Siyuan Li

Siyuan Li on Hugging Face Daily Papers: 18 papers, 5 in the top 3 of their day, 811 upvotes.

  1. OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers 75 upvotes, #1 of 2026-07-07
  2. PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams 13 upvotes, #22 of 2026-06-08
  3. RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution 18 upvotes, #13 of 2026-05-25
  4. PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control 16 upvotes, #16 of 2026-05-18
  5. PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents 32 upvotes, #7 of 2026-05-12
  6. NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation 13 upvotes, #20 of 2026-05-12
  7. Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists 47 upvotes, #4 of 2026-05-01
  8. Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora 90 upvotes, #2 of 2026-04-29
  9. The Trinity of Consistency as a Defining Principle for General World Models 194 upvotes, #1 of 2026-02-27
  10. Thinking with Drafting: Optical Decompression via Logical Reconstruction 32 upvotes, #9 of 2026-02-13
  11. MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging 8 upvotes, #15 of 2025-11-24
  12. GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models 31 upvotes, #4 of 2025-11-17
  13. MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding 14 upvotes, #17 of 2025-10-28
  14. Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning 38 upvotes, #5 of 2025-07-29
  15. Taming LLMs by Scaling Learning Rates with Gradient Grouping 36 upvotes, #4 of 2025-06-03
  16. MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization 78 upvotes, #1 of 2025-04-03
  17. Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning 33 upvotes, #8 of 2024-10-10
  18. Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts 22 upvotes, #2 of 2024-05-31

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.