Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights Paper • 2603.12228 • Published 10 days ago • 11
mlx-community/Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit 27B • Updated 16 days ago • 21.2k • 47
AutoHarness: improving LLM agents by automatically synthesizing a code harness Paper • 2603.03329 • Published Feb 10 • 1
AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games Paper • 2602.17594 • Published about 1 month ago • 9
Doc-to-LoRA: Learning to Instantly Internalize Contexts Paper • 2602.15902 • Published Feb 13 • 3
Fast Inference from Transformers via Speculative Decoding Paper • 2211.17192 • Published Nov 30, 2022 • 11
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools Paper • 2405.20362 • Published May 30, 2024 • 3