AI models and papers trending on October 16, 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 Friday, October 16, 2026 the model at the top of the ranking was google/embeddinggemma-2 (feature extraction), with 144,280 downloads in 30 days and 2,431 likes. The most upvoted paper was "OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding" from VCLab, with 129 votes. 14 of the 15 leading papers had a code repository attached.
Recorded 2026-10-16 07:00 UTC · numbers are those of that moment
Papers
- 129
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)
- 104
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
- 68
Self-Evolving Agent Harness
ZGCAGIarXiv 2610.18813 (opens in a new tab)Code (opens in a new tab)
- 58
Speculative Forcing for Efficient Autoregressive Video Generation
NAVER AI LabarXiv 2610.22347 (opens in a new tab)Code (opens in a new tab)
- 45
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)
- 44
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)
- 36
3DCodeVerse: Exploring 3D Worlds as Code
University of Southern CaliforniaarXiv 2610.22341 (opens in a new tab)Code (opens in a new tab)
- 28
Orbia: Do Generated Videos Form a Consistent 3D World?
TencentarXiv 2610.20693 (opens in a new tab)Code (opens in a new tab)
- 26
Mosaic: Multi-Session Agentic Reinforcement Learning
LARK Lab@HKUST (GZ)arXiv 2610.22174 (opens in a new tab)Code (opens in a new tab)
- 25
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
ByteDancearXiv 2610.19849 (opens in a new tab)Code (opens in a new tab)
- 25
Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation
Shanghai AI LaboratoryarXiv 2610.20818 (opens in a new tab)Code (opens in a new tab)
- 24
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)
- 23
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)
- 22
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)
- 21
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
arXiv 2610.22344 (opens in a new tab)Code (opens in a new tab)
Models
- 1
Feature extraction · 144K downloads / 30 d · 2,431 likes
- 2
Text generation · 75.3K downloads / 30 d · 1,766 likes
- 3
Qwen/Qwen-Image-2.1-Turbo (opens in a new tab)
Text to image · 15.3K downloads / 30 d · 896 likes
- 4
openbmb/MiniCPM-V-4.7-35B-A3B (opens in a new tab)
Image text to text · 9,278 downloads / 30 d · 804 likes
- 5
abenzerps/Qwen-Image-2.1-Uncensored-Quantized
Text to image · 2.42M downloads / 30 d · 4,399 likes
- 6
Text to speech · 4,048 downloads / 30 d · 497 likes
- 7
Image to video · 1.87M downloads / 30 d · 7,976 likes
- 8
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF (opens in a new tab)
Text to image · 296K downloads / 30 d · 502 likes
- 9
LiquidAI/LFM2.5-24B-A2B (opens in a new tab)
Text generation · 6,286 downloads / 30 d · 396 likes
- 10
baidu/Unlimited-OCR (opens in a new tab)
Image text to text · 1.16M downloads / 30 d · 4,716 likes
- 11
Image text to text · 7.36M downloads / 30 d · 17.8K likes
- 12
ConwayResearch/Underdog-Saluki-27B-1.0 (opens in a new tab)
Text generation · 344K downloads / 30 d · 502 likes
- 13
Image text to text · 149K downloads / 30 d · 372 likes
- 14
meta-models/Muse-Spark-Open-816B-A42B
Image text to text · 402 downloads / 30 d · 314 likes
- 15
black-forest-labs/flux-3-image-klein
Image to image · 3,241 downloads / 30 d · 289 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.