autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training
autotrust
• • 126Community Blog & Articles
Community Articles
view all
Impactful scheduling for GPU clusters
29
October 9, 2026 
ml-interndatasetsspaces
The model that didn't exist, so you made it yourself
43
October 8, 2026 
Multimodal open d1 decision models for the edge
35
October 7, 2026 
Introducing Falcon ASR
18
October 7, 2026 
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
19
October 7, 2026 
The Agent Said It Was Done. The Database Disagreed.
72
October 3, 2026 
AutoSynthData: Generating Training Data for Enterprise Agents
48
October 2, 2026 
audiospeechleaderboard
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
63
September 30, 2026 
Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents
22
September 29, 2026 
Holo4: powering generalist computer-use agents
89
September 28, 2026 
rldatasetshub
Welcome RL Environments to the hub
- +4
35
September 28, 2026 
evaluationresearchcommunity
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
- +5
29
September 22, 2026 
transformersggufkernels
Transformers now runs llama.cpp quants
111
September 22, 2026 
mlxopen-sourcecommunity
Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community
- +1
93
September 22, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training
autotrust
• • 126LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model
lightonai
• • 29Falcon OCR Arabic: 270M Parameters State-of-the-Art Arabic OCR
tiiuae
• • 28Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance
tiiuae
• • 29Carbon-A: Finding genes in known and unknown genomes
HuggingFaceBio
• • 23New in llama.cpp: Decision Models
ggml-org
• • 95Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration
FINAL-Bench
• • 12NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
nvidia
• • 89The Open Quantum Challenge: Quantum Simulation and QEC Decoding on Classical GPUs
FINAL-Bench
• • 11autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model
autotrust
• • 48Sparseup-fr: A French replication of Linkup's sparse embedding model
alphaedge-ai
• • 9ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third
lightonai
• • 8Open-sourcing AstaBrief, the fast report-generation model in Asta
allenai
• • 28Universal Modder: A Practical Guide to AI Game Modding
a2aprotocol
• • 8Six Questions to Ask a LeRobot Dataset Before You Train
harpreetsahota
• • 6Leading the System One Mosaic Benchmark: What Darwin-27B-ZTC-v2's #1 Means
FINAL-Bench
• • 6ViDiHand: The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
Xingang-Pan
• • 5Uncensor any LLM with abliteration
mlabonne
• • 931OpenAI Decisions API vs. Jev: A Practical Guide to Decision Models
a2aprotocol
• • 6How to Use the Jev AI Model: A Step-by-Step Developer Guide
sora-2
• • 43