AIConfPaper
← Search

Zixuan Wu

12 accepted papers

2026

Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning Environment

Aleksander Boruch-Gruszecki, Yangtian Zi, Zixuan Wu, Tejas Oberoi, Carolyn Jane Anderson, Joydeep Biswas +1
ICLR 2026poster

Large language models (LLMs) already excel at writing code in high-resource languages such as Python and JavaScript, yet stumble on low-resource languages that remain essential to science and engineering. Besides the obvious shortage of pre-training data, post-training itself is a bottleneck: every…

Cited by 0Source ↗code ↗Scholar ↗
2026

SpeedCP: Fast Kernel-based Conditional Conformal Prediction

Yating Liu, Yeo Jin Jung, Zixuan Wu, So Won Jeong, Claire Donnat
ICML 2026poster

Conformal prediction provides distribution-free prediction sets with finite-sample conditional guarantees. RKHS-based frameworks—while promising for complex covariate shifts—suffer from prohibitive computational costs. To guarantee conditional validity under such shifts while ensuring feasibility, w…

Cited by 2Source ↗Scholar ↗
2025

GlyphPattern: An Abstract Pattern Recognition for Vision-Language Models

Zixuan Wu, Yoolim Kim, Carolyn Jane Anderson
ACL 2025finding

Vision-Language Models (VLMs) have made rapid progress in reasoning across visual and textual data. While VLMs perform well on vision tasks that they are trained on, our results highlight key challenges in abstract pattern recognition. We present GlyphPattern, a 954 item dataset that pairs 318 human…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance

Kin Man Lee, Sean Ye, Qingyu Xiao, Zixuan Wu, Zulfiqar Zaidi, David B. D'Ambrosio +2
ICRA 2025

Advances in robot learning have enabled robots to generate skills for a variety of tasks. Yet, robot learning is typically sample inefficient, struggles to learn from data sources exhibiting varied behaviors, and does not naturally incorporate constraints. These properties are critical for fast, agi

Cited by 8Source ↗Scholar ↗
2025

Learning Dynamics of a Ball with Differentiable Factor Graph and Roto-Translational Invariant Representations

Qingyu Xiao, Zixuan Wu, Matthew C. Gombolay
ICRA 2025

Robots in dynamic environments need fast, accurate models of how objects move in their environments to support agile planning. In sports such as ping pong, analytical models often struggle to accurately predict ball trajectories with spins due to complex aerodynamics, elastic behaviors, and the chal

Cited by 2Source ↗Scholar ↗
2025

Learning Multi-Agent Coordination for Replenishment At Sea

Byeolyi Han, Minwoo Cho, Letian Chen, Rohan R. Paleja, Zixuan Wu, Sean Ye +3
RA-L 2025

Optimizing large-scale logistics is computationally challenging due to its scale and requirement to be robust to stochastic and time-varying weather disturbances. However, prior research in multi-agent reinforcement learning (MARL) does not address scenarios that capture complexity of logistics oper

Cited by 1Source ↗Scholar ↗
2025

Learning Wheelchair Tennis Navigation from Broadcast Videos with Domain Knowledge Transfer and Diffusion Motion Planning

Zixuan Wu, Zulfiqar Zaidi, Adithya Patil, Qingyu Xiao, Matthew C. Gombolay
ICRA 2025

In this paper, we propose a novel and generalizable zero-shot knowledge transfer framework that distills expert sports navigation strategies from web videos into robotic systems with adversarial constraints and out-of-distribution image trajectories. Our pipeline enables diffusion-based imitation le

Cited by 3Source ↗Scholar ↗
2025

Substance Beats Style: Why Beginning Students Fail to Code with LLMs

Francesca Lucchetti, Zixuan Wu, Arjun Guha, Molly Q Feldman, Carolyn Jane Anderson
NAACL 2025long

Although LLMs are increasing the productivity of professional programmers, existing work shows that beginners struggle to prompt LLMs to solve text-to-code tasks (Nguyen et al., 2024; Prather et al., 2024b; Mordechai et al., 2024). Why is this the case? This paper explores two competing hypotheses a…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

Automated Non-invasive Analysis of Motile Sperms Using Cross-scale Guidance Network

Wei Dai, Zixuan Wu, Jiaqi Wang, Rui Liu, Min Wang, Tianyi Wu +3
ICRA 2024poster

Unbiased measurement of sperm morphometric and motility parameters is essential for assessing fertility potential and guiding visual feedback for microrobotic manipulation. Automated analysis of multiple sperms and selection of an optimal sperm is crucial for in vitro fertilisation treatment such as…

Cited by 0Source ↗Scholar ↗
2023

Learning Models of Adversarial Agent Behavior Under Partial Observability

Sean Ye, Manisha Natarajan, Zixuan Wu, Rohan Paleja, Letian Chen, Matthew C. Gombolay
IROS 2023poster

The need for opponent modeling and tracking arises in several real-world scenarios, such as professional sports, video game design, and drug-trafficking interdiction. In this work, we present Graph based Adversarial Modeling with Mutual Information (GrAMMI) for modeling the behavior of an adversaria…

Cited by 6Source ↗code ↗Scholar ↗
2020

A Simple and Effective Framework for Pairwise Deep Metric Learning

Qi Qi, Yan Yan, Zixuan Wu, Xiaoyu Wang, Tianbao Yang
ECCV 2020poster

Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗