AI2 days agoModel Performance Begins with Data: Researchers from Ai2 Release DataDecide—A Benchmark Suite to Understand Pretraining Data Impact Across 30K LLM Checkpoints
AI4 days agoTHUDM Releases GLM 4: A 32B Parameter Model Competing Head-to-Head with GPT-4o and DeepSeek-V3
AIApril 13, 2025A Coding Implementation on Introduction to Weight Quantization: Key Aspect in Enhancing Efficiency in Deep Learning and LLMs
AIApril 13, 2025Moonsight AI Released Kimi-VL: A Compact and Powerful Vision-Language Model Series Redefining Multimodal Reasoning, Long-Context Understanding, and High-Resolution Visual Processing
AIApril 12, 2025Allen Institute for AI (Ai2) Launches OLMoTrace: Real-Time Tracing of LLM Outputs Back to Training Data
AIApril 11, 2025Balancing Accuracy and Efficiency in Language Models: A Two-Phase RL Post-Training Approach for Concise Reasoning