9 citations · 33 across the 24 of their papers we have counts for
25 papers
A Function-Space Approach to the Statistical Mechanics of Learning Dynamics
Yizhou Zhang, Weichen Wu, Lun Du +1
In the kernel regime, neural-network learning inherits its preferences from a frozen spectrum. During feature learning, this spectrum evolves, yet networks retain systematic biases…
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
Wen Ye, Muyan Weng, Chuizheng Meng +3
Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning. However, due to privacy concern…
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
Chenyou Guo, Zongqi Liu, Yizhou Zhang +2
While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evolution, current AI in Earth scie…
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
Hao Ye, Jisheng Dang, Junfeng Fang +7
Recent extensive research has demonstrated that the enhanced reasoning capabilities acquired by models through Reinforcement Learning with Verifiable Rewards (RLVR) are primarily c…
Training Generalizable Collaborative Agents via Strategic Risk Aversion
Chengrui Qu, Yizhou Zhang, Nicolas Lanzetti +1
Many emerging agentic paradigms require agents to collaborate with one another (or people) to achieve shared goals. Unfortunately, existing approaches to learning policies for such…
Provably Convergent Actor-Critic for MARL through Risk-aversion
Yizhou Zhang, Eric Mazumdar
Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary st…
When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
Yizhou Zhang
Empirical power--law scaling has been widely observed across modern deep learning systems, yet its theoretical origins and scope of validity remain incompletely understood. The Gen…
Renormalizable Spectral-Shell Dynamics as the Origin of Neural Scaling Laws
Yizhou Zhang
Neural scaling laws and double-descent phenomena suggest that deep-network training obeys a simple macroscopic structure despite highly nonlinear optimization dynamics. We derive s…
Data Curation Through the Lens of Spectral Dynamics: Static Limits, Dynamic Acceleration, and Practical Oracles
Yizhou Zhang, Lun Du
Large-scale neural models are increasingly trained with data pruning, synthetic data generation, cross-model distillation, reinforcement learning from human feedback (RLHF), and di…
A Generalized Spectral Framework to Expain Neural Scaling and Compression Dynamics
Yizhou Zhang
Empirical scaling laws describe how test loss and other performance metrics depend on model size, dataset size, and compute. While such laws are consistent within specific regimes,…
FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning
Yizhou Zhang, Ning Lv, Teng Wang +1
Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning.…
Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral Economics
Yizhou Zhang, Eric Mazumdar
Risk-aversion and bounded rationality are two key characteristics of human decision-making. Risk-averse quantal-response equilibrium (RQE) is a solution concept that incorporates t…
SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning
Jisheng Dang, Yizhou Zhang, Hao Ye +6
Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and…
KL-regularization Itself is Differentially Private in Bandits and RLHF
Yizhou Zhang, Kishan Panaganti, Laixi Shi +2
Differential Privacy (DP) provides a rigorous framework for privacy, ensuring the outputs of data-driven algorithms remain statistically indistinguishable across datasets that diff…
Learning to Steer Learners in Games
Yizhou Zhang, Yi-An Ma, Eric Mazumdar
We consider the problem of learning to exploit learning algorithms through repeated interactions in games. Specifically, we focus on the case of repeated two player, finite-action…
Understanding Artificial Neural Network's Behavior from Neuron Activation Perspective
Yizhou Zhang, Yang Sui
This paper explores the intricate behavior of deep neural networks (DNNs) through the lens of neuron activation dynamics. We propose a probabilistic framework that can analyze mode…
TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
Wen Ye, Wei Yang, Defu Cao +4
Time series analysis is crucial in real-world applications, yet traditional methods focus on isolated tasks only, and recent studies on time series reasoning remain limited to eith…
TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
Defu Cao, Wen Ye, Yizhou Zhang +1
Foundation models, particularly Large Language Models (LLMs), have revolutionized text and video processing, yet time series data presents distinct challenges for such approaches d…
An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
Yizhou Zhang, Lun Du, Defu Cao +2
Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications. However, when handling tasks invol…
Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model
Yizhou Zhang, Loc Trinh, Defu Cao +2
Recent years have witnessed the sustained evolution of misinformation that aims at manipulating public opinions. Unlike traditional rumors or fake news editors who mainly rely on g…
Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning
Yizhou Zhang, Guannan Qu, Pan Xu +3
We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of thei…
Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media
Yizhou Zhang, Defu Cao, Yan Liu
Recent years have witnessed the rise of misinformation campaigns that spread specific narratives on social media to manipulate public opinions on different areas, such as politics…
VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media
Yizhou Zhang, Karishma Sharma, Yan Liu
Recent years have witnessed an increasing use of coordinated accounts on social media, operated by misinformation campaigns to influence public opinion and manipulate social outcom…
PolSIRD: Modeling Epidemic Spread under Intervention Policies
Nitin Kamra, Yizhou Zhang, Sirisha Rambhatla +2
Epidemic spread in a population is traditionally modeled via compartmentalized models which represent the free evolution of disease in absence of any intervention policies. In addi…