arXiv subjects

Mu Zhang

Publications and source records attributed to Mu Zhang.

8 recordsLinked to original sources

arXiv2026

Associative Networks in Decision Making

We present a model of associative networks that captures how decision makers expand their consideration set through mental associations between alternatives. Our model provides a tractable approach to study how associations shape choice when some alternatives are available and others are merely observable but unavailable. We characterize the model within a random attention framework and demonstrate unique identification of all parameters. This framework delivers a unified account of several prominent choice anomalies, including classic menu effects and their ``phantom'' counterparts. We illustrate how associative links serve as a strategic variable in applications such as branding, imitation, and platform design.

econ.TH↗

arXiv2026

Decision Making Under Multidimensional Risk

Choice alternatives are often multidimensional and risky. We introduce and axiomatize the \textit{structured multidimensional expected utility} representation, a unified framework that generalizes existing approaches to evaluating such alternatives. The representation uses a \textit{rooted clustered tree} to organize the joint, separate, and conditional evaluation of risk across dimensions within a common structure. We analyze the uniqueness of the representation and characterize useful special cases. We apply the representation to inequality across individuals, groups, and generations and to multisource income, characterizing the implications of bracketing for stochastic dominance and the avoidance of multidimensional risk.

econ.TH↗

arXiv2026

dRAE: Representation Autoencoder with Hyper-Spherical Codes

In this work, we aim to discretize the high-dimensional visual representations to bridge the gap with language models - a non-trivial challenge, as existing quantization methods suffer from codebook collapse, failing to scale while preserving semantic coherence. We identify the root cause as metric mismatch: standard Euclidean codebook objectives are fundamentally misaligned with the anisotropic geometry of representation space, leading to codebook embeddings with high-variance magnitude scales and uneven angular distributions that hinder scalability. To address this, we propose Hyper-Spherical Quantization (HSQ), which decouples semantic content from feature magnitude via angular routing, preventing code assignment from being dominated by scale rather than meaning. The resulting discrete Representation Autoencoder (dRAE) achieves high-fidelity reconstruction while preserving semantic integrity and supporting scalable codebook budget. Extensive experiments demonstrate consistent performance gains as the vocabulary size scales to 131{,}072, along with 100\% codebook utilization, simplified training pipeline, and strong performance across understanding and generation tasks.

cs.CV↗

arXiv2025

Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy Optimization (GRPO). In this study, we introduce MaskGRPO, the first viable approach to enable scalable multimodal reinforcement learning in discrete diffusion with effective importance sampling and modality-specific adaptations. To this end, we first clarify the theoretical foundation for DDMs, which facilitates building an importance estimator that captures valuable token fluctuation for gradient updates. We then delicately tailored the rollout method for visual sequences, which yields diverse completions and reliable optimization gradients. Upon math reasoning, coding, and visual generation benchmarks, MaskGRPO brings more stable and efficient updates, leading to stronger reasoning performance and better generation quality. This study establishes MaskGRPO as a systematic policy optimization approach and the first practical way for discretized visual diffusion.

cs.AI↗

arXiv2024

CC-Diff: Enhancing Contextual Coherence in Remote Sensing Image Synthesis

Existing image synthesis methods for natural scenes focus primarily on foreground control, often reducing the background to simplistic textures. Consequently, these approaches tend to overlook the intrinsic correlation between foreground and background, which may lead to incoherent and unrealistic synthesis results in remote sensing (RS) scenarios. In this paper, we introduce CC-Diff, a $\underline{\textbf{Diff}}$usion Model-based approach for RS image generation with enhanced $\underline{\textbf{C}}$ontext $\underline{\textbf{C}}$oherence. Specifically, we propose a novel Dual Re-sampler for feature extraction, with a built-in `Context Bridge' to explicitly capture the intricate interdependency between foreground and background. Moreover, we reinforce their connection by employing a foreground-aware attention mechanism during the generation of background features, thereby enhancing the plausibility of the synthesized context. Extensive experiments show that CC-Diff outperforms state-of-the-art methods across critical quality metrics, excelling in the RS domain and effectively generalizing to natural images. Remarkably, CC-Diff also shows high trainability, boosting detection accuracy by 1.83 mAP on DOTA and 2.25 mAP on the COCO benchmark.

cs.CV↗

arXiv2023

WRTester: Differential Testing of WebAssembly Runtimes via Semantic-aware Binary Generation

Wasm runtime is a fundamental component in the Wasm ecosystem, as it directly impacts whether Wasm applications can be executed as expected. Bugs in Wasm runtime bugs are frequently reported, thus our research community has made a few attempts to design automated testing frameworks for detecting bugs in Wasm runtimes. However, existing testing frameworks are limited by the quality of test cases, i.e., they face challenges of generating both semantic-rich and syntactic-correct Wasm binaries, thus complicated bugs cannot be triggered. In this work, we present WRTester, a novel differential testing framework that can generated complicated Wasm test cases by disassembling and assembling of real-world Wasm binaries, which can trigger hidden inconsistencies among Wasm runtimes. For further pinpointing the root causes of unexpected behaviors, we design a runtime-agnostic root cause location method to accurately locate bugs. Extensive evaluation suggests that WRTester outperforms SOTA techniques in terms of both efficiency and effectiveness. We have uncovered 33 unique bugs in popular Wasm runtimes, among which 25 have been confirmed.

cs.SE↗

arXiv2021

A Theory of Choice Bracketing under Risk

Aggregating risks from multiple sources can be complex and demanding, and decision makers usually adopt heuristics to simplify the evaluation process. This paper axiomatizes two closed related and yet different heuristics, narrow bracketing and correlation neglect, by relaxing the independence axiom in the expected utility theory. The flexibility of our framework allows for applications in various economic problems. First, our model can explain the experimental evidence of narrow bracketing over monetary gambles. Second, when one source represents background risk, we can accommodate Rabin (2000)'s critique and explain risk aversion over small gambles. Finally, when different sources represent consumptions in different periods, we unify three seemingly distinct models of time preferences and propose a novel model that simultaneously satisfies indifference to temporal resolution of uncertainty, separation of time and risk preferences, and recursivity in the domain of lotteries. As a direct application to macroeconomics and finance, we provide an alternative to Epstein and Zin (1989) which avoids the unreasonably high timing premium discussed in Epstein, Farhi, and Strzalecki (2014).

econ.TH↗

arXiv2019

Duet: An Expressive Higher-order Language and Linear Type System for Statically Enforcing Differential Privacy

During the past decade, differential privacy has become the gold standard for protecting the privacy of individuals. However, verifying that a particular program provides differential privacy often remains a manual task to be completed by an expert in the field. Language-based techniques have been proposed for fully automating proofs of differential privacy via type system design, however these results have lagged behind advances in differentially-private algorithms, leaving a noticeable gap in programs which can be automatically verified while also providing state-of-the-art bounds on privacy. We propose Duet, an expressive higher-order language, linear type system and tool for automatically verifying differential privacy of general-purpose higher-order programs. In addition to general purpose programming, Duet supports encoding machine learning algorithms such as stochastic gradient descent, as well as common auxiliary data analysis tasks such as clipping, normalization and hyperparameter tuning - each of which are particularly challenging to encode in a statically verified differential privacy framework. We present a core design of the Duet language and linear type system, and complete key proofs about privacy for well-typed programs. We then show how to extend Duet to support realistic machine learning applications and recent variants of differential privacy which result in improved accuracy for many practical differentially private algorithms. Finally, we implement several differentially private machine learning algorithms in Duet which have never before been automatically verified by a language-based tool, and we present experimental results which demonstrate the benefits of Duet's language design in terms of accuracy of trained machine learning models.

cs.PL↗