1 citations · 1 across the 19 of their papers we have counts for
22 papers
PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction
Shuai Shao, Jinchen He, Cunxin Fan +10
Building physical simulations from video requires coding agents to translate observations into executable models and refine them through tool use. We introduce PhysCodeGym, a bench…
CatPortrait: Taming Video Generative Models for Portrait Animation via In-context Conditioning
Ziqi Ni, Zhou Fang, Shijian Wang +2
Recent video generative models have shown strong capability in synthesizing high-quality and temporally coherent videos. Yet, adapting them for controllable portrait animation rema…
RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation
Haocheng Yang, Yuchao Zhang, Licheng Pan +8
Rubric-based reinforcement learning (RL) provides interpretable rewards for aligning large language models (LLMs) by evaluating responses against query-specific evaluation criteria…
Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum
Xingjian Wang, Shijian Wang, Yibo Wang +4
Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on simple queries. They largely ov…
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
Xichen Zhang, Guankai Li, Yinghao Zhu +6
Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-scale memory. However, curren…
Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
Shuai Shao, Kangning Zhang, Qingyao Li +7
Agents built around large language models continually accumulate interaction trajectories during deployment, yet their behavior typically remains fixed. Beyond updating model weigh…
EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE
Zexuan Yan, Yuzhou Wu, Yue Ma +9
Egocentric video offers rich manipulation experience for embodied AI, yet collecting diverse egocentric data across scenes, objects, motions, and embodiments remains costly. We pre…
Uncertainty-Aware Reward Modeling for Stable RLHF
Licheng Pan, Haocheng Yang, Haoxuan Li +7
Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. H…
AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
Jiarui Jin, Zexuan Yan, Shijian Wang +2
In this paper, we present AgentDisCo, a novel Disentangled and Collaborative agentic architecture that formulates deep research as an adversarial optimization problem between infor…
MMSkills: Towards Multimodal Skills for General Visual Agents
Kangning Zhang, Shuai Shao, Qingyao Li +8
Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable co…
Optimal Transport for LLM Reward Modeling from Noisy Preference
Licheng Pan, Haochen Yang, Haoxuan Li +8
Reward models are fundamental to Reinforcement Learning from Human Feedback (RLHF), yet real-world datasets are inevitably corrupted by noisy preference. Conventional training obje…
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Fanqing Meng, Lingxiao Du, Zijian Wu +46
Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change in…
MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences
Shijian Wang, Jiarui Jin, Runhao Fu +11
Research agents have recently achieved significant progress in information seeking and synthesis across heterogeneous textual and visual sources. In this paper, we introduce MuSEAg…
GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows
Zexuan Yan, Jiarui Jin, Yue Ma +5
Despite recent advances in generative models driving significant progress in text rendering, accurately generating complex text and mathematical formulas remains a formidable chall…
Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
Bowei Xia, Mengkang Hu, Shijian Wang +5
Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, exist…
OmniGAIA: Towards Native Omni-Modal AI Agents
Xiaoxi Li, Wenxiang Jiao, Jiarui Jin +10
Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However,…
Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
Mengkang Hu, Bowei Xia, Yuran Wu +9
Symbolic world models (e.g., PDDL domains or executable simulators) are central to model-based planning, but training LLMs to generate such world models is limited by the lack of l…
Synthetic Curriculum Reinforces Compositional Text-to-Image Generation
Shijian Wang, Runhao Fu, Siyi Zhao +6
Text-to-Image (T2I) generation has long been an open problem, with compositional synthesis remaining particularly challenging. This task requires accurate rendering of complex scen…
Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
Shijian Wang, Jiarui Jin, Xingjian Wang +6
Recent advances in image reasoning methods, particularly "Thinking with Images", have demonstrated remarkable success in Multimodal Large Language Models (MLLMs); however, this dyn…
Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification
Shijian Wang, Linxin Song, Ryotaro Shimizu +2
Zero-shot domain-specific image classification is challenging in classifying real images without ground-truth in-domain training examples. Recent research involved knowledge from t…
Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model
Shijian Wang, Linxin Song, Jieyu Zhang +9
Current multimodal language model (MLM) training approaches overlook the influence of instruction templates. Previous research deals with this problem by leveraging hand-crafted or…
Adaptive In-conversation Team Building for Language Model Agents
Linxin Song, Jiale Liu, Jieyu Zhang +5
Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks, while the effective design of multiple agents for a particula…