200 citations · 322 across the 7 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning
Jingwei Ni, Dmitry Abulkhanov, Vladislav Smirnov +5
Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one. Deciding when to stop is a metareason…
cs.LG2026
IDLM: Inverse-distilled Diffusion Language Models
David Li, Nikita Gushchin, Dmitry Abulkhanov +4
Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To ad…