1 citations · 1 across the 20 of their papers we have counts for
22 papers
FARL: A Fully Automated Pipeline of RL Interface and Solver Design
Tianyu Jin, Liuyu Xiang, Chaowen Yang +3
Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new tasks still relies heavily on…
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
Xiaoang Xu, Siyuan Liu, Shuo Wang +13
Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation and context costs. Existing methods either lose intermediat…
HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses
Xiao Zhang, Yusheng Wang, Yuhao Fei +5
Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts. However, this capability creates delaye…
SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game Planning
Tianyu Jin, Shuo Chen, Yida Wang +5
Grand-strategy games such as Civilization pose a distinctive long-horizon planning problem: an agent must divide one shared resource pool among six competing domains -- technology,…
Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents
Zedong Yu, Qianxing Li, Zhi Gao +8
Graphical user interface (GUI) agents are systems powered by large multimodal models (LMMs). They perceive screen state and execute user instructions through GUI actions such as cl…
AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration
Haotian Li, Yida Wang, Leyuan Wang +7
In recent years, multimodal large language models (MLLMs) have shown strong potential for embodied intelligence, yet their ability to maintain geometrically consistent spatial unde…
Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis
Zicheng Kong, Dehua Ma, Zhenbo Xu +9
Multimodal large language models (MLLMs) struggle with alignment due to the limitations of existing reward models (RMs), which are predominantly vision-centric, dependent on costly…
Simulation-Free PSRO: Removing Game Simulation from Policy Space Response Oracles
Yingzhuo Liu, Shuodi Liu, Weijun Luo +2
Policy Space Response Oracles (PSRO) combines game-theoretic equilibrium computation with learning and is effective in approximating Nash Equilibrium in zero-sum games. However, th…
Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders
Qingsen Ma, Dianyun Wang, Jiaming Lyu +8
The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose…
Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis
Qingsen Ma, Chen Zou, Dianyun Wang +3
Under extremely low-light conditions, novel view synthesis (NVS) faces severe degradation in terms of geometry, color consistency, and radiometric stability. Standard 3D Gaussian S…
Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
Shuodi Liu, Yingzhuo Liu, Zi Wang +4
Large language models (LLMs) have demonstrated remarkable reasoning and planning capabilities, driving extensive research into task decomposition. Existing task decomposition metho…
GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks
Chenrui Shi, Zedong Yu, Zhi Gao +7
Vision language models (VLMs) have advanced graphical user interface (GUI) task automation but still lag behind humans. We hypothesize this gap stems from missing core GUI knowledg…
OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing
Fuqing Bie, Shiyu Huang, Xijia Tao +6
While generalist foundation models like Gemini and GPT-4o demonstrate impressive multi-modal competence, existing evaluations fail to test their intelligence in dynamic, interactiv…
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Pengxiang Li, Zechen Hu, Zirui Shang +15
Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL):…
Do MLLMs Really Understand the Charts?
Xiao Zhang, Dongyuan Li, Liuyu Xiang +3
Although Multimodal Large Language Models (MLLMs) have demonstrated increasingly impressive performance in chart understanding, most of them exhibit alarming hallucinations and sig…
Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding
Xiaojie Zhang, Yuanfei Wang, Ruihai Wu +5
Articulated objects pose diverse manipulation challenges for robots. Since their internal structures are not directly observable, robots must adaptively explore and refine actions…
Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation
Chenxu Wang, Yonggang Jin, Cheng Hu +7
Adapting a single agent to a new multi-agent system brings challenges, necessitating adjustments across various tasks, environments, and interactions with unknown teammates and opp…
GIEBench: Towards Holistic Evaluation of Group Identity-based Empathy for Large Language Models
Leyan Wang, Yonggang Jin, Tianhao Shen +9
As large language models (LLMs) continue to develop and gain widespread application, the ability of LLMs to exhibit empathy towards diverse group identities and understand their pe…
Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning Perspective
Leyuan Wang, Liuyu Xiang, Yunlong Wang +2
Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argu…
CLIP model is an Efficient Online Lifelong Learner
Leyuan Wang, Liuyu Xiang, Yujie Wei +2
Online Lifelong Learning (OLL) addresses the challenge of learning from continuous and non-stationary data streams. Existing online lifelong learning methods based on image classif…
Dynamic Generation of Personalities with Large Language Models
Jianzhi Liu, Hexiang Gu, Tianyu Zheng +4
In the realm of mimicking human deliberation, large language models (LLMs) show promising performance, thereby amplifying the importance of this research area. Deliberation is infl…
Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction
Yonggang Jin, Ge Zhang, Hao Zhao +7
Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkabl…