AI models and papers trending on October 17, 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 17, 2026 the model at the top of the ranking was google/embeddinggemma-2 (feature extraction), with 151,258 downloads in 30 days and 2,525 likes. The most upvoted paper (from the daily list of October 16, 2026) was "Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation", with 660 votes. 15 of the 15 leading papers had a code repository attached.
Recorded 2026-10-17 07:00 UTC · numbers are those of that moment
Papers
- 660
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
arXiv 2610.21601 (opens in a new tab)Code (opens in a new tab)
- 572
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
VCLabarXiv 2610.18829 (opens in a new tab)Code (opens in a new tab)
- 307
OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
Tongyi-MAIarXiv 2610.22200 (opens in a new tab)Code (opens in a new tab)
- 280
FDE-Gym: The Last Mile of AI Delivery
DeepLethearXiv 2610.22350 (opens in a new tab)Code (opens in a new tab)
- 220
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
Mind LabarXiv 2610.22276 (opens in a new tab)Code (opens in a new tab)
- 200
RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
MAC-AutoMLarXiv 2610.17665 (opens in a new tab)Code (opens in a new tab)
- 192
Self-Evolving Agent Harness
ZGCAGIarXiv 2610.18813 (opens in a new tab)Code (opens in a new tab)
- 134
Learning Where to Split: Dynamic Band Splitting for Audio Source Separation
Tsinghua Machine Learning GrouparXiv 2610.14993 (opens in a new tab)Code (opens in a new tab)
- 117
InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views
zju3dvarXiv 2610.20341 (opens in a new tab)Code (opens in a new tab)
- 102
3DCodeVerse: Exploring 3D Worlds as Code
University of Southern CaliforniaarXiv 2610.22341 (opens in a new tab)Code (opens in a new tab)
- 96
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
Tongyi-MAIarXiv 2610.20939 (opens in a new tab)Code (opens in a new tab)
- 88
Behavioral Compositionality of Sparse Autoencoder Representations
OpenSAEarXiv 2610.21261 (opens in a new tab)Code (opens in a new tab)
- 77
SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation
University of RochesterarXiv 2610.22264 (opens in a new tab)Code (opens in a new tab)
- 76
Speculative Forcing for Efficient Autoregressive Video Generation
NAVER AI LabarXiv 2610.22347 (opens in a new tab)Code (opens in a new tab)
- 54
VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models
ZJU-OmniAIarXiv 2610.21306 (opens in a new tab)Code (opens in a new tab)
Models
- 1
Feature extraction · 151K downloads / 30 d · 2,525 likes
- 2
Text generation · 85.6K downloads / 30 d · 1,842 likes
- 3
openbmb/MiniCPM-V-4.7-35B-A3B (opens in a new tab)
Image text to text · 17.6K downloads / 30 d · 859 likes
- 4
Text to speech · 6,158 downloads / 30 d · 566 likes
- 5
Qwen/Qwen-Image-2.1-Turbo (opens in a new tab)
Text to image · 17.4K downloads / 30 d · 948 likes
- 6
Image to video · 1.92M downloads / 30 d · 8,114 likes
- 7
abenzerps/Qwen-Image-2.1-Uncensored-Quantized
Text to image · 2.48M downloads / 30 d · 4,451 likes
- 8
meta-models/Muse-Spark-Open-816B-A42B
Image text to text · 815 downloads / 30 d · 457 likes
- 9
LiquidAI/LFM2.5-24B-A2B (opens in a new tab)
Text generation · 9,356 downloads / 30 d · 436 likes
- 10
black-forest-labs/flux-3-image-klein-comfy
Image to image · 73.8K downloads / 30 d · 489 likes
- 11
black-forest-labs/flux-3-image-klein
Image to image · 22.8K downloads / 30 d · 411 likes
- 12
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF (opens in a new tab)
Text to image · 328K downloads / 30 d · 521 likes
- 13
baidu/Unlimited-OCR (opens in a new tab)
Image text to text · 1.26M downloads / 30 d · 4,755 likes
- 14
Image text to text · 7.52M downloads / 30 d · 17.9K likes
- 15
openbmb/MiniCPM-V-4.7-1B (opens in a new tab)
Image text to text · 8,822 downloads / 30 d · 369 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.