Sublime

ImageRAG Powered by Llama 3.2 Vision ImageRAG is a powerful RAG system combining Colpali's ColQwen image embeddings with Ollama LLaMA 3.2 Vision. 🌟 Key Features of ImageRAG 🧬 ColQwen model for generating powerful image embeddings via Colpali 🤖 LL... See more

Top-rated papers from ICLR 2025 Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport - Rating: 9.0 - https://t.co/Ybsw2296I9 OLMoE: Open Mixture-of-Experts Language Models - Rating: 8.67 - https://t.co/KmaXgEym4T Compositional Entailment Learning for Hyperbolic Vision-Language Models - Rating: 8.0 - https://t.co/IuemddOOPO The Complexity of Two-Team Polymatrix Games with Independent Adversaries - Rating: 8.0 - https://t.co/XSuzLUV1b0 Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment - Rating: 8.0 - https://t.co/7MfBTFltad SAM 2: Segment Anything in Images and Videos - Rating: 8.0 - https://t.co/U5DVeWndR5 Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ Regression - Rating: 8.0 - https://t.co/iWZQXiQtT6 Differential Transformer - Rating: 8.0 - https://t.co/BjWsQfOeG9 LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization - Rating: 8.0 - https://t.co/PMlfsBhJYR Spider 2.0: Can Language Models Resolve Real-World Enterprise Text-to-SQL Workflows? - Rating: 8.0 - https://t.co/qYBOVZr6FP BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions - Rating: 8.0 - https://t.co/9SchPdadSs Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models - Rating: 8.0 - https://t.co/MiHjZOqkGC Scaling... See more

Video of my talk on self-supervised learning, energy-based models, and training methods for joint-embedding architectures (e.g. Siamese nets) in contrastive and non-contrastive modes. Given at the French-German Symposium on ML. (with panel discussion). https://t.co/zCf4PBm9O7