2 citations · 2 across the 2 of their papers we have counts for
2 papers
cs.LG2026
How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum
Chu-Cheng Lin, Eugene Ie
The standard recipe for training reasoning models---SFT on rationale annotations followed by RLVR---relies on rationale annotations being available and clean. When no annotated rat…
cs.LG2020★ 2 cited
Limitations of Autoregressive Models and Their Alternatives
Chu-Cheng Lin, Aaron Jaech, Xin Li +2
Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol. While this is attractive, it means they cannot model…