5 papers
Quantifying the Stability of Multi-Step Reasoning via Error Amplification
Dongyue Li, Ziniu Zhang, Minxuan Duan +1
We consider the stability of multi-step reasoning processes, which have extensive applications in language models, including chain-of-thought and algorithmic reasoning. While longe…
Efficient Estimation of Kernel Surrogate Models for Task Attribution
Zhenshuo Zhang, Minxuan Duan, Hongyang R. Zhang
Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text prediction -- simultaneously. A key qu…
Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
Ziniu Zhang, Minxuan Duan, Haris N. Koutsopoulos +1
We consider analyzing traffic accident patterns using both road network data and satellite images aligned to road graph nodes. Previous work for predicting accident occurrences rel…
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
Dongyue Li, Zhenshuo Zhang, Minxuan Duan +2
Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural…
Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
Zhenshuo Zhang, Minxuan Duan, Youran Ye +1
We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given objectives (or tasks), we seek th…