13 citations · 20 across the 23 of their papers we have counts for
27 papers
QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards
Rongzhi Zhang, Rui Feng, Zhihan Zhang +8
Rubric-based RL is a promising route for extending reinforcement learning beyond verifiable rewards, yet existing methods optimize rubrics while treating the query distribution as…
Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
Zixuan Zhang, Kaixuan Huang, Tuo Zhao +2
Diffusion models have become a leading framework in generative modeling, yet their theoretical understanding -- especially for high-dimensional data concentrated on low-dimensional…
Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
Siyuan Xu, Shiyang Li, Xin Liu +9
Existing synthetic tool-use corpora are primarily designed for offline supervised fine-tuning, yet reinforcement learning (RL) requires executable environments that support reward-…
Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards
Cheng Jiayang, Xin Liu, Zhihan Zhang +8
Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workfl…
How Accurately Can a Gaussian Approximate Stochastic Approximation Iterates?
Shaan Ul Haque, Zedong Wang, Zixuan Zhang +1
Stochastic approximation (SA) is a method for finding the root of an operator perturbed by noise. The focus of this paper is studying the distribution of SA iterates in finite time…
BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models
Liming Liu, Binxuan Huang, Zixuan Zhang +3
Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation…
Instant Personalized Large Language Model Adaptation via Hypernetwork
Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen +8
Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) method…
Machine Learning Powered Feasible Path Framework with Adaptive Sampling for Black-box Optimization
Zixuan Zhang, Xiaowei Song, Jiaming Li +7
Black-box optimization (BBO) involves functions that are unknown, inexact and/or expensive-to-evaluate. Existing BBO algorithms face several challenges, including high computationa…
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
Yining Lu, Zilong Wang, Shiyang Li +6
Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thu…
LLMs Can Generate a Better Answer by Aggregating Their Own Responses
Zichong Li, Xinyu Feng, Yuheng Cai +6
Large Language Models (LLMs) have shown remarkable capabilities across tasks, yet they often require additional prompting techniques when facing complex problems. While approaches…
IHEval: Evaluating Language Models on Following the Instruction Hierarchy
Zhihan Zhang, Shiyang Li, Zixuan Zhang +11
The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent an…
A Minimalist Example of Edge-of-Stability and Progressive Sharpening
Liming Liu, Zixuan Zhang, Simon Du +1
Recent advances in deep learning optimization have unveiled two intriguing phenomena under large learning rates: Edge of Stability (EoS) and Progressive Sharpening (PS), challengin…
Double Distillation Network for Multi-Agent Reinforcement Learning
Yang Zhou, Siying Wang, Wenyu Chen +3
Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the…
COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs
Liming Liu, Zhenghao Xu, Zixuan Zhang +5
Large Language Models (LLMs) have demonstrated remarkable success across various domains, yet their optimization remains a significant challenge due to the complex and high-dimensi…
Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning
Ruoning Zhang, Siying Wang, Wenyu Chen +5
The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, conventional methods based on CTDE…
Feasible Path SQP Algorithm for Simulation-based Optimization Surrogated with Differentiable Machine Learning Models
Zixuan Zhang, Xiaowei Song, Yujiao Zeng +6
With the development of artificial intelligence, simulation-based optimization problems, which present a significant challenge in the process systems engineering community, are inc…
Robust Reinforcement Learning from Corrupted Human Feedback
Alexander Bukharin, Ilgee Hong, Haoming Jiang +4
Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, cont…
RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning
Ziyu Wang, Wenhao Jiang, Zixuan Zhang +2
Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms. Learning such a modular structure can often improv…
Smoothening block rewards: How much should miners pay for mining pools?
Axel Cortes-Cubero, Juan P. Madrigal-Cianci, Kiran Karra +1
The rewards a blockchain miner earns vary with time. Most of the time is spent mining without receiving any rewards, and only occasionally the miner wins a block and earns a reward…
An Agent-Based Model Framework for Utility-Based Cryptoeconomies
Kiran Karra, Tom Mellan, Maria Silva +3
In this paper, we outline a framework for modeling utility-based blockchain-enabled economic systems using Agent Based Modeling (ABM). Our approach is to model the supply dynamics…
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Zixuan Zhang, Kaiqi Zhang, Minshuo Chen +4
Convolutional residual neural networks (ConvResNets), though overparameterized, can achieve remarkable prediction performance in practice, which cannot be well explained by convent…
Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories
Zixuan Zhang, Minshuo Chen, Mengdi Wang +2
Existing theories on deep nonparametric regression have shown that when the input data lie on a low-dimensional manifold, deep neural networks can adapt to the intrinsic data struc…
Rethinking Safe Control in the Presence of Self-Seeking Humans
Zixuan Zhang, Maitham AL-Sunni, Haoming Jing +2
Safe control methods are often intended to behave safely even in worst-case human uncertainties. However, humans may exploit such safety-first systems, which results in greater ris…
Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control
Zixuan Zhang, Yuning Jiang, Yuanming Shi +2
With the recent advances in mobile energy storage technologies, electric vehicles (EVs) have become a crucial part of smart grids. When EVs participate in the demand response progr…