siqi zhu

siqi zhu on Hugging Face Daily Papers: 11 papers, 2 in the top 3 of their day, 544 upvotes.

1. From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation 0 upvotes, #46 of 2026-10-05
2. Agents' Last Exam 345 upvotes, #1 of 2026-06-09
3. The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes 5 upvotes, #41 of 2026-05-13
4. Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages 3 upvotes, #46 of 2026-05-11
5. Agentic AI Systems Should Be Designed as Marginal Token Allocators 4 upvotes, #18 of 2026-05-05
6. OpenTinker: Separating Concerns in Agentic Reinforcement Learning 5 upvotes, #20 of 2026-01-13
7. Multi-Agent Evolve: LLM Self-Improve through Co-evolution 8 upvotes, #18 of 2025-10-28
8. GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare 2 upvotes, #37 of 2025-10-13
9. Efficiently Serving LLM Reasoning Programs with Certaindex 31 upvotes, #4 of 2024-12-31
10. Efficient LLM Scheduling by Learning to Rank 14 upvotes, #7 of 2024-08-29
11. LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs 60 upvotes, #1 of 2024-08-14

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.