AI models and papers trending on October 10, 2026
The edition of this day as it was recorded: models with the likes and downloads they had then, and the most upvoted papers of the daily list.
On Saturday, October 10, 2026 the model at the top of the ranking was google/embeddinggemma-2 (feature extraction), with 45,605 downloads in 30 days and 1,488 likes. 2 models were held back for having likes without downloads. The most upvoted paper (from the daily list of October 9, 2026) was "AgentGarten: Code Worlds for Evolving Agents" from MirroS, with 145 votes. 12 of the 15 leading papers had a code repository attached.
Recorded 2026-10-10 21:12 UTC · numbers are those of that moment
Papers
- 145
AgentGarten: Code Worlds for Evolving Agents
MirroSarXiv 2610.12374 (opens in a new tab)Code (opens in a new tab)
- 131
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
National University of SingaporearXiv 2610.08215 (opens in a new tab)Code (opens in a new tab)
- 123
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Tsinghua-NICS-EFCarXiv 2610.12242 (opens in a new tab)Code (opens in a new tab)
- 101
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Nanyang Technological University SingaporearXiv 2610.06100 (opens in a new tab)Code (opens in a new tab)
- 66
SuperNav: An Agentic Navigation System for Any Task in Any Scene
zju3dvarXiv 2610.12126 (opens in a new tab)Code (opens in a new tab)
- 65
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Xiaomi MiMoarXiv 2610.11959 (opens in a new tab)
- 47
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
KAIST AIarXiv 2610.12299 (opens in a new tab)Code (opens in a new tab)
- 43
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
arXiv 2609.38173 (opens in a new tab)Code (opens in a new tab)
- 35
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
Alaya LabarXiv 2610.12461 (opens in a new tab)Code (opens in a new tab)
- 34
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
The University of Hong KongarXiv 2610.12421 (opens in a new tab)Code (opens in a new tab)
- 34
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
arXiv 2610.12468 (opens in a new tab)Code (opens in a new tab)
- 33
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
Multimodal AI Lab - Technical University of DarmstadtarXiv 2610.09087 (opens in a new tab)Code (opens in a new tab)
- 33
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Tencent HunyuanarXiv 2610.06801 (opens in a new tab)Code (opens in a new tab)
- 30
TestPrism: Rethinking Test Evaluation Beyond a Single Reference
NJU-LINK LabarXiv 2610.12289 (opens in a new tab)
- 28
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
University College LondonarXiv 2610.11794 (opens in a new tab)
Models
- 1
Feature extraction · 45.6K downloads / 30 d · 1,488 likes
- 2
Cloudflare/clef (opens in a new tab)
Image text to text · 13.6K downloads / 30 d · 1,982 likes
- 3
Text generation · 33.7K downloads / 30 d · 940 likes
- 4
abenzerps/Qwen-Image-2.1-Uncensored-GGUF (opens in a new tab)
Text to image · 2.1M downloads / 30 d · 3,859 likes
- 5
Aleph-Alpha/Kolibri-1 (opens in a new tab)
Text generation · 10.5K downloads / 30 d · 859 likes
- 6
Venastine-Research/Xing4.0-29B-A4B-GGUF (opens in a new tab)
Text generation · 45.2K downloads / 30 d · 679 likes
- 7
Image to video · 1.72M downloads / 30 d · 7,159 likes
- 8
Qwen/Qwen-Image-2.1-Turbo (opens in a new tab)
Text to image · 2,138 downloads / 30 d · 433 likes
- 9
Image text to text · 6.77M downloads / 30 d · 17.4K likes
- 10
Cloudflare/clef-flash (opens in a new tab)
Image text to text · 20.7K downloads / 30 d · 729 likes
- 11
canberkkkkkk/ema-lightning (opens in a new tab)
Text to speech · 15.7K downloads / 30 d · 333 likes
- 12
convaiinnovations/laya (opens in a new tab)
Text classification · 42.9K downloads / 30 d · 5,456 likes
- 13
Cactus-Compute/whistle (opens in a new tab)
Automatic speech recognition · 12.8K downloads / 30 d · 302 likes
- 14
ConwayResearch/Underdog-Saluki-27B-1.0 (opens in a new tab)
Text generation · 59.2K downloads / 30 d · 265 likes
- 15
LiquidAI/d1-3B (opens in a new tab)
Image text to text · 9,088 downloads / 30 d · 260 likes
- FrancisRing/Prism · 145 likes, 0 downloads
- ausboss/Qwen-Image-2.1-Outfit-Swap-Consistency-LoRA · 113 likes, 0 downloads
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.