6 papers
WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training
Zehao Chen, Gongxun Li, Tianxiang Ai +9
On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation. The sa…
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger
Zehao Chen, Gongxun Li, Tianxiang Ai +9
As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training…
Safe Planning in Unknown Environments Using Conformalized Semantic Maps
David Smith Sundarsingh, Yifei Li, Tianji Tang +3
This paper addresses semantic planning problems in unknown environments under perceptual uncertainty. The environment contains multiple unknown semantically labeled regions or obje…
LLMBoost: Make Large Language Models Stronger with Boosting
Zehao Chen, Tianxiang Ai, Yifei Li +11
Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or fina…
LocalEscaper: A Weakly-supervised Framework with Regional Reconstruction for Scalable Neural TSP Solvers
Junrui Wen, Yifei Li, Bart Selman +1
Neural solvers have shown significant potential in solving the Traveling Salesman Problem (TSP), yet current approaches face significant challenges. Supervised learning (SL)-based…
Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answering
Xiao Long, Liansheng Zhuang, Chen Shen +3
Recently, large language models (LLMs) have demonstrated impressive performance in Knowledge Graph Question Answering (KGQA) tasks, which aim to find answers based on knowledge gra…