Arman Cohan
@armancohan.bsky.social
NLP/AI Research
Assistant Professor @Yale
Assistant Professor @Yale
We release TESS2, a new diffusion LLM! 🚀
Some highlights:
⚪ A general instruction-following LLM!
⚪ Use reward guidance to steer model generations at test time.
⚪ Natural inference-time compute scaling
Checkout @hamishivi.bsky.social's thread for details below, the demo is fun to play with! 👇
Some highlights:
⚪ A general instruction-following LLM!
⚪ Use reward guidance to steer model generations at test time.
⚪ Natural inference-time compute scaling
Checkout @hamishivi.bsky.social's thread for details below, the demo is fun to play with! 👇
(1/8) Excited to share some new work: TESS 2!
TESS 2 is an instruction-tuned diffusion LM that can perform close to AR counterparts for general QA tasks, trained by adapting from an existing pretrained AR model.
📜 Paper: arxiv.org/abs/2502.13917
🤖 Demo: huggingface.co/spaces/hamis...
More below ⬇️
TESS 2 is an instruction-tuned diffusion LM that can perform close to AR counterparts for general QA tasks, trained by adapting from an existing pretrained AR model.
📜 Paper: arxiv.org/abs/2502.13917
🤖 Demo: huggingface.co/spaces/hamis...
More below ⬇️
February 21, 2025 at 2:01 PM
We release TESS2, a new diffusion LLM! 🚀
Some highlights:
⚪ A general instruction-following LLM!
⚪ Use reward guidance to steer model generations at test time.
⚪ Natural inference-time compute scaling
Checkout @hamishivi.bsky.social's thread for details below, the demo is fun to play with! 👇
Some highlights:
⚪ A general instruction-following LLM!
⚪ Use reward guidance to steer model generations at test time.
⚪ Natural inference-time compute scaling
Checkout @hamishivi.bsky.social's thread for details below, the demo is fun to play with! 👇