6 papers
STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks
ELita Lobo, Xu Chen, Jingjing Meng +5
Existing LLM-based web agents struggle on complex, long-horizon tasks due to limited in-context memory, weak planning abilities, and greedy behaviors that lead to premature termina…
Pix2Key: Controllable Open-Vocabulary Retrieval with Semantic Decomposition and Self-Supervised Visual Dictionary Learning
Guoyizhe Wei, Yang Jiao, Nan Xi +4
Composed Image Retrieval (CIR) uses a reference image plus a natural-language edit to retrieve images that apply the requested change while preserving other relevant visual content…
Learning by Analogy: A Causal Framework for Composition Generalization
Lingjing Kong, Shaoan Xie, Yang Jiao +6
Compositional generalization -- the ability to understand and generate novel combinations of learned concepts -- enables models to extend their capabilities beyond limited experien…
Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Multi-Objective Weighted-Chebyshev Actor-Critic Approach
Fnu Hairi, Jiao Yang, Tianchen Zhou +6
In many multi-objective reinforcement learning (MORL) applications, being able to systematically explore the Pareto-stationary solutions under multiple non-convex reward objectives…
Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items
Junting Wang, Chenghuan Guo, Jiao Yang +3
We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purchase suggestions. Existing approaches ty…
Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments
Tianchen Zhou, Jia Liu, Yang Jiao +4
Online learning to rank (ONL2R) is a foundational problem for recommender systems and has received increasing attention in recent years. Among the existing approaches for ONL2R, a…