AI models and papers trending on September 30, 2026
The edition of this day as it was recorded: the most upvoted papers of the daily list.
On Wednesday, September 30, 2026 the most upvoted paper was "Raven: The Harness of Harnesses for Composable Agentic Intelligence" from EverMind, with 515 votes. 11 of the 15 leading papers had a code repository attached. No model list exists for this day: Hugging Face does not publish past trending lists, and our collector had not started yet.
Papers only · rebuilt on 2026-10-03 09:16 UTC from the Hugging Face daily papers archive
Papers
- 515
Raven: The Harness of Harnesses for Composable Agentic Intelligence
EverMindarXiv 2609.33439 (opens in a new tab)Code (opens in a new tab)
- 400
MaLiang-Harness: A Programmable Path to Image and Video Generation
National University of SingaporearXiv 2609.34309 (opens in a new tab)Code (opens in a new tab)
- 372
In-Context Learning for Robots: Methods and Applications
Knowin AIarXiv 2609.36012 (opens in a new tab)Code (opens in a new tab)
- 309
Scaling Properties of Same-Family On-Policy Distillation
Zhejiang UniversityarXiv 2609.32722 (opens in a new tab)
- 282
Omni-IO Skills: Harnessing Your Agent Omni-Native
National University of SingaporearXiv 2609.31847 (opens in a new tab)Code (opens in a new tab)
- 159
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation
Zhejiang UniversityarXiv 2609.34759 (opens in a new tab)Code (opens in a new tab)
- 143
VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models
The University of MelbournearXiv 2609.32607 (opens in a new tab)Code (opens in a new tab)
- 127
LEGO-Anything: Coding Agents for 3D Scene Reconstruction
Amazon Web ServicesarXiv 2609.36380 (opens in a new tab)
- 123
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Tsinghua-LeapLabarXiv 2609.34981 (opens in a new tab)Code (opens in a new tab)
- 102
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Amazon SciencearXiv 2609.38155 (opens in a new tab)Code (opens in a new tab)
- 96
Think Before You Score: Thinking Reward Model for Visual Generation
arXiv 2609.37372 (opens in a new tab)Code (opens in a new tab)
- 94
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
ByteDance SeedarXiv 2609.36322 (opens in a new tab)
- 90
Follow the Entities: A Corpus Map for Agentic Search
- 89
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
meituanarXiv 2609.36601 (opens in a new tab)Code (opens in a new tab)
- 72
LLMs are General Asynchronous Agents
Yandex ResearcharXiv 2609.35427 (opens in a new tab)Code (opens in a new tab)
Models
No model list exists for this day. Hugging Face does not publish past trending lists, so days before the collector started carry papers only.
About the archive
How far back does the archive go?
Model lists exist from the first day the collector ran: Hugging Face does not publish past trending lists, so they cannot be rebuilt. Paper lists for earlier days were rebuilt from the Hugging Face daily papers archive, and those days are marked "papers only".
What is kept for each day?
The leading models with their task, likes and downloads on that day, the models held back, and the leading papers with their upvotes. Abstracts are not duplicated in the archive; each paper links to arXiv.
Do archived numbers change?
No. A day’s record is the last collection of that day and is not rewritten afterwards. Likes and downloads you see on an archived day are the values on that day, not today’s.
How are weeks defined?
ISO 8601 weeks: Monday to Sunday, numbered so that week 1 contains the first Thursday of the year. The address /week/2026-40 is week 40 of 2026.