Ligong Han

Towards Generalizable Implicit In-Context Learning with Attention Routing

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

Re-Meanflow: Efficient One-Step Generative Modeling via Meanflow on Rectified Trajectories

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization

Implicit In-context Learning

SQuat: Subspace-orthogonal KV Cache Quantization

LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation

Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

Discrete Inversion: A Controllable Latent Space for Multinomial Diffusion and Masked Generative Models