Model Detail
pocket-tts
—pocket-tts is an AI model released by kyutai. Distributed under the permissive cc-by-4.0 license.
The cc-by-4.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
pocket-tts is best fit for general-purpose AI workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
SpliceBind: Isoform-Aware Prediction of Binding Pocket Druggability
arXiv:2606.04020v1 Announce Type: cross Abstract: Splice-mediated drug resistance occurs in up to 40% of patients on targeted kinase inhibitors, yet state-of-the-art druggability tools operate on single structures and cannot compare across isoforms. We introduce SpliceBind, a graph neural network fr
From Holo Pockets to Electron Density: GPT-style Drug Design with Density
arXiv:2605.08767v2 Announce Type: replace Abstract: Recent advances in generative modeling have enabled significant progress in structure-based drug design (SBDD). Existing methods typically condition molecule generation on empty binding pockets from holo complexes, overlooking informative component
A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
arXiv:2606.03948v1 Announce Type: new Abstract: We implement simultaneous translation capability with the offline direct speech-to-text translation model Canary, using the state-of-the-art policy AlignAtt, and submit it to IWSLT 2026 Simultaneous Speech Translation Shared task for Czech to English a
Pocket-Dentist: On-Device Dental Image Understanding via Efficient Multimodal Large Language Models
arXiv:2605.29299v2 Announce Type: replace-cross Abstract: Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cost. This limits their widespread deployment for dental screening outside specialist centres,
Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
arXiv:2605.18654v1 Announce Type: cross Abstract: A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or CatBoost student that runs natively on CPU. The central obstacle is s
