AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic hub

Hugging Face

Hugging Face is the GitHub of machine learning — the platform hosting millions of open models, datasets and demos. Its Transformers library and open leaderboards made it the center of gravity for open-source AI. All our Hugging Face coverage lives on this page.

Official site ↗262 articles
In the glossary:Foundation ModelFine-tuningMachine Learning
OPST: A Model Fine-Tunes Itself on Its Own Questions, No Humans Required
LLM·Hugging Face Daily Papers

OPST: A Model Fine-Tunes Itself on Its Own Questions, No Humans Required

Oct 23, 2026·3 min
New Algorithm Finds Nash Equilibrium in 5,600 Games to 1e-5 Precision
LLM

New Algorithm Finds Nash Equilibrium in 5,600 Games to 1e-5 Precision

Oct 23, 2026·3 min
NX-AI's KronLSTM Changes the Delta Rule and Stabilizes Memory Without Normalization
LLM

NX-AI's KronLSTM Changes the Delta Rule and Stabilizes Memory Without Normalization

Oct 22, 2026·2 min
SpecMRL Improves Matryoshka Embeddings: Half the Dimensions Beat Full MRL
LLM

SpecMRL Improves Matryoshka Embeddings: Half the Dimensions Beat Full MRL

Oct 22, 2026·2 min
Manga2Animate: A Multi-Agent System Turns Manga Into Anime Through a Script and a Storyboard
LLM·Hugging Face Daily Papers

Manga2Animate: A Multi-Agent System Turns Manga Into Anime Through a Script and a Storyboard

Manga2Animate splits manga adaptation into two steps: a script and a storyboard. A creator agent produces each one, and a reviewer agent checks it against the…

Oct 22, 2026·2 min
Study: Overfitting and Extra Compute Eat 68% of the Gains from Harness Evolution
LLM·Hugging Face Daily Papers

Study: Overfitting and Extra Compute Eat 68% of the Gains from Harness Evolution

The new HDA protocol broke down automated agent-optimization gains across 11 models: on average, overfitting accounts for 54% and test-time scaling for 14%, while…

Oct 22, 2026·2 min
Researchers Test 16 Types of Hints for OPSD and Find a Selection Metric
LLM·Hugging Face Daily Papers

Researchers Test 16 Types of Hints for OPSD and Find a Selection Metric

16 privileged-information configs, 3 agentic benchmarks, 3 models: KL metrics predict how much a hint will help OPSD better than directly testing the hint's…

Oct 22, 2026·3 min
Researchers personalize three MoE LLMs and find the experts responsible for adaptation
LLM·Hugging Face Daily Papers

Researchers personalize three MoE LLMs and find the experts responsible for adaptation

Researchers fine-tuned three open MoE models on a personalization dataset and used crosscoders to isolate experts that encode individual user features.

Oct 22, 2026·2 min
Top themes
01ACT3D teaches a VLM to explore 3D scenes and beats Gemini 3.6 Flash: 53.2% across six benchmarksOct 22, 2026·2 min02Intact cuts prompt injection success in browser agents from 73.1% to 12.8%Oct 22, 2026·2 min03Anthropic lets six METR auditors into its office, with the right to publish reports without a vetoOct 22, 2026·3 min04A no-hair theorem for transformers: the prompt is forgotten as t^-α, α≈0.55–0.7Oct 22, 2026·2 min05MIST shows video world models don't forget; they fail to carry out the commandOct 22, 2026·2 min
"Wait" in Reasoning Models Turns Out to Be Inherited from Data, Not Discovered by RL
LLM·Hugging Face Daily Papers

"Wait" in Reasoning Models Turns Out to Be Inherited from Data, Not Discovered by RL

Oct 22, 2026·3 min
DeepSeek releases V4.1-Flash-1017 and opens its Search API at $0.75 per 1000 calls
LLM·DeepSeek Blog

DeepSeek releases V4.1-Flash-1017 and opens its Search API at $0.75 per 1000 calls

Oct 22, 2026·2 min
Researchers Annotate 2,122 WildChat Conversations: 71.1% of Legal Chats Seek Personal Advice
LLM·Hugging Face Daily Papers

Researchers Annotate 2,122 WildChat Conversations: 71.1% of Legal Chats Seek Personal Advice

Oct 22, 2026·2 min
Changing the definition of "unsafe" moves a guardrail score from 0 to 100 with 0.03% of weights
LLM·Hugging Face Daily Papers

Changing the definition of "unsafe" moves a guardrail score from 0 to 100 with 0.03% of weights

Oct 22, 2026·3 min
Researchers Propose Anti-Persistence: LLM Agent Memory Without Stored Rules
LLM·Hugging Face Daily Papers

Researchers Propose Anti-Persistence: LLM Agent Memory Without Stored Rules

A new memory design for LLM agents stores trajectories and outcomes, then rebuilds guidance from scratch for each task. It uses the fewest LLM calls of the designs…

Oct 22, 2026·2 min
3D Scene Generation: DiT Works in a 3D Latent and Encodes a Scene in 1K Tokens
LLM·Hugging Face Daily Papers

3D Scene Generation: DiT Works in a 3D Latent and Encodes a Scene in 1K Tokens

Researchers move scene diffusion from 2D views into an implicit 3D latent space built on DINOv2, SigLIP2 and DA3. Per the paper's title, a scene fits in roughly 1K…

Oct 22, 2026·2 min
T2Quant Reallocates Precision Across Diffusion LLM Steps: Up to +6.7 pp
LLM·Hugging Face Daily Papers

T2Quant Reallocates Precision Across Diffusion LLM Steps: Up to +6.7 pp

Researchers propose T2Quant, which quantizes diffusion language models by varying activation bit-width per denoising step, adding up to 6.7 pp accuracy at the same bit budget.

Oct 22, 2026·2 min
UserArena: A 64 729-Session Benchmark Tests Whether Shoppers Can Be Simulated
LLM·Hugging Face Daily Papers

UserArena: A 64 729-Session Benchmark Tests Whether Shoppers Can Be Simulated

Oct 22, 2026·3 min
HiSTEVE 1.0 Plays Minecraft With a Mouse and Keyboard: 85.0% on MineStudio Bench
LLM·Hugging Face Daily Papers

HiSTEVE 1.0 Plays Minecraft With a Mouse and Keyboard: 85.0% on MineStudio Bench

Oct 22, 2026·3 min
Dual Exam: GPT 6 Astra Scores 31.3 Among Multimodal Agents
LLM·Hugging Face Daily Papers

Dual Exam: GPT 6 Astra Scores 31.3 Among Multimodal Agents

Oct 22, 2026·3 min
MMVistaReason: Open Recipe Trains a 4B Model That Beats Qwen3.5-9B on 15 Benchmarks
LLM·Hugging Face Daily Papers

MMVistaReason: Open Recipe Trains a 4B Model That Beats Qwen3.5-9B on 15 Benchmarks

Oct 22, 2026·3 min
Survey by Shengqiong Wu and Hao Fei: 600+ Papers on Video Models as World Models
LLM·Hugging Face Daily Papers

Survey by Shengqiong Wu and Hao Fei: 600+ Papers on Video Models as World Models

Oct 22, 2026·3 min
UCLA Team Pushes the Speed–Quality Frontier in Speculative Diffusion With Two Knobs
LLM

UCLA Team Pushes the Speed–Quality Frontier in Speculative Diffusion With Two Knobs

Oct 22, 2026·3 min
PaperFormalizer Turns LaTeX Papers into Verified Lean Code, with the Author in the Loop
LLM

PaperFormalizer Turns LaTeX Papers into Verified Lean Code, with the Author in the Loop

Oct 22, 2026·2 min
OPTIC compresses Gemma 4 E4B's per-layer embeddings 100x while keeping 97.8% of quality
LLM

OPTIC compresses Gemma 4 E4B's per-layer embeddings 100x while keeping 97.8% of quality

Oct 22, 2026·3 min
Nestor: nested sparsity in attention beats MoE at equal compute
LLM·Hugging Face Daily Papers

Nestor: nested sparsity in attention beats MoE at equal compute

Tianzhe Chu, Druv Pai, and Yi Ma propose the Nestor transformer: attention sparsity nests inside MoE, delivering gains at equal compute and in continual pretraining.

Oct 22, 2026·3 min
A 17-million-parameter encoder picks the right tool in 14ms on CPU
LLM·Hugging Face Daily Papers

A 17-million-parameter encoder picks the right tool in 14ms on CPU

Tardelli Stekel has released six open encoders ranging from 17M to 1B parameters for closed-set selection. The 68M and 150M models beat the 435M DeBERTa-v3 by 4.9…

Oct 22, 2026·3 min