Miao Zhang

Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation

Boost Post-Training Quantization via Null Space Optimization for Large Language Models

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting

CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning

Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression

Enhancing GUI Agent with Uncertainty-Aware Self-Trained Evaluator

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning

SFi-Former: Sparse Flow induced Attention for Graph Transformer