On Path to Multimodal Generalist: General-Level and General-Bench Paper β’ 2505.04620 β’ Published 5 days ago β’ 71
Absolute Zero: Reinforced Self-play Reasoning with Zero Data Paper β’ 2505.03335 β’ Published 7 days ago β’ 118
Moshi v0.1 Release Collection MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi β’ 15 items β’ Updated 25 days ago β’ 228
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens Paper β’ 2502.18890 β’ Published Feb 26 β’ 30
VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges Paper β’ 2409.01071 β’ Published Sep 2, 2024 β’ 28