17 papers
GroundedVDR: Grounding Video-to-Web Evidence Dependencies in Video Deep Research
Xiyuan Liang, Yu Wang, Zuhao Yang +7
Video large multimodal models have improved at identifying cross-frame visual evidence and conducting open-web retrieval, as reflected in recent video deep research (VDR) benchmark…
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding
Keming Wu, Baoyi Wang, Kaichen Zhang +7
Streaming video understanding demands direct responses from the causally observed prefix of an unfolding video. Existing systems add inference-time memory, retrieval, and compressi…
Enhancing Pathological VLMs with Cross-scale Reasoning
Chi Phan, Tianyi Zhang, Qiaochu Xue +5
Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from global tissue architecture at low magnification to cellular morphology at higher m…
PathScale-R1: Cross-scale Reasoning for Pathological Image Analysis
Chi Phan, Tianyi Zhang, Yufeng Wu +7
Pathological diagnosis is inherently multi-scale, requiring the integration of global tissue architecture at low magnification with cellular morphology at higher magnification. How…
The Illusion of Multi-Agent Advantage
Prathyusha Jwalapuram, Hehai Lin, Chuyuan Li +7
Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed d…
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Zuhao Yang, Kaichen Zhang, Sudong Wang +7
Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video unders…
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
Keming Wu, Yijing Cui, Wenhan Xue +11
Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet…
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Keming Wu, Zuhao Yang, Kaichen Zhang +24
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning…
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
Sudong Wang, Weiquan Huang, Xiaomin Yu +9
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiab…
Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems
Hehai Lin, Yu Yan, Zixuan Wang +6
Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked…
BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement Learning
Yubao Zhao, Weiquan Huang, Sudong Wang +4
Agentic reinforcement learning enables large language models to perform multi-turn planning and tool use, but long-horizon training remains challenging under sparse trajectory-leve…
Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
Yunjian Zhang, Sudong Wang, Yang Li +5
Large language models (LLMs) have exhibited remarkable performance on complex reasoning tasks, with reinforcement learning under verifiable rewards (RLVR) emerging as a principled…
AMA: Adaptive Memory via Multi-Agent Collaboration
Weiquan Huang, Zixuan Wang, Hehai Lin +6
The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the…
SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
Peiran Xu, Sudong Wang, Yao Zhu +3
Spatial cognition is fundamental to real-world multimodal intelligence, allowing models to effectively interact with the physical environment. While multimodal large language model…
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Zuhao Yang, Sudong Wang, Kaichen Zhang +8
Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when proc…
Interactive Learning for LLM Reasoning
Hehai Lin, Shilei Cao, Sudong Wang +5
Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large Language Models (LLMs), thereby c…
Towards Understanding How Knowledge Evolves in Large Vision-Language Models
Sudong Wang, Yunjian Zhang, Yao Zhu +4
Large Vision-Language Models (LVLMs) are gradually becoming the foundation for many artificial intelligence applications. However, understanding their internal working mechanisms h…