dots studio

dots studio on Hugging Face Daily Papers: 9 papers, 4 in the top 3 of their day, 2 paper of the day.

1. VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World? 17 upvotes, #7 of 2026-08-12
2. xHC: Expanded Hyper-Connections 56 upvotes, #5 of 2026-07-20
3. VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild 15 upvotes, #24 of 2026-05-28
4. Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information 191 upvotes, #1 of 2026-05-20
5. Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning 204 upvotes, #1 of 2026-03-12
6. VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training 215 upvotes, #2 of 2026-02-23
7. REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents 23 upvotes, #5 of 2026-02-17
8. DeepEyesV2: Toward Agentic Multimodal Model 38 upvotes, #3 of 2025-11-10
9. Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning? 6 upvotes, #24 of 2025-10-08

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.