News June 27, 2024 Google releases Gemma 2 Google has introduced Gemma 2, its latest generation of open AI models, aimed at enhancing research and development in artificial intelligence. With 9B and 27B parameter versions, Gemma 2 boasts significant improvements in
Research June 25, 2024 Data curation via joint example selection further accelerates multimodal learning Abstract
Research June 20, 2024 Connecting the Dots - LLMs can Infer and Verbalize Latent Structure from Disparate Training Data Abstract
News June 18, 2024 Meta releases New AI Research Models to Accelerate Innovation at Scale For over a decade, Meta's Fundamental AI Research (FAIR) team has been dedicated to advancing AI through open research. In light of rapid innovations in the field, we recognize that collaboration with the
News June 14, 2024 NVIDIA announced Nemotron 340B Nemotron-4 340B, a family of models optimized for NVIDIA NeMo and NVIDIA TensorRT-LLM, includes cutting-edge instruct and reward models, and a dataset for generative AI training.
News June 14, 2024 Google open Project During the Google I/O 2024 developer conference, Google revealed that Project IDX, its next-generation, AI-powered browser-based development environment, is now in open beta. Initially introduced in August as an invite-only service, Project IDX
Research June 13, 2024 Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B Monte Carlo Trees with Llama-3 8B solve mathematics limitations of LLMs
Research June 13, 2024 Depth Anything V2 Samba architecture achieves 3.73x faster throughput with enhanced context
Research June 11, 2024 Samba - Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling Samba architecture achieves 3.73x faster throughput with enhanced context
