From the 2 of 7 linked papers with an AI index.
7 papers
Design-Specification Tiling for ICL-based CAD Code Generation
Yali Du, San-Zhuo Xi, Hui Sun +1
The paper introduces Design‑Specification Tiling, a method for selecting in‑context learning exemplars that maximizes coverage of CAD design requirements, using a knowledge‑suffici…
SpecRL: Reinforcement Learning with Test-Based Completeness Rewards for Formal Specification Synthesis
Zhechong Huang, Zhao Zhang, Zeyu Sun +2
SpecRL is a reinforcement learning system that improves automatic generation of program specifications by rewarding candidates that reject impossible behaviors identified through g…
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Hui Sun, Yun-Ji Zhang, Zheng Xie +4
Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing methods either treat all tests equally or r…
Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation
Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang +3
Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-…
Mitigating Negative Transfer via Reducing Environmental Disagreement
Hui Sun, Zheng Xie, Hao-Yuan He +1
Unsupervised Domain Adaptation~(UDA) focuses on transferring knowledge from a labeled source domain to an unlabeled target domain, addressing the challenge of \emph{domain shift}.…
MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs
Hui Sun, Shiyin Lu, Huanyu Wang +5
Video large language models (Video-LLMs) have made significant progress in understanding videos. However, processing multiple frames leads to lengthy visual token sequences, presen…