Yuxin Zhang

Out of the Memory Barrier: A Highly Memory-Efficient Training System for LLMs with Million-Token Contexts

Test-Time Iterative Error Correction for Efficient Diffusion Models

HS-SFT: Hybrid Sparse Supervised Fine-tuning for Offline LLM KV Cache Eviction

RoPK: A Head-Level Key Cache Channel Pruning Method for Efficient Long-Context LLM Inference

FOLD: Fast Correct Speculative Decoding

Continuous Test-Time Adaptation of Vision-Language Models

Beyond Proxy Metrics: A New Evaluation Framework for LLM Compression by Directly Measuring Generative Faithfulness

Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective

BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training

GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models

Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective

Dynamic Low-Rank Sparse Adaptation for Large Language Models

BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

Multi-Perspective Test-Time Prompt Tuning for Global, Local Visuals, and Language

Towards Efficient Automatic Self-Pruning of Large Language Models