Zhijian Liu

Zhijian Liu on Hugging Face Daily Papers: 16 papers, 7 in the top 3 of their day, 932 upvotes.

  1. DFlash: Block Diffusion for Flash Speculative Decoding 41 upvotes, #5 of 2026-02-06
  2. VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference 23 upvotes, #13 of 2025-12-02
  3. OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM 79 upvotes, #2 of 2025-10-20
  4. KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems 2 upvotes, #31 of 2025-10-16
  5. Fast-dLLM v2: Efficient Block-Diffusion LLM 47 upvotes, #5 of 2025-10-08
  6. 3D Aware Region Prompted Vision Language Model 12 upvotes, #9 of 2025-09-17
  7. Scaling RL to Long Videos 132 upvotes, #1 of 2025-07-11
  8. SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity 17 upvotes, #8 of 2025-07-01
  9. Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding 39 upvotes, #6 of 2025-05-30
  10. Token-Efficient Long Video Understanding for Multimodal LLMs 79 upvotes, #2 of 2025-03-07
  11. LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention 12 upvotes, #15 of 2025-02-21
  12. NVILA: Efficient Frontier Visual Language Models 47 upvotes, #3 of 2024-12-06
  13. LongVILA: Scaling Long-Context Visual Language Models for Long Videos 50 upvotes, #1 of 2024-08-20
  14. StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation 75 upvotes, #1 of 2023-12-21
  15. Point Transformer V3: Simpler, Faster, Stronger 21 upvotes, #6 of 2023-12-18
  16. LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models 90 upvotes, #1 of 2023-09-22

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.