Yujun Lin

Yujun Lin on Hugging Face Daily Papers: 12 papers, 2 in the top 3 of their day, 530 upvotes.

  1. Flash-KMeans: Fast and Memory-Efficient Exact K-Means 78 upvotes, #3 of 2026-03-12
  2. Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization 33 upvotes, #8 of 2026-02-05
  3. Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow 21 upvotes, #6 of 2026-01-26
  4. VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference 23 upvotes, #13 of 2025-12-02
  5. QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs 164 upvotes, #1 of 2025-10-14
  6. DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder 33 upvotes, #8 of 2025-10-01
  7. DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space 6 upvotes, #48 of 2025-09-30
  8. Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation 36 upvotes, #4 of 2025-07-02
  9. Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation 38 upvotes, #12 of 2025-05-28
  10. LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention 12 upvotes, #15 of 2025-02-21
  11. SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer 16 upvotes, #9 of 2025-01-31
  12. SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models 15 upvotes, #13 of 2024-11-08

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.