+$. TAS prioritizes deterministic steps to enhance certainty and sampling efficiency. Extensive experiments on benchmarks demonstrate that our method is compatible with previous problem-agnostic DMIR methods and significantly boosts their performance without increasing computational costs. Our code is available at https://github.com/FouierL/EquS. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Comments: 12 pages, 9 figures

From Sequential to Recursive: Enhancing Decision-Focused Learning with Bidirectional Feedback

Authors: Xinyu Wang, Jinxiao Du, Yiyang Peng, Wei Ma

Abstract: Decision-focused learning (DFL) has emerged as a powerful end-to-end alternative to conventional predict-then-optimize (PTO) pipelines by directly optimizing predictive models through downstream decision losses. Existing DFL frameworks are limited by their strictly sequential structure, referred to as sequential DFL (S-DFL). However, S-DFL fails to capture the bidirectional feedback between predic… ▽ More Decision-focused learning (DFL) has emerged as a powerful end-to-end alternative to conventional predict-then-optimize (PTO) pipelines by directly optimizing predictive models through downstream decision losses. Existing DFL frameworks are limited by their strictly sequential structure, referred to as sequential DFL (S-DFL). However, S-DFL fails to capture the bidirectional feedback between prediction and optimization in complex interaction scenarios. In view of this, we first time propose recursive decision-focused learning (R-DFL), a novel framework that introduces bidirectional feedback between downstream optimization and upstream prediction. We further extend two distinct differentiation methods: explicit unrolling via automatic differentiation and implicit differentiation based on fixed-point methods, to facilitate efficient gradient propagation in R-DFL. We rigorously prove that both methods achieve comparable gradient accuracy, with the implicit method offering superior computational efficiency. Extensive experiments on both synthetic and real-world datasets, including the newsvendor problem and the bipartite matching problem, demonstrate that R-DFL not only substantially enhances the final decision quality over sequential baselines but also exhibits robust adaptability across diverse scenarios in closed-loop decision-making problems. △ Less

Submitted 27 November, 2025; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: Accepted by The 40th Annual AAAI Conference on Artificial Intelligence (AAAI-26), Main track

From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training

Authors: Donglai Xu, Hongzheng Yang, Yuzhi Zhao, Pingping Zhang, Jinpeng Chen, Wenao Ma, Zhijian Hou, Mengyang Wu, Xiaolei Li, Senkang Hu, Ziyi Guan, Jason Chun Lok Li, Lai Man Po

Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone to substantial annotation noise in real-world scenarios. Existing unsupervised RLVR methods, including pure entropy minimization, can overfit to incorrect labels and limit the crucial reward ranking signal for Group-Rel… ▽ More Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone to substantial annotation noise in real-world scenarios. Existing unsupervised RLVR methods, including pure entropy minimization, can overfit to incorrect labels and limit the crucial reward ranking signal for Group-Relative Policy Optimization (GRPO). To address these challenges and enhance noise tolerance, we propose a novel two-stage, token-level entropy optimization method for RLVR. This approach dynamically guides the model from exploration to exploitation during training. In the initial exploration phase, token-level entropy maximization promotes diverse and stochastic output generation, serving as a strong regularizer that prevents premature convergence to noisy labels and ensures sufficient intra-group variation, which enables more reliable reward gradient estimation in GRPO. As training progresses, the method transitions into the exploitation phase, where token-level entropy minimization encourages the model to produce confident and deterministic outputs, thereby consolidating acquired knowledge and refining prediction accuracy. Empirically, across three MLLM backbones - Qwen2-VL-2B, Qwen2-VL-7B, and Qwen2.5-VL-3B - spanning diverse noise settings and multiple tasks, our phased strategy consistently outperforms prior approaches by unifying and enhancing external, internal, and entropy-based methods, delivering robust and superior performance across the board. △ Less

Submitted 10 November, 2025; originally announced November 2025.

S$^2$Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening

Authors: Bowei He, Bowen Gao, Yankai Chen, Yanyan Lan, Chen Ma, Philip S. Yu, Ya-Qin Zhang, Wei-Ying Ma

Abstract: Virtual screening (VS) is an essential task in drug discovery, focusing on the identification of small-molecule ligands that bind to specific protein pockets. Existing deep learning methods, from early regression models to recent contrastive learning approaches, primarily rely on structural data while overlooking protein sequences, which are more accessible and can enhance generalizability. Howeve… ▽ More Virtual screening (VS) is an essential task in drug discovery, focusing on the identification of small-molecule ligands that bind to specific protein pockets. Existing deep learning methods, from early regression models to recent contrastive learning approaches, primarily rely on structural data while overlooking protein sequences, which are more accessible and can enhance generalizability. However, directly integrating protein sequences poses challenges due to the redundancy and noise in large-scale protein-ligand datasets. To address these limitations, we propose \textbf{S$^2$Drug}, a two-stage framework that explicitly incorporates protein \textbf{S}equence information and 3D \textbf{S}tructure context in protein-ligand contrastive representation learning. In the first stage, we perform protein sequence pretraining on ChemBL using an ESM2-based backbone, combined with a tailored data sampling strategy to reduce redundancy and noise on both protein and ligand sides. In the second stage, we fine-tune on PDBBind by fusing sequence and structure information through a residue-level gating module, while introducing an auxiliary binding site prediction task. This auxiliary task guides the model to accurately localize binding residues within the protein sequence and capture their 3D spatial arrangement, thereby refining protein-ligand matching. Across multiple benchmarks, S$^2$Drug consistently improves virtual screening performance and achieves strong results on binding site prediction, demonstrating the value of bridging sequence and structure in contrastive learning. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI 2026 Main Technical Track

Rate-Optimal Streaming Codes Under an Extended Delay Profile for Three-Node Relay Networks With Burst Erasures

Authors: Zhipeng Li, Wenjie Ma

Abstract: This paper investigates streaming codes for three-node relay networks under burst packet erasures with a delay constraint $T$. In any sliding window of $T+1$ consecutive packets, the source-to-relay and relay-to-destination channels may introduce burst erasures of lengths at most $b_1$ and $b_2$, respectively. Let $u = \max\{b_1, b_2\}$ and $v = \min\{b_1, b_2\}$. Singhvi et al. proposed a constru… ▽ More This paper investigates streaming codes for three-node relay networks under burst packet erasures with a delay constraint $T$. In any sliding window of $T+1$ consecutive packets, the source-to-relay and relay-to-destination channels may introduce burst erasures of lengths at most $b_1$ and $b_2$, respectively. Let $u = \max\{b_1, b_2\}$ and $v = \min\{b_1, b_2\}$. Singhvi et al. proposed a construction achieving the optimal rate when $u\mid (T-u-v)$. In this paper, we present an extended delay profile method that attains the optimal rate under a relaxed constraint $\frac{T - u - v}{2u - v} \leq \left\lfloor \frac{T - u - v}{u} \right\rfloor$ and it strictly cover restriction $u\mid (T-u-v)$. %Furthermore, we demonstrate that the optimal rate for streaming codes is not achievable when $0< T-u-v<v$ under the convolutional code framework. △ Less

Submitted 10 November, 2025; originally announced November 2025.

FLEX: Continuous Agent Evolution via Forward Learning from Experience

Authors: Zhicheng Cai, Xinyuan Guo, Yu Pei, Jiangtao Feng, Jinsong Su, Jiangjie Chen, Ya-Qin Zhang, Wei-Ying Ma, Mingxuan Wang, Hao Zhou

Abstract: Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLE… ▽ More Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLEX cultivates scalable and inheritable evolution by constructing a structured experience library through continual reflection on successes and failures during interaction with the environment. FLEX delivers substantial improvements on mathematical reasoning, chemical retrosynthesis, and protein fitness prediction (up to 23% on AIME25, 10% on USPTO50k, and 14% on ProteinGym). We further identify a clear scaling law of experiential growth and the phenomenon of experience inheritance across agents, marking a step toward scalable and inheritable continuous agent evolution. Project Page: https://flex-gensi-thuair.github.io. △ Less

Submitted 7 December, 2025; v1 submitted 9 November, 2025; originally announced November 2025.

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation

Authors: Qiming Li, Zekai Ye, Xiaocheng Feng, Weihong Zhong, Weitao Ma, Xiachong Feng

Abstract: Despite the remarkable advancements of Large Vision-Language Models (LVLMs), the mechanistic interpretability remains underexplored. Existing analyses are insufficiently comprehensive and lack examination covering visual and textual tokens, model components, and the full range of layers. This limitation restricts actionable insights to improve the faithfulness of model output and the development o… ▽ More Despite the remarkable advancements of Large Vision-Language Models (LVLMs), the mechanistic interpretability remains underexplored. Existing analyses are insufficiently comprehensive and lack examination covering visual and textual tokens, model components, and the full range of layers. This limitation restricts actionable insights to improve the faithfulness of model output and the development of downstream tasks, such as hallucination mitigation. To address this limitation, we introduce Fine-grained Cross-modal Causal Tracing (FCCT) framework, which systematically quantifies the causal effects on visual object perception. FCCT conducts fine-grained analysis covering the full range of visual and textual tokens, three core model components including multi-head self-attention (MHSA), feed-forward networks (FFNs), and hidden states, across all decoder layers. Our analysis is the first to demonstrate that MHSAs of the last token in middle layers play a critical role in aggregating cross-modal information, while FFNs exhibit a three-stage hierarchical progression for the storage and transfer of visual object representations. Building on these insights, we propose Intermediate Representation Injection (IRI), a training-free inference-time technique that reinforces visual object information flow by precisely intervening on cross-modal representations at specific components and layers, thereby enhancing perception and mitigating hallucination. Consistent improvements across five widely used benchmarks and LVLMs demonstrate IRI achieves state-of-the-art performance, while preserving inference speed and other foundational performance. △ Less

Submitted 19 November, 2025; v1 submitted 8 November, 2025; originally announced November 2025.

Comments: AAAI2026 Oral

GSE: Evaluating Sticker Visual Semantic Similarity via a General Sticker Encoder

Authors: Heng Er Metilda Chee, Jiayin Wang, Zhiqiang Guo, Weizhi Ma, Min Zhang

Abstract: Stickers have become a popular form of visual communication, yet understanding their semantic relationships remains challenging due to their highly diverse and symbolic content. In this work, we formally {define the Sticker Semantic Similarity task} and introduce {Triple-S}, the first benchmark for this task, consisting of 905 human-annotated positive and negative sticker pairs. Through extensive… ▽ More Stickers have become a popular form of visual communication, yet understanding their semantic relationships remains challenging due to their highly diverse and symbolic content. In this work, we formally {define the Sticker Semantic Similarity task} and introduce {Triple-S}, the first benchmark for this task, consisting of 905 human-annotated positive and negative sticker pairs. Through extensive evaluation, we show that existing pretrained vision and multimodal models struggle to capture nuanced sticker semantics. To address this, we propose the {General Sticker Encoder (GSE)}, a lightweight and versatile model that learns robust sticker embeddings using both Triple-S and additional datasets. GSE achieves superior performance on unseen stickers, and demonstrates strong results on downstream tasks such as emotion classification and sticker-to-sticker retrieval. By releasing both Triple-S and GSE, we provide standardized evaluation tools and robust embeddings, enabling future research in sticker understanding, retrieval, and multimodal content generation. The Triple-S benchmark and GSE have been publicly released and are available here. △ Less

Submitted 6 November, 2025; originally announced November 2025.

X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations

Authors: Maximus A. Pace, Prithwish Dan, Chuanruo Ning, Atiksh Bhardwaj, Audrey Du, Edward W. Duan, Wei-Chiu Ma, Kushal Kedia

Abstract: Human videos can be recorded quickly and at scale, making them an appealing source of training data for robot learning. However, humans and robots differ fundamentally in embodiment, resulting in mismatched action execution. Direct kinematic retargeting of human hand motion can therefore produce actions that are physically infeasible for robots. Despite these low-level differences, human demonstra… ▽ More Human videos can be recorded quickly and at scale, making them an appealing source of training data for robot learning. However, humans and robots differ fundamentally in embodiment, resulting in mismatched action execution. Direct kinematic retargeting of human hand motion can therefore produce actions that are physically infeasible for robots. Despite these low-level differences, human demonstrations provide valuable motion cues about how to manipulate and interact with objects. Our key idea is to exploit the forward diffusion process: as noise is added to actions, low-level execution differences fade while high-level task guidance is preserved. We present X-Diffusion, a principled framework for training diffusion policies that maximally leverages human data without learning dynamically infeasible motions. X-Diffusion first trains a classifier to predict whether a noisy action is executed by a human or robot. Then, a human action is incorporated into policy training only after adding sufficient noise such that the classifier cannot discern its embodiment. Actions consistent with robot execution supervise fine-grained denoising at low noise levels, while mismatched human actions provide only coarse guidance at higher noise levels. Our experiments show that naive co-training under execution mismatches degrades policy performance, while X-Diffusion consistently improves it. Across five manipulation tasks, X-Diffusion achieves a 16% higher average success rate than the best baseline. The project website is available at https://portal-cornell.github.io/X-Diffusion/. △ Less

Submitted 6 November, 2025; originally announced November 2025.

Emu3.5: Native Multimodal Models are World Learners

Authors: Yufeng Cui, Honghao Chen, Haoge Deng, Xu Huang, Xinghang Li, Jirong Liu, Yang Liu, Zhuoyan Luo, Jinsheng Wang, Wenxuan Wang, Yueze Wang, Chengyuan Wang, Fan Zhang, Yingli Zhao, Ting Pan, Xianduo Li, Zecheng Hao, Wenxuan Ma, Zhuo Chen, Yulong Ao, Tiejun Huang, Zhongyuan Wang, Xinlong Wang

Abstract: We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interle… ▽ More We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research. △ Less

Submitted 30 October, 2025; originally announced October 2025.

Comments: project page: https://emu.world

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start

Authors: Kun Chen, Peng Shi, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao, Lin Ma

Abstract: Reinforcement learning (RL) with verifiable rewards has recently catalyzed a wave of "MLLM-r1" approaches that bring RL to vision language models. Most representative paradigms begin with a cold start, typically employing supervised fine-tuning (SFT), to initialize the policy before RL. However, SFT-based cold start adopts the reasoning paradigm intertwined with task solution and output format, wh… ▽ More Reinforcement learning (RL) with verifiable rewards has recently catalyzed a wave of "MLLM-r1" approaches that bring RL to vision language models. Most representative paradigms begin with a cold start, typically employing supervised fine-tuning (SFT), to initialize the policy before RL. However, SFT-based cold start adopts the reasoning paradigm intertwined with task solution and output format, which may induce instruction-style overfitting, weakens out-of-distribution generalization, and ultimately affects downstream RL. We revisit the cold start along two views, its training method and data construction, and introduce the Generalization Factor (GF) coefficient to quantify the generalization capability under different methods. Our empirical study finds that preference-based training methods (e.g. DPO) generalizes better than SFT-based methods in cold start. Motivated by this, we propose SPECS-a Self-distilled, Preference-based Cold Start framework that decouples multimodal learning: (1) generates introspective preference data pairs via self-distillation, avoiding reliance on larger teachers or manual annotation; (2) performs preference-based training to learn, focusing on shallow, transferable surface-form criteria (format, structure, style) rather than memorizing content; and (3) hands off to RL with verifiable rewards for deep reasoning results. Experimental results across multiple multimodal benchmarks show that our decoupling learning framework yields consistent performance gains over strong baselines, improving MEGA-Bench by 4.1% and MathVista by 12.2%. Additional experiments indicate that SPECS contributes to reducing in-distribution "stuckness," improving exploration, stabilizing training, and raising the performance ceiling. △ Less

Submitted 18 November, 2025; v1 submitted 28 October, 2025; originally announced October 2025.

Comments: Project Page: https://github.com/Kwen-Chen/SPECS-VL

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

Implicit State Estimation via Video Replanning

Authors: Po-Chen Ko, Jiayuan Mao, Yu-Hsiang Fu, Hsien-Jeng Yeh, Chu-Rong Chen, Wei-Chiu Ma, Yilun Du, Shao-Hua Sun

Abstract: Video-based representations have gained prominence in planning and decision-making due to their ability to encode rich spatiotemporal dynamics and geometric relationships. These representations enable flexible and generalizable solutions for complex tasks such as object manipulation and navigation. However, existing video planning frameworks often struggle to adapt to failures at interaction time… ▽ More Video-based representations have gained prominence in planning and decision-making due to their ability to encode rich spatiotemporal dynamics and geometric relationships. These representations enable flexible and generalizable solutions for complex tasks such as object manipulation and navigation. However, existing video planning frameworks often struggle to adapt to failures at interaction time due to their inability to reason about uncertainties in partially observed environments. To overcome these limitations, we introduce a novel framework that integrates interaction-time data into the planning process. Our approach updates model parameters online and filters out previously failed plans during generation. This enables implicit state estimation, allowing the system to adapt dynamically without explicitly modeling unknown state variables. We evaluate our framework through extensive experiments on a new simulated manipulation benchmark, demonstrating its ability to improve replanning performance and advance the field of video-based decision-making. △ Less

Submitted 20 October, 2025; originally announced October 2025.

On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders

Authors: Wenyu Mao, Jiancan Wu, Guoqing Hu, Zhengyi Yang, Wei Ji, Xiang Wang

Abstract: Diffusion models have emerged as a powerful paradigm for generative sequential recommendation, which typically generate next items to recommend guided by user interaction histories with a multi-step denoising process. However, the multi-step process relies on discrete approximations, introducing discretization error that creates a trade-off between computational efficiency and recommendation effec… ▽ More Diffusion models have emerged as a powerful paradigm for generative sequential recommendation, which typically generate next items to recommend guided by user interaction histories with a multi-step denoising process. However, the multi-step process relies on discrete approximations, introducing discretization error that creates a trade-off between computational efficiency and recommendation effectiveness. To address this trade-off, we propose TA-Rec, a two-stage framework that achieves one-step generation by smoothing the denoising function during pretraining while alleviating trajectory deviation by aligning with user preferences during fine-tuning. Specifically, to improve the efficiency without sacrificing the recommendation performance, TA-Rec pretrains the denoising model with Temporal Consistency Regularization (TCR), enforcing the consistency between the denoising results across adjacent steps. Thus, we can smooth the denoising function to map the noise as oracle items in one step with bounded error. To further enhance effectiveness, TA-Rec introduces Adaptive Preference Alignment (APA) that aligns the denoising process with user preference adaptively based on preference pair similarity and timesteps. Extensive experiments prove that TA-Rec's two-stage objective effectively mitigates the discretization errors-induced trade-off, enhancing both efficiency and effectiveness of diffusion-based recommenders. △ Less

Submitted 22 October, 2025; v1 submitted 20 October, 2025; originally announced October 2025.

Pursuing Minimal Sufficiency in Spatial Reasoning

Authors: Yejie Guo, Yunzhong Hou, Wufei Ma, Meng Tang, Ming-Hsuan Yang

Abstract: Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from 2D-centric pre-training, and reasoning failures induced by redundant 3D information. To address these, we first construct a Minimal Sufficient Set (MSS) of information… ▽ More Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from 2D-centric pre-training, and reasoning failures induced by redundant 3D information. To address these, we first construct a Minimal Sufficient Set (MSS) of information before answering a given question: a compact selection of 3D perception results from \textit{expert models}. We introduce MSSR (Minimal Sufficient Spatial Reasoner), a dual-agent framework that implements this principle. A Perception Agent programmatically queries 3D scenes using a versatile perception toolbox to extract sufficient information, including a novel SOG (Situated Orientation Grounding) module that robustly extracts language-grounded directions. A Reasoning Agent then iteratively refines this information to pursue minimality, pruning redundant details and requesting missing ones in a closed loop until the MSS is curated. Extensive experiments demonstrate that our method, by explicitly pursuing both sufficiency and minimality, significantly improves accuracy and achieves state-of-the-art performance across two challenging benchmarks. Furthermore, our framework produces interpretable reasoning paths, offering a promising source of high-quality training data for future models. Source code is available at https://github.com/gyj155/mssr. △ Less

Submitted 18 October, 2025; originally announced October 2025.

Integrating LLM and Diffusion-Based Agents for Social Simulation

Authors: Xinyi Li, Zhiqiang Guo, Qinglang Guo, Hao Jin, Weizhi Ma, Min Zhang

Abstract: Agent-based social simulation provides a valuable methodology for predicting social information diffusion, yet existing approaches face two primary limitations. Traditional agent models often rely on rigid behavioral rules and lack semantic understanding of textual content, while emerging large language model (LLM)-based agents incur prohibitive computational costs at scale. To address these chall… ▽ More Agent-based social simulation provides a valuable methodology for predicting social information diffusion, yet existing approaches face two primary limitations. Traditional agent models often rely on rigid behavioral rules and lack semantic understanding of textual content, while emerging large language model (LLM)-based agents incur prohibitive computational costs at scale. To address these challenges, we propose a hybrid simulation framework that strategically integrates LLM-driven agents with diffusion model-based agents. The framework employs LLM-based agents to simulate a core subset of users with rich semantic reasoning, while a diffusion model handles the remaining population efficiently. Although the two agent types operate on disjoint user groups, both incorporate key factors including user personalization, social influence, and content awareness, and interact through a coordinated simulation process. Extensive experiments on three real-world datasets demonstrate that our framework outperforms existing methods in prediction accuracy, validating the effectiveness of its modular design. △ Less

Submitted 18 October, 2025; originally announced October 2025.

Comments: 10 pages, 3 figures, 4 tables

A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling

Authors: Shiyu Ji, Farnoosh Hashemi, Joice Chen, Juanwen Pan, Weicheng Ma, Hefan Zhang, Sophia Pan, Ming Cheng, Shubham Mohole, Saeed Hassanpour, Soroush Vosoughi, Michael Macy

Abstract: Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been limited by reliance on human annotation, which is costly, inconsistent, difficult to scale. Their associated datasets are often limited to specific topics and strategies, posing challenges for robust model development. We… ▽ More Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been limited by reliance on human annotation, which is costly, inconsistent, difficult to scale. Their associated datasets are often limited to specific topics and strategies, posing challenges for robust model development. We propose a novel framework that leverages large language models (LLMs) to automatically generate and label synthetic debate data based on a four-part rhetorical typology (causal, empirical, emotional, moral). We fine-tune transformer-based classifiers on this LLM-labeled dataset and validate its performance against human-labeled data on this dataset and on multiple external corpora. Our model achieves high performance and strong generalization across topical domains. We illustrate two applications with the fine-tuned model: (1) the improvement in persuasiveness prediction from incorporating rhetorical strategy labels, and (2) analyzing temporal and partisan shifts in rhetorical strategies in U.S. Presidential debates (1960-2020), revealing increased use of affective over cognitive argument in U.S. Presidential debates. △ Less

Submitted 16 October, 2025; originally announced October 2025.

Comments: The first two authors contributed equally

Coder as Editor: Code-driven Interpretable Molecular Optimization

Authors: Wenyu Zhu, Chengzhu Li, Xiaohe Tian, Yifan Wang, Yinjun Jia, Jianhui Wang, Bowen Gao, Ya-Qin Zhang, Wei-Ying Ma, Yanyan Lan

Abstract: Molecular optimization is a central task in drug discovery that requires precise structural reasoning and domain knowledge. While large language models (LLMs) have shown promise in generating high-level editing intentions in natural language, they often struggle to faithfully execute these modifications-particularly when operating on non-intuitive representations like SMILES. We introduce MECo, a… ▽ More Molecular optimization is a central task in drug discovery that requires precise structural reasoning and domain knowledge. While large language models (LLMs) have shown promise in generating high-level editing intentions in natural language, they often struggle to faithfully execute these modifications-particularly when operating on non-intuitive representations like SMILES. We introduce MECo, a framework that bridges reasoning and execution by translating editing actions into executable code. MECo reformulates molecular optimization for LLMs as a cascaded framework: generating human-interpretable editing intentions from a molecule and property goal, followed by translating those intentions into executable structural edits via code generation. Our approach achieves over 98% accuracy in reproducing held-out realistic edits derived from chemical reactions and target-specific compound pairs. On downstream optimization benchmarks spanning physicochemical properties and target activities, MECo substantially improves consistency by 38-86 percentage points to 90%+ and achieves higher success rates over SMILES-based baselines while preserving structural similarity. By aligning intention with execution, MECo enables consistent, controllable and interpretable molecular design, laying the foundation for high-fidelity feedback loops and collaborative human-AI workflows in drug discovery. △ Less

Submitted 16 October, 2025; originally announced October 2025.

Reliable Fine-Grained Evaluation of Natural Language Math Proofs

Authors: Wenjie Ma, Andrei Cojocaru, Neel Kolhe, Bradley Louie, Robin Said Sharif, Haihan Zhang, Vincent Zhuang, Matei Zaharia, Sewon Min

Abstract: Recent advances in large language models (LLMs) for mathematical reasoning have largely focused on tasks with easily verifiable final answers; however, generating and verifying natural language math proofs remains an open challenge. We identify the absence of a reliable, fine-grained evaluator for LLM-generated math proofs as a critical gap. To address this, we propose a systematic methodology for… ▽ More Recent advances in large language models (LLMs) for mathematical reasoning have largely focused on tasks with easily verifiable final answers; however, generating and verifying natural language math proofs remains an open challenge. We identify the absence of a reliable, fine-grained evaluator for LLM-generated math proofs as a critical gap. To address this, we propose a systematic methodology for developing and validating evaluators that assign fine-grained scores on a 0-7 scale to model-generated math proofs. To enable this study, we introduce ProofBench, the first expert-annotated dataset of fine-grained proof ratings, spanning 145 problems from six major math competitions (USAMO, IMO, Putnam, etc) and 435 LLM-generated solutions from Gemini-2.5-pro, o3, and DeepSeek-R1. %with expert gradings. Using ProofBench as a testbed, we systematically explore the evaluator design space across key axes: the backbone model, input context, instructions and evaluation workflow. Our analysis delivers ProofGrader, an evaluator that combines a strong reasoning backbone LM, rich context from reference solutions and marking schemes, and a simple ensembling method; it achieves a low Mean Absolute Error (MAE) of 0.926 against expert scores, significantly outperforming naive baselines. Finally, we demonstrate its practical utility in a best-of-$n$ selection task: at $n=16$, ProofGrader achieves an average score of 4.14 (out of 7), closing 78% of the gap between a naive binary evaluator (2.48) and the human oracle (4.62), highlighting its potential to advance downstream proof generation. △ Less

Submitted 13 October, 2025; originally announced October 2025.

Comments: 31 pages, 6 figures, 10 tables

Kernel Representation and Similarity Measure for Incomplete Data

Authors: Yang Cao, Sikun Yang, Kai He, Wenjun Ma, Ming Liu, Yujiu Yang, Jian Weng

Abstract: Measuring similarity between incomplete data is a fundamental challenge in web mining, recommendation systems, and user behavior analysis. Traditional approaches either discard incomplete data or perform imputation as a preprocessing step, leading to information loss and biased similarity estimates. This paper presents the proximity kernel, a new similarity measure that directly computes similarit… ▽ More Measuring similarity between incomplete data is a fundamental challenge in web mining, recommendation systems, and user behavior analysis. Traditional approaches either discard incomplete data or perform imputation as a preprocessing step, leading to information loss and biased similarity estimates. This paper presents the proximity kernel, a new similarity measure that directly computes similarity between incomplete data in kernel feature space without explicit imputation in the original space. The proposed method introduces data-dependent binning combined with proximity assignment to project data into a high-dimensional sparse representation that adapts to local density variations. For missing value handling, we propose a cascading fallback strategy to estimate missing feature distributions. We conduct clustering tasks on the proposed kernel representation across 12 real world incomplete datasets, demonstrating superior performance compared to existing methods while maintaining linear time complexity. All the code are available at https://anonymous.4open.science/r/proximity-kernel-2289. △ Less

Submitted 15 October, 2025; originally announced October 2025.