AI2 days agoModel Performance Begins with Data: Researchers from Ai2 Release DataDecide—A Benchmark Suite to Understand Pretraining Data Impact Across 30K LLM Checkpoints
AI2 days agoOpenAI Releases Codex CLI: An Open-Source Local Coding Agent that Turns Natural Language into Working Code
AI3 days agoMIT Researchers Introduce DISCIPL: A Self-Steering Framework Using Planner and Follower Language Models for Efficient Constrained Generation and Reasoning
AI3 days agoSQL-R1: A Reinforcement Learning-based NL2SQL Model that Outperforms Larger Systems in Complex Queries with Transparent and Accurate SQL Generation
AI4 days agoTHUDM Releases GLM 4: A 32B Parameter Model Competing Head-to-Head with GPT-4o and DeepSeek-V3
AI5 days agoA Coding Implementation for Advanced Multi-Head Latent Attention and Fine-Grained Expert Segmentation
