Zhijian Liu

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Fast-dLLM v2: Efficient Block-Diffusion LLM

3D Aware Region Prompted Vision Language Model

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory

Scaling RL to Long Videos

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity