Xiaoran Liu (SII)

Xiaoran Liu (SII) on Hugging Face Daily Papers: 14 papers, 6 in the top 3 of their day, 741 upvotes.

  1. Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position 33 upvotes, #21 of 2026-10-08
  2. AI Can Learn Scientific Taste 397 upvotes, #1 of 2026-03-17
  3. Prism: Spectral-Aware Block-Sparse Attention 35 upvotes, #8 of 2026-02-11
  4. FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation 20 upvotes, #10 of 2026-02-02
  5. AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts 19 upvotes, #14 of 2026-01-30
  6. DiRL: An Efficient Post-Training Framework for Diffusion Language Models 19 upvotes, #12 of 2025-12-30
  7. Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs 55 upvotes, #2 of 2025-12-09
  8. SIM-CoT: Supervised Implicit Chain-of-Thought 35 upvotes, #2 of 2025-09-25
  9. Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction 9 upvotes, #11 of 2025-08-05
  10. LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs 43 upvotes, #4 of 2025-06-18
  11. Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache 20 upvotes, #5 of 2025-06-16
  12. Thus Spake Long-Context Large Language Model 66 upvotes, #2 of 2025-02-25
  13. VideoRoPE: What Makes for Good Video Rotary Position Embedding? 60 upvotes, #3 of 2025-02-10
  14. InternLM2 Technical Report 22 upvotes, #3 of 2024-03-27

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.