AIMay 1, 2025Multimodal AI on Developer GPUs: Alibaba Releases Qwen2.5-Omni-3B with 50% Lower VRAM Usage and Nearly-7B Model Performance
AIApril 30, 2025Reinforcement Learning for Email Agents: OpenPipe’s ART·E Outperforms o3 in Accuracy, Latency, and Cost
AIApril 29, 2025ViSMaP: Unsupervised Summarization of Hour-Long Videos Using Meta-Prompting and Short-Form Datasets
AIApril 28, 2025A Coding Tutorial of Model Context Protocol Focusing on Semantic Chunking, Dynamic Token Management, and Context Relevance Scoring for Efficient LLM Interactions
AIApril 28, 2025Researchers from Sea AI Lab, UCAS, NUS, and SJTU Introduce FlowReasoner: a Query-Level Meta-Agent for Personalized System Generation
