LeMaterial: an open source initiative to accelerate materials discovery and research Dec 10, 2024 β’ 35
Towards Best Practices for Open Datasets for LLM Training Paper β’ 2501.08365 β’ Published 10 days ago β’ 47
view article Article MiniMax-01 is Now Open-Source: Scaling Lightning Attention for the AI Agent Era By MiniMax-AI β’ 9 days ago β’ 40
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning Paper β’ 2406.11896 β’ Published Jun 14, 2024 β’ 20
view post Post 3345 I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!https://x.com/casper_hansen_/status/1875872309996855343Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025![1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)[2] https://huggingface.co/blog/ganqu/prime See translation π₯ 8 8 π§ 2 2 + Reply
view article Article πΊπ¦ββ¬ LLM Comparison/Test: DeepSeek-V3, QVQ-72B-Preview, Falcon3 10B, Llama 3.3 70B, Nemotron 70B in my updated MMLU-Pro CS benchmark By wolfram β’ 22 days ago β’ 38
Phi-3 Collection Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. β’ 26 items β’ Updated 16 days ago β’ 546
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction Paper β’ 2412.04454 β’ Published Dec 5, 2024 β’ 59