2 citations · 3 across the 18 of their papers we have counts for
20 papers
INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning
Shuai Wang, Jiayi Kuang, Yinghui Li +4
Mathematical reasoning has seen rapid progress in large language models (LLMs), yet existing methods optimize predominantly for final-answer correctness, raising the question wheth…
From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities
Jiayi Kuang, Yinghui Li, Yunze Song +11
Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate onl…
Dream2Reward: Transition-Alignment Reward Models from Positive Demonstrations for Robotic Manipulation
Haoyu Zhang, Zecui Zeng, Bin Wang +3
Learning robotic policies requires dense rewards that remain informative when behavior departs from successful demonstrations. Progress-based rewards estimate how far an observatio…
Joint On-and-Off Policy Learning for Vision-and-Language Navigation
Qingrong He, Lin Zhao, Kevin Zheng +1
Vision-and-Language Navigation (VLN) necessitates an embodied agent to navigate in the physical world by adhering to natural language instructions. Recent advancements in Vision-La…
Visually-Guided Policy Optimization for Multimodal Reasoning
Zengbin Wang, Feng Xiong, Liang Lin +5
Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning ability of vision-language models (VLMs). However, the inherent text-dominated nature…
Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding
Yinghui Li, Jiayi Kuang, Peng Xing +11
Multimodal large language models (MLLMs) perform strongly on natural images, yet their ability to understand discrete visual symbols remains unclear. We present a multi-domain benc…
AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?
Liang Lin, Feng Xiong, Zengbin Wang +5
Diffusion Large Language Models (DLLMs) have emerged as a powerful alternative to autoregressive models, enabling parallel token generation across multiple positions. However, pref…
TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning
Daixian Liu, Jiayi Kuang, Yinghui Li +8
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual recognition and semantic understanding, yet precise compositional spatial reasoning under geome…
SHARE: Sharing Human Actions across Robot Embodiments through Unified Retargeting and Tracking
Haoyu Zhang, Junzhe Xu, Shibo Jin +8
The central challenge in reusing human actions across robots is the need to realize shared intent through incompatible kinematics, dynamics, and control interfaces. We present SHAR…
Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making
Yue Pei, Hongming Zhang, Chao Gao +7
Target-conditioned sequence models provide a simple interface for controllable offline decision making, but the requested target return can be an unreliable control signal, especia…
Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
Liang Lin, Zhihao Xu, Xuehai Tang +5
The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensit…
RoboPearls: Editable Video Simulation for Robot Manipulation
Tao Tang, Likui Zhang, Youpeng Wen +9
The development of generalist robot manipulation policies has seen significant progress, driven by large-scale demonstration data across diverse environments. However, the high cos…
EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
Bingqian Lin, Yunshuang Nie, Khun Loun Zai +10
Recent studies have revealed the potential of training open-source Large Language Models (LLMs) to unleash LLMs' reasoning ability for enhancing vision-language navigation (VLN) pe…
RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation
Kaidong Zhang, Rongtao Xu, Pengzhen Ren +4
Operating robots in open-ended scenarios with diverse tasks is a crucial research and application direction in robotics. While recent progress in natural language processing and la…
Pre-Trained Video Generative Models as World Simulators
Haoran He, Yang Zhang, Liang Lin +2
Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often genera…
InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction
Pengzhen Ren, Min Li, Zhen Luo +15
Realizing scaling laws in embodied AI has become a focus. However, previous work has been scattered across diverse simulation platforms, with assets and models lacking unified inte…
All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents
Zhiqiang Wang, Hao Zheng, Yunshuang Nie +11
Embodied AI is transforming how AI systems interact with the physical world, yet existing datasets are inadequate for developing versatile, general-purpose agents. These limitation…
VideoQA in the Era of LLMs: An Empirical Study
Junbin Xiao, Nanxin Huang, Hangyu Qin +8
Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks. As a golden testbed, Video Question Answering (VideoQA) plays pivotal role in V…
Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram
Ming-Liang Zhang, Zhong-Zhi Li, Fei Yin +2
Geometry problem solving (GPS) requires capacities of multi-modal understanding, multi-hop reasoning and theorem knowledge application. In this paper, we propose a neural-symbolic…
Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification
Gexin Huang, Chenfei Wu, Mingjie Li +6
Predicting genetic mutations from whole slide images is indispensable for cancer diagnosis. However, existing work training multiple binary classification models faces two challeng…