LensVLM: Selective Context Expansion for Compressed Visual Representation of Text Paper • 2605.07019 • Published May 7 • 6
UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective Paper • 2305.10306 • Published May 22, 2023 • 1
view article Article **Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization** nvidia • 2 days ago • 52
Jev-style decision models: open data Collection Data for Jev-style decision models. Notes say where labels come from: humans, exact rules or an LLM teacher. Last updated 2026-09-24. • 17 items • Updated 1 day ago • 7
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction Paper • 2609.24983 • Published 5 days ago • 54
view article Article Transformers now runs llama.cpp quants +1 marcsun13, ArthurZ, lysandre • 4 days ago • 62
view article Article Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community +3 pcuenq, lysandre, victor, julien-c, Jundot • 4 days ago • 69
view article Article tokenizers v1: encode, decode and scaling, measured +2 ArthurZ, sbrandeis, mcpotato, lysandre • 5 days ago • 75
GLiClass: Generalist Lightweight Model for Sequence Classification Tasks Paper • 2508.07662 • Published Aug 11, 2025 • 11
The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder Paper • 2602.18487 • Published Feb 11 • 7
view article Article Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model CohereLabs • Aug 12 • 41
Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards Paper • 2609.03181 • Published 24 days ago • 11
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 24 days ago • 402
OCR: Leaderboards Collection Where OCR models are actually scored. Benchmark datasets with results tables first, then per-language leaderboard Spaces. Ordered by likes. • 7 items • Updated 9 days ago • 3
view article Article Generating Synthetic Training Data with Dask on Hugging Face Jobs Hanno-Labs • 10 days ago • 3