9 papers
LatentMem: Customizing Latent Memory for Multi-Agent Systems
Muxin Fu, Xiangyuan Xue, Yafu Li +5
Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual…
FM SO.P: A Progressive Task Mixture Framework with Automatic Evaluation for Cross-Domain SOP Understanding
Siyuan Huang, Ziyu Wang, Chao Pan +1
Standard Operating Procedures (SOPs) are critical for enterprise operations, yet existing language models struggle with SOP understanding and cross-domain generalization. Current m…
DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
Zefeng He, Xiaoye Qu, Yafu Li +3
While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leadin…
VideoSSR: Video Self-Supervised Reinforcement Learning
Zefeng He, Xiaoye Qu, Yafu Li +3
Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapi…
Spotlight on Token Perception for Multimodal Reinforcement Learning
Siyuan Huang, Xiaoye Qu, Yafu Li +4
While Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Vision-Language Models (LVLMs), most existing methods in multimodal rea…
FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
Zefeng He, Xiaoye Qu, Yafu Li +3
While Large Vision-Language Models (LVLMs) have achieved substantial progress in video understanding, their application to long video reasoning is hindered by uniform frame samplin…
Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
Yiming Wang, Pei Zhang, Siyuan Huang +4
Test-time scaling enhances large language model performance by allocating additional compute resources during inference. Best-of-N (BoN) sampling serves as a common sampling-based…
AutoAL: Automated Active Learning with Differentiable Query Strategy Search
Yifeng Wang, Xueying Zhan, Siyu Huang
As deep learning continues to evolve, the need for data efficiency becomes increasingly important. Considering labeling large datasets is both time-consuming and expensive, active…
Multimodal Generalized Category Discovery
Yuchang Su, Renping Zhou, Siyu Huang +4
Generalized Category Discovery (GCD) aims to classify inputs into both known and novel categories, a task crucial for open-world scientific discoveries. However, current GCD method…