Lixuan He

Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers

Towards a Unified View of Large Language Model Post-Training

Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

VISA: Preserving Fine-Grained Perception in MLLMs via Visual Semantic Anchoring

MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering

Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Memory System

Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm