Kam-Fai Wong

Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents

EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget

Teaching Language Model to Act Efficiently

RT-Remover: A Real-Time Video Object Removal by Composing Tracking and Removal in Auto-Regressive Diffusion Transformers

WebAggregator: Scaling Complex Logical Information Aggregation for Web Agents Foundation Models

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning

Hybrid Attribution Priors for Explainable and Robust Model Training

Meta-Memory for Large Language Models

Distortion-free Watermarking for Large Language Models via Adaptive Top-$p$ Sampling

MiniMax-Remover: Taming Bad Noise Helps Video Object Removal

Beyond Two-Stage Training: Integrating SFT and RL for Improved Reasoning in LLMs

Centrality-guided Pre-training for Graph

PEARL: Towards Permutation-Resilient LLMs

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Enhance Graph Contrastive Learning with Perturbation Discrimination