Co is introduced, a Counterfactual Consistency framework to enhance action controllability through two complementary constraints: Multi-step counterfactual consistency constrains reference, inverse-action, and zero-action rollouts, while action-spatial counterfactual consistency enforces consistent predictions under mi...
Yu-Hong Shi, Zhenhao Chu, Jie Wei et al.· 5 citations
ADSL-PDE improves both search efficiency and optimization stability, achieving an improvement of more than 52% within the first ten evolution iterations, suggesting a broader principle for LLM-driven auto-design: effective agents do not merely require stronger reasoning, but rather a search representation that concentr...
GraphIR, an architecture-aware intermediate representation that supplements executable programs with a mutation-aligned candidate state, achieves the best overall search performance while maintaining comparable model size and favorable end-to-end NAS efficiency when integrated into OpenEvolve.
Zhen Liu, Wanqi Zhou, Shuanghao Bai et al.· 1 citation
This paper argues that the key lies in designing an appropriate search-state representation that connects the internal knowledge of LLMs with the structural requirements and constraints of visual-token pruning, and proposes AutoPrune, a training-free framework for LLM-driven visual-token pruning policy design.
Zhen Liu, Wenli Huang, Wei Song et al.· 0 citations
HELP, a program optimizer that prompts an LLM to generate diverse, non-overlapping atomic edits and then systematically selects and composes them into coherent program improvements using evaluator scores, is introduced.
Jingwen Fu, Zhen Liu, Yuhan Liu et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
