Postdoc, Massachusetts Institute of Technology
2 papers at NeurIPS 2025
We present JetLM, a new family of LMs, which matches leading full-attention models while significantly improving generation throughput.
Long-RL enables RL on hour-long videos on a single A100; LongVILA-R1-7B supports 8,192 frames and scores 65.1%/71.1% on VideoMME.
