Self-evolving training improves the performance of agents on difficult tasks through verifiable feedback, but it often applies costly deliberation uniformly across tasks. To address this problem, we propose Mode-Optimized Reasoning with Self-Adaptive Effort (MORE), a self-evolving training framework that adaptively sel...
Dian-Xing Shi, Ding-Jie Fu, Tian-Yu Lei et al.· 0 citations
Experiments on FastVLM-1.5B across multiple vision-language benchmarks demonstrate that VPRune achieves a favorable accuracy--compression trade-off, with particularly pronounced advantages under aggressive compression, demonstrating its practicality for resource-constrained LVLM deployment.
This work introduces ANCHOR, an LLM-based supervisory framework that delivers evaluative feedback at multiple phases of self-evolution and aggregates reviewed signals into context for subsequent steps and shows that ANCHOR substantially improves safety performance while maintaining stable performance on the core capabi...
Dian-Xing Shi, Jun He, Junhao Chen et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.