MARVIS: Modality Adaptive Reasoning over VISualizations Paper β’ 2507.01544 β’ Published 15 days ago β’ 12
ARIG: Autoregressive Interactive Head Generation for Real-time Conversations Paper β’ 2507.00472 β’ Published 16 days ago β’ 11
Answer Matching Outperforms Multiple Choice for Language Model Evaluation Paper β’ 2507.02856 β’ Published 14 days ago β’ 8
InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding Paper β’ 2506.15745 β’ Published 29 days ago β’ 13
view article Article Halo: Open Source Health Tracking with Wearables By cyrilzakka β’ Nov 19, 2024 β’ 112
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks Paper β’ 2311.06242 β’ Published Nov 10, 2023 β’ 94