SELF-EMO lets LLMs bootstrap better emotion recognition and expression via self-play, data flywheel filtering with smoothed IoU rewards, and SELF-GRPO reinforcement learning, yielding SOTA gains on IEMOCAP, MELD, and EmoryNLP.
Spell: Self-play reinforcement learning for evolving long-context language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
EvoVid proposes a temporal-centric self-evolution framework for Video-LLMs that uses temporal-aware Questioner and temporal-grounded Solver rewards to improve performance directly from unannotated videos.
D²Evo mines medium-difficulty anchors from the current model, trains a Questioner to generate matching questions, and jointly optimizes Solver and Questioner for progressive gains, outperforming baselines on math reasoning with under 2K real samples.
citing papers explorer
-
SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression
SELF-EMO lets LLMs bootstrap better emotion recognition and expression via self-play, data flywheel filtering with smoothed IoU rewards, and SELF-GRPO reinforcement learning, yielding SOTA gains on IEMOCAP, MELD, and EmoryNLP.
-
EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
EvoVid proposes a temporal-centric self-evolution framework for Video-LLMs that uses temporal-aware Questioner and temporal-grounded Solver rewards to improve performance directly from unannotated videos.
-
D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
D²Evo mines medium-difficulty anchors from the current model, trains a Questioner to generate matching questions, and jointly optimizes Solver and Questioner for progressive gains, outperforming baselines on math reasoning with under 2K real samples.