11 papers
ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation
Can Jin, Ying Li, Jingchen Sun +5
Visual prompting (VP) has emerged as a parameter-efficient method for adapting pre-trained models to downstream tasks. However, existing approaches encounter a trade-off between fl…
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Jiakang Li, Guanyu Zhu, Can Jin +8
Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavio…
CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs
Chengwen Liu, Hao Peng, Jisheng Dang +3
In multimodal video reasoning, reinforcement learning-based methods typically rely on simplistic and inflexible reasoning-length control strategies that fail to adapt to the model'…
Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs
Chengwen Liu, Zhe Huang, Jisheng Dang +3
Reinforcement learning has improved the reasoning ability of large language models, but applying outcome-only rewards to video multimodal large language models (Video-MLLMs) provid…
DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
Can Jin, Hongwu Peng, Mingcan Xiang +7
Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top- routing imposes a rigid sparsity pattern that ignores the int…
RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
Can Jin, Hongwu Peng, Anxiang Zhang +8
In an Information Retrieval (IR) system, reranking plays a critical role by sorting candidate passages according to their relevance to a specific query. This process demands a nuan…