Junrulu

Junrulu on Hugging Face Daily Papers: 10 papers, 1 in the top 3 of their day, 408 upvotes.

  1. On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer 16 upvotes, #13 of 2026-11-06
  2. HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs 33 upvotes, #22 of 2026-10-20
  3. Self-Distillation with Verbal Regularization 39 upvotes, #29 of 2026-10-14
  4. ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL 27 upvotes, #13 of 2026-08-31
  5. Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge 19 upvotes, #14 of 2026-08-31
  6. Toward Native Multimodal Modeling: A Roadmap 42 upvotes, #6 of 2026-05-26
  7. Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis 41 upvotes, #8 of 2026-05-19
  8. Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision 41 upvotes, #4 of 2026-01-28
  9. Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models 119 upvotes, #2 of 2026-01-01
  10. SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space 26 upvotes, #11 of 2025-11-26

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.