HUMAN-WRITTEN & LEGALLY-SOURCED* Collection Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis *...mostly. • 165 items • Updated 2 days ago • 2
ETHICALLY-DECENT & LEGALLY-ADJACENT Collection Depending on your definitions, these models may not be strictly "ethical" or "legal", yet they are 100% more ethical and legal than GPT or Claude. • 15 items • Updated 2 days ago • 1
ETHICALLY-DECENT & LEGALLY-ADJACENT Collection Depending on your definitions, these models may not be strictly "ethical" or "legal", yet they are 100% more ethical and legal than GPT or Claude. • 15 items • Updated 2 days ago • 1
espnet/owsm_v3.1_ebf_small_lowrestriction Automatic Speech Recognition • Updated Mar 27, 2025 • 10 • 3
AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors Paper • 2601.20524 • Published 4 days ago • 4
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization Paper • 2604.08476 • Published 3 days ago • 6
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web Paper • 2604.08516 • Published 4 days ago • 34
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 88 items • Updated 2 days ago • 12
HUMAN-WRITTEN & LEGALLY-SOURCED* Collection Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis *...mostly. • 165 items • Updated 2 days ago • 2
Test-Time Scaling Makes Overtraining Compute-Optimal Paper • 2604.01411 • Published 12 days ago • 27
Token Warping Helps MLLMs Look from Nearby Viewpoints Paper • 2604.02870 • Published 10 days ago • 33
Less Detail, Better Answers: Degradation-Driven Prompting for VQA Paper • 2604.04838 • Published 7 days ago • 13