OpenCLIP 4.2 ships with CLAP2 variable-length audio and NaFlexViT support
wightmanr · x · 2026-11-14
OpenCLIP v4.2 adds support for the new CLAP2 variable-length audio-text models plus a broad refresh: OpenMaMMUT (open-weight dual contrastive+generative) with pooling fixes for MaMMUT2/CoCa2, GenLIP/GenLAP generative decoder-only models, NaFlexViT encoders across the board, ModernText towers (RoPE, SwiGLU, gated attention, long context, TikTokenizer), an enhanced variable-length data pipeline with length bucketing, and a refactored training stack with FSDP2 and torch.compile, with PyTorch 2.15 varlen attention coming. Source: mlfoundations/openclip.
More from Research
- NYU Courant launches Center for Mathematics and AI, co-directed by Bruna and Vicol — kchonyc · 2026-11-14
- mariofilho: Pareto plots should be mandatory for benchmarks — mariofilhoml · 2026-11-14
- MIT's AI 'mechanic' can read and edit the internals of other neural networks, Nature reports — marinkazitnik · 2026-11-14
- Rewiring just 47 neurons induces emergent misalignment in Qwen, then makes it interpretable — maxsloef · 2026-11-14
- Antithesis spent 8 years cracking NetHack Ascension, now clears ~80% of seeds in under 5 minutes — spikedoanz · 2026-11-14
- 5.46M-param touch model LingBot-Touch pokes straws through sealed lids autonomously — Puzzleheaded-Buy3008 · 2026-11-14