Chen Wei

HippoTune: A Hippocampal Associative Loop–Inspired Fine-Tuning Method for Continual Learning

ChainGPT: Dual-Reasoning Model with Recurrent Depth and Multi-Rank State Updates

MoCa: Modeling Object Consistency for 3D Camera Control in Video Generation

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model

SMAR: Soft Modality-Aware Routing Strategy for MoE-based Multimodal Large Language Models Preserving Language Capabilities

MoB: Mixture of Block Transformer for Accelerating Video Generation with Dynamic Routing

TAMP: Task-aware Multimodal Pre-Interaction for fine-grained Large Language Models

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference

Dense2MoE: Unifying Pruning and Upcycling for Efficient Large Language Models

Your Large Reasoning Models Can Be Safer on Its Own

COPO: Consistency-Aware Policy Optimization

Toward Balanced Continual Learning via Fine-Grained Neuronal Intervention Inspired by Memory Consolidation

Learning to Plan Like the Human Brain via Visuospatial Perception and Semantic-Episodic Synergistic Decision-Making

EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation

Test-time Zero-shot Recognition with Good Attributes