4 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Speculative decoding accelerates autoregressive generation by using a lightweight draft model to propose multiple tokens that are verified by a target model in parallel. However, the standard acceptance rule focuses on exact distribution correction and rejects tokens that remain highly plausible under the target model...
ForGE is introduced, a failure-guided framework that co-evolves prompts and training data and establishes failures as a shared interface between prompt optimization and data synthesis, and shows the benefit of jointly adapting what a model is instructed to do and what it learns from
A three-stage calibration framework that evaluates confidence before, during, and after chain-of-thought generation, corresponding to difficulty estimation, early termination, and answer aggregation finds that OPD provides the most useful pre-reasoning confidence, SFT gives the strongest online signal for early stoppin...
A three-stage calibration framework that evaluates confidence before, during, and after chain-of-thought generation, corresponding to difficulty estimation, early termination, and answer aggregation finds that OPD provides the most useful pre-reasoning confidence, SFT gives the strongest online signal for early stoppin...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
