BAIDU

BAIDU on Hugging Face Daily Papers: 14 papers, 1 in the top 3 of their day, 0 paper of the day.

1. Unlimited OCR Works 43 upvotes, #8 of 2026-06-23
2. Memento: Reconstruct to Remember for Consistent Long Video Generation 16 upvotes, #13 of 2026-06-16
3. DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning 6 upvotes, #31 of 2026-06-09
4. When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents 23 upvotes, #11 of 2026-06-08
5. MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation 17 upvotes, #16 of 2026-06-04
6. Native Audio-Visual Alignment for Generation 33 upvotes, #11 of 2026-05-29
7. EndPrompt: Efficient Long-Context Extension via Terminal Anchoring 15 upvotes, #18 of 2026-05-19
8. Measuring Maximum Activations in Open Large Language Models 18 upvotes, #16 of 2026-05-19
9. AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning 21 upvotes, #13 of 2026-05-11
10. Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs 13 upvotes, #11 of 2026-04-09
11. SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing 65 upvotes, #2 of 2026-03-20
12. Qianfan-OCR: A Unified End-to-End Model for Document Intelligence 145 upvotes, #5 of 2026-03-18
13. Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification 12 upvotes, #19 of 2026-02-04
14. MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions 5 upvotes, #11 of 2024-10-09

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.