Zhangchen Xu

Zhangchen Xu on Hugging Face Daily Papers: 11 papers, 2 in the top 3 of their day, 353 upvotes.

1. AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks? 29 upvotes, #7 of 2026-06-04
2. Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty? 11 upvotes, #18 of 2026-05-14
3. Emergent Social Intelligence Risks in Generative Multi-Agent Systems 50 upvotes, #4 of 2026-03-31
4. Building a Foundational Guardrail for General Agentic Systems via Synthetic Data 26 upvotes, #12 of 2025-10-14
5. TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments 24 upvotes, #12 of 2025-10-03
6. VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL 9 upvotes, #22 of 2025-06-03
7. TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning 12 upvotes, #22 of 2025-05-23
8. KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding 26 upvotes, #4 of 2025-03-06
9. Small Models Struggle to Learn from Strong Reasoners 27 upvotes, #7 of 2025-02-20
10. Stronger Models are NOT Stronger Teachers for Instruction Tuning 27 upvotes, #1 of 2024-11-13
11. Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing 42 upvotes, #2 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.