9 papers
PerSPL: Personalized Semi-supervised Preference Learning
Xiaoan Xu, Tingzhou Wei, Juncheng Dong +3
Personalized reward models require user-specific preference comparisons, but collecting such feedback is costly and provides only limited supervision for each user. At the same tim…
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
Xiaoang Xu, Siyuan Liu, Shuo Wang +13
Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation and context costs. Existing methods either lose intermediat…
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning
Zhu Zhang, Jixun Wang, Xiaoang Xu +6
On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, however, token-level teacher sup…
COOPA: A Modular LLM Agent Architecture for Operations Research Problems
Chuanhao Li, Xiaoan Xu, Dirk Bergemann +3
Operations Research (OR) provides a rigorous framework for high-stakes decision-making, but effective OR modeling requires substantial domain knowledge, mathematical abstraction, a…
Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning
Alper Kamil Bozkurt, Xiaoan Xu, Shangtong Zhang +2
In offline-to-online reinforcement learning (O2O-RL), policies are first safely trained offline using previously collected datasets and then further fine-tuned for tasks via limite…
Neuro-Logic Lifelong Learning
Bowen He, Xiaoan Xu, Alper Kamil Bozkurt +2
Solving Inductive Logic Programming (ILP) problems with neural networks is a key challenge in Neural-Symbolic Ar- tificial Intelligence (AI). While most research has focused on des…
Fisher Random Walk: Automatic Debiasing Contextual Preference Inference for Large Language Model Evaluation
Yichi Zhang, Alexander Belloni, Ethan X. Fang +2
Motivated by the need for rigorous and scalable evaluation of large language models, we study contextual preference inference for pairwise comparison functionals of context-depende…
A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
Xiaoang Xu, Shuo Wang, Xu Han +6
Large Reasoning Models (LRMs) achieve superior performance by extending the thought length. However, a lengthy thinking trajectory leads to reduced efficiency. Most of the existing…
METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth
Jiawei Li, Xiaoang Xu, Yang Gao
Model evolution enables learning from feedback to refine experiences and update skills, transforming models from having no domain knowledge to becoming domain experts. However, the…