autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model
autotrust
• • 219Community Blog & Articles
Community Articles
view all
ml-interndatasetsspaces
The model that didn't exist, so you made it yourself
5
October 8, 2026 
Multimodal open d1 decision models for the edge
27
October 7, 2026 
Introducing Falcon ASR
1
October 7, 2026 
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
12
October 7, 2026 
The Agent Said It Was Done. The Database Disagreed.
61
October 3, 2026 
Open-sourcing AstaBrief, the fast report-generation model in Asta
28
October 2, 2026 
AutoSynthData: Generating Training Data for Enterprise Agents
46
October 2, 2026 
audiospeechleaderboard
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
55
September 30, 2026 
Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents
21
September 29, 2026 
Holo4: powering generalist computer-use agents
85
September 28, 2026 
rldatasetshub
Welcome RL Environments to the hub
- +4
31
September 28, 2026 
evaluationresearchcommunity
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
- +5
28
September 22, 2026 
transformersggufkernels
Transformers now runs llama.cpp quants
102
September 22, 2026 
mlxopen-sourcecommunity
Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community
- +1
88
September 22, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model
autotrust
• • 219autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training
autotrust
• • 166New in llama.cpp: Decision Models
ggml-org
• • 89NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
nvidia
• • 86LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model
lightonai
• • 18Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance
tiiuae
• • 20Falcon OCR Arabic: 270M Parameters State-of-the-Art Arabic OCR
tiiuae
• • 16Carbon-A: Finding genes in known and unknown genomes
HuggingFaceBio
• • 16Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration
FINAL-Bench
• • 12Data-center AI, now on a laptop — POCKET-Darwin-180B
FINAL-Bench
• • 10Live Human Feedback in the Training Loop: Aligning Diffusion Models with Real People
Rapidata
• • 10Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs
allenai
• • 25YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research
espnet
• • 35Bringing Humanoids to LeRobot
nepyope
• • 26KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 428Universal Modder: A Practical Guide to AI Game Modding
a2aprotocol
• • 6OpenAI Decisions API vs. Jev: A Practical Guide to Decision Models
a2aprotocol
• • 5Decoding LLM Alignment: A Concise Guide for GRPO and its variants
Sneha7
• • 5ViDiHand: The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
Xingang-Pan
• • 4Uncensor any LLM with abliteration
mlabonne
• • 929