Bin Li

ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant

HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST

DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialogue Policy with Cognitive Dual-Systems

CACR: Reinforcing Temporal Answer Grounding in Videos via Candidate-Aware Causal Reasoning

DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models

Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision-Language Models

Star-Corrector: A Multi-Turn Interactive Reinforcement Learning Framework for Lean4 Theorem Correction

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks