Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignmentarxiv.org2 points·by badmonster·vor 7 Monaten·0 comments
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generationarxiv.org2 points·by badmonster·vor 7 Monaten·0 comments
Agentic Learner with Grow-and-Refine Multimodal Semantic Memoryarxiv.org1 points·by badmonster·vor 8 Monaten·0 comments
Extract structured information from Hacker News and keep in sync with Postgrescocoindex.io2 points·by badmonster·vor 8 Monaten·0 comments
When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflectionarxiv.org2 points·by badmonster·vor 8 Monaten·1 comments
Streamline Structured and Unstructured Data Flows from Postgres with AIcocoindex.io1 points·by badmonster·vor 8 Monaten·0 comments
Counterfactual World Models via Digital Twin-Conditioned Video Diffusionarxiv.org2 points·by badmonster·vor 8 Monaten·0 comments
How to perform adaptive batching for massive remote LLM callscocoindex.io2 points·by badmonster·vor 8 Monaten·0 comments
Adaptive Batching – 5x throughput on your data pipelinescocoindex.io1 points·by badmonster·vor 8 Monaten·0 comments
Nested Learning – A new ML paradigm for continual learningresearch.google7 points·by badmonster·vor 8 Monaten·0 comments
Grasp Any Region: Precise, Contextual Pixel Understanding for Multimodal LLMsarxiv.org1 points·by badmonster·vor 9 Monaten·0 comments
StreamingVLM: Real-Time Understanding for Infinite Video Streamsarxiv.org33 points·by badmonster·vor 9 Monaten·0 comments