Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Extremely Sparse Supervision Incentivizes Reasoning Ability
Zhishuai Liu, Xingzi Xu, Mehmet Saygin Seyfioglu +2
Large language models demonstrate increasingly strong reasoning capabilities through effective post-training. Yet, prevailing post-training methods optimize over massive numbers of…
cs.AI2026
Trie Automata for Constrained Decoding over Large Finite Sets
Xingzi Xu, Karim Bouyarmane
Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of valid str…