AI models and papers trending on October 13, 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 Tuesday, October 13, 2026 the model at the top of the ranking was google/embeddinggemma-2 (feature extraction), with 115,763 downloads in 30 days and 1,979 likes. The most upvoted paper was "Scaling Agentic Data for Long-Horizon Terminal Intelligence" from alibaba, with 65 votes. 12 of the 14 leading papers had a code repository attached.
Recorded 2026-10-13 07:04 UTC · numbers are those of that moment
Papers
- 65
Scaling Agentic Data for Long-Horizon Terminal Intelligence
- 53
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
XPENG AIarXiv 2609.39601 (opens in a new tab)Code (opens in a new tab)
- 30
Multi-Stream Attention Residuals
Shanghai Jiao Tong UniversityarXiv 2610.13630 (opens in a new tab)Code (opens in a new tab)
- 29
AgentSWE: Can Coding Agents Build the Agent You Actually Want?
- 18
Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents
Nanyang Technological UniversityarXiv 2609.33304 (opens in a new tab)Code (opens in a new tab)
- 16
Thinking Inertia: LLMs Keep Thinking When Told Not To
Stanford UniversityarXiv 2610.11765 (opens in a new tab)Code (opens in a new tab)
- 14
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
XPENG AIarXiv 2609.39600 (opens in a new tab)Code (opens in a new tab)
- 14
SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
Shanghai AI LaboratoryarXiv 2610.13832 (opens in a new tab)Code (opens in a new tab)
- 9
Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method
Shanghai Jiao Tong UniversityarXiv 2609.35965 (opens in a new tab)Code (opens in a new tab)
- 7
T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images
Preferred Networks, Inc.arXiv 2610.03308 (opens in a new tab)Code (opens in a new tab)
- 3
ARCS: Towards Precise Text-to-SQL via Structured Disambiguation
Megagon LabsarXiv 2610.09396 (opens in a new tab)Code (opens in a new tab)
- 2
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
Nanjing UniversityarXiv 2610.12933 (opens in a new tab)Code (opens in a new tab)
- 1
VIS-Ground: Video Interactive Storytelling with Contextual Grounding
GooglearXiv 2610.09326 (opens in a new tab)Code (opens in a new tab)
- 1
SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code
University of California at San DiegoarXiv 2610.09116 (opens in a new tab)Code (opens in a new tab)
Models
- 1
Feature extraction · 116K downloads / 30 d · 1,979 likes
- 2
Text generation · 46.1K downloads / 30 d · 1,358 likes
- 3
Qwen/Qwen-Image-2.1-Turbo (opens in a new tab)
Text to image · 6,787 downloads / 30 d · 660 likes
- 4
abenzerps/Qwen-Image-2.1-Uncensored-Quantized
Text to image · 2.19M downloads / 30 d · 4,128 likes
- 5
Cloudflare/clef (opens in a new tab)
Image text to text · 15.1K downloads / 30 d · 2,105 likes
- 6
Image to video · 1.72M downloads / 30 d · 7,514 likes
- 7
ConwayResearch/Underdog-Saluki-27B-1.0 (opens in a new tab)
Text generation · 242K downloads / 30 d · 382 likes
- 8
Image text to text · 6.9M downloads / 30 d · 17.6K likes
- 9
LiquidAI/d1-3B (opens in a new tab)
Image text to text · 11.9K downloads / 30 d · 356 likes
- 10
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF (opens in a new tab)
Text to image · 162K downloads / 30 d · 380 likes
- 11
canberkkkkkk/ema-lightning (opens in a new tab)
Text to speech · 20.3K downloads / 30 d · 395 likes
- 12
Image text to text · 75.3K downloads / 30 d · 289 likes
- 13
unsloth/embeddinggemma-2-GGUF (opens in a new tab)
Feature extraction · 71.9K downloads / 30 d · 285 likes
- 14
Venastine-Research/Xing4.0-29B-A4B-GGUF (opens in a new tab)
Text generation · 52.8K downloads / 30 d · 707 likes
- 15
convaiinnovations/laya (opens in a new tab)
Text classification · 45.1K downloads / 30 d · 5,541 likes
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.