Sai Rajeswar

Sai Rajeswar on Hugging Face Daily Papers: 18 papers, 4 in the top 3 of their day, 786 upvotes.

  1. SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding 70 upvotes, #4 of 2026-07-15
  2. Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics 60 upvotes, #6 of 2026-05-13
  3. Therefore I am. I Think 30 upvotes, #9 of 2026-04-03
  4. Terminal Agents Suffice for Enterprise Automation 92 upvotes, #2 of 2026-04-02
  5. VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing 6 upvotes, #28 of 2026-04-01
  6. CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents 92 upvotes, #1 of 2026-03-26
  7. EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings 142 upvotes, #5 of 2026-03-17
  8. Grounding Computer Use Agents on Human Demonstrations 98 upvotes, #1 of 2025-11-11
  9. Apriel-1.5-15b-Thinker 106 upvotes, #1 of 2025-10-06
  10. Optimizing What Matters: AUC-Driven Learning for Robust Neural Retrieval 2 upvotes, #45 of 2025-10-03
  11. AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs 21 upvotes, #11 of 2025-09-12
  12. The Promise of RL for Autoregressive Image Editing 11 upvotes, #9 of 2025-08-06
  13. Rendering-Aware Reinforcement Learning for Vector Graphics Generation 11 upvotes, #33 of 2025-05-28
  14. Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA 2 upvotes, #41 of 2025-05-26
  15. AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding 33 upvotes, #5 of 2025-02-04
  16. BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks 8 upvotes, #13 of 2024-12-09
  17. RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content 14 upvotes, #10 of 2024-06-19
  18. VCR: Visual Caption Restoration 10 upvotes, #16 of 2024-06-13

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.