Searcharxiv⌕ Search

arXiv subjects

Zihan Zhang

Publications and source records attributed to Zihan Zhang.

At least 73 records · Page 4Linked to original sources
arXiv2026

CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs

Existing research largely reduces cultural intelligence in LLMs to a knowledge-level problem, overlooking whether models can effectively utilize their acquired knowledge in realistic scenarios. To bridge this gap, we introduce CultureForest, a benchmark for \textit{Cultural Norm Grounded Reasoning}. Each question is grounded in a small set of atomic norms, enabling verifiable and attributable evaluation. CultureForest comprises 5,378 examples across 8 domains and 53 countries/regions, and supports a progressive evaluation from multiple-choice to open-ended generation. Extensive experiments reveal that even top-tier models degrade substantially in open-ended settings, accompanied by pronounced cross-region disparities. Through targeted analysis, we uncover several consistent patterns: (1) test-time reasoning yields limited gains and may exacerbate inequity; (2) models exhibit highly shared regional preference structures; (3) model responses are markedly conservative, especially under stricter cultural constraints; and (4) by disentangling cultural knowledge acquisition from cultural reasoning, we show that while LLMs possess substantial cultural knowledge, their performance is further bottlenecked by its effective use. These findings point to a necessary shift from knowledge-centric evaluation toward measuring knowledge-grounded reasoning.

cs.CL↗
arXiv2026

An Improvement of Konstantoulas' Density Constant

Let $A\subset N$, and define its ordered representation function $r(n)=\#\{(a,b)\in A\times A:a+b=n\}.$ The Erdos--Turan conjecture asserts that, if $r(n) > 0$ for all sufficiently large $n$, then $r(n)$ is unbounded. Konstantoulas proved a density-theoretic version: if the upper density of $E=N\setminus(A+A)$ is less than $1/10$, then $\limsup_{n\to\infty} r(n)> 5$. In this paper, we improve Konstantoulas' constant to $7/32$. We also prove that $D(E)< 1/2$ implies $\limsup_{n\to\infty} r(n) > 3$, and give a conditional criterion forcing $\limsup_{n\to\infty} r(n)>7$.

math.NT↗
arXiv2026

Graph Neural Networks for Generalized Mundlak Estimator under Network Confounding

This paper proposes a generalized Mundlak estimator based on graph neural networks (GME-GNN). The estimator is designed to mitigate bias arising from group-level heterogeneity and to accommodate within-group dependence among individuals. Traditional fixed-effects models handle group heterogeneity via group-specific intercepts, but require overly strict linear additivity and intra-group independence assumptions, and are confined to within-group comparisons. Rather than relying on intercepts, GME-GNN uses aggregated group-level balancing statistics to fully control between-group confounding, enabling valid cross-group comparisons and relaxing linearity constraints. It further employs graph neural network message-passing to adaptively learn nonlinear representations and capture intra-group interaction effects. Theoretical analysis shows that the estimator satisfies double robustness and is asymptotically normal. Simulation and empirical studies confirm its performance.

econ.EM↗
arXiv2026

FedOptima: Optimizing Resource Utilization in Federated Learning

Federated learning (FL) systems facilitate distributed machine learning across a server and multiple devices. However, FL systems have low resource utilization on servers and devices, limiting their practical use in the real world. This inefficiency primarily arises from two types of idle time: (i) task dependency between the server and devices, and (ii) stragglers among heterogeneous devices. This paper introduces FedOptima, a resource-optimized FL system designed to simultaneously minimize both types of idle time; existing systems do not eliminate or reduce both at the same time. FedOptima offloads the training of certain layers of a neural network from a device to a server using three innovations. First, devices operate independently of each other using asynchronous aggregation to eliminate straggler effects, and independently of the server by utilizing auxiliary networks to minimize idle time caused by task dependency. Second, the server performs centralized training using a task scheduler that ensures balanced contributions from all devices, improving model accuracy. Third, an efficient memory management mechanism on the server increases the scalability of the number of participating devices. Extensive experiments are conducted on multiple lab-based testbeds, evaluated on image classification and sentiment analysis tasks with CNNs and Transformers. Compared to four state-of-the-art offloading-based and asynchronous FL baselines, FedOptima (i) achieves higher or comparable accuracy, (ii) accelerates training by 1.9x to 21.8x, (iii) reduces server and device idle time by up to 93.9% and 81.8%, respectively, and (iv) increases throughput by 1.1x to 2.0x.

cs.DC↗
arXiv2026

Unique Decoding of Reed-Solomon and Related Codes for Semi-Adversarial Errors

Motivated by recent developments in coding theory, particular in list-decoding, we introduce a new error model which we call semi-adversarial errors. This error model bridges between fully random errors and fully adversarial errors by allowing some symbols of a message to be corrupted by an adversary while others are replaced with uniformly random symbols. As our main quest, we seek to understand optimal efficient unique decoding algorithms in the semi-adversarial model. For interleaved Reed--Solomon (IRS), folded Reed--Solomon (FRS) and univariate multiplicity codes, we design decoding algorithms running in near-linear time for most mixtures of random and adversarial errors. Our analysis matches the information-theoretic optimum for semi-adversarial errors. Our algorithm for interleaved Reed--Solomon codes is an improved implementation of the decoding algorithm by Bleichenbacher--Kiayias--Yung (BKY) for fully random errors. We use a novel monomial-tracking technique to analyze its performance in this new semi-adversarial errors. Inspired by the BKY algorithm, we use novel interpolations to extend our approach to the settings of folded Reed--Solomon and multiplicity codes, resulting in fast algorithms for unique decoding against semi-adversarial errors. Our new decoders for FRS and multiplicity codes replace the sophisticated root-finding step in traditional algorithms, such as the Guruswami--Wang algorithm, with a straightforward polynomial long division. Analysis of these algorithms requires more robust monomial-tracking arguments than IRS codes.

cs.IT↗
arXiv2026

Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO

We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and direct preference optimization~(DPO). Our study decomposes this gap into two sources: the explicit representation gap under exact optimization and the implicit representation gap under finite samples. In the exact optimization setting, we characterize how the relative capacities of the reward and policy model classes influence the final policy qualities. We show that RLHF, DPO, or online DPO can outperform one another depending on type of model mis-specifications. Notably, online DPO can outperform both RLHF and standard DPO when the reward and policy model classes are isomorphic and both mis-specified. In the approximate optimization setting, we provide a concrete construction where the ground-truth reward is sparse and show that RLHF requires significantly fewer samples than DPO to recover an effective reward model, highlighting a statistical advantage of two-stage learning. Together, these results provide a comprehensive understanding of the performance gap between RLHF and DPO under various settings, and offer practical insights into when each method is preferred.

cs.LG↗
arXiv2026

Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs

Although Large Multimodal Models (LMMs) have achieved strong performance on general video understanding, their susceptibility to textual prior shortcuts during causal discovery has been recognized as a critical deficit. The underlying mechanisms of this phenomenon remain incompletely understood, as existing benchmarks only measure response accuracy without revealing the sources and extent of the deficit. We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis, probing causal discovery through five controlled configurations that systematically manipulate visual and textual modalities to decompose their respective contributions to model behavior and dissect the failure modes. Evaluating 17 mainstream LMMs, we find that models faithfully perceive video content yet systematically underexploit it during causal reasoning. We further observe that stronger post-training amplifies rather than mitigates textual prior reliance, and that higher baseline performance correlates with greater fragility under perturbation. To address these, we propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment, which augments GRPO by explicitly pushing the policy away from a prior-only counterfactual teacher induced by visual corruption. Specifically, ADPO maximizes the divergence between the policy distributions conditioned on the original and visually corrupted inputs, thereby forcing the model to ground its reasoning in visual evidence rather than textual shortcuts. Extensive experiments show that ADPO improves visual engagement without sacrificing fundamental comprehension, thus offering a preliminary step toward reliable causal discovery.

cs.CL↗
arXiv2026

QCP: A Practical Separation Logic-based C Program Verification Tool

As software systems increase in size and complexity dramatically, ensuring their correctness, security, and reliability becomes an increasingly formidable challenge. Despite significant advancements in verification techniques and tools, their practical application to complex, real-world systems is often hindered by critical gaps in both automation and expressiveness. To address these difficulties, this paper presents \textbf{Qualified C Programming Verifier (QCP)}, a novel verification tool that integrates annotation-based automatic verification with interactive proving using Rocq. QCP employs symbolic execution and a separation logic entailment solver to automatically discharge many verification obligations, while deferring more complex obligations to Rocq for manual proof. Furthermore, QCP includes a VS Code extension designed to enhance proof efficiency and support a deeper understanding of both the program behavior and verification outcomes.

cs.PL↗
arXiv2026

Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving

Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning-such as solving Olympiad-level physics problems-remains largely unexplored. Inspired by the way students prepare for competitions by reviewing past problems, we investigate the potential of RAG to enhance physics reasoning in foundation models. We introduce PhoPile, a high-quality multimodal dataset specifically designed for Olympiad-level physics, enabling systematic study of retrieval-based reasoning. PhoPile includes diagrams, graphs, and equations, capturing the inherently multimodal nature of physics problem solving. Using PhoPile, we benchmark RAG-augmented foundation models, covering both large language models (LLMs) and large multimodal models (LMMs) with multiple retrievers. Our results demonstrate that integrating retrieval with physics corpora can improve model performance, while also highlighting challenges that motivate further research in retrieval-augmented physics reasoning.

cs.CL↗
arXiv2026

Evaluating Gender Wage Inequality in Academia using Causal Inference Methods for Observational Data

Observational studies often present challenges for causal inference due to confounding and heterogeneity. In this paper, we illustrate how modern causal inference methods can be applied to large-scale academic salary data. Using records from 12,039 tenure-track faculty in the University of North Carolina system, linked with bibliometric indicators and institutional classifications, we estimate the causal effect of gender on faculty salaries. Our analysis combines propensity score matching with causal forests to adjust for rank, discipline, research productivity, and career experience. Results indicate that female faculty earn approximately 6% less than comparable male colleagues, with variation in the gap across career stages and levels of research productivity. This case study demonstrates how causal inference methods for observational data can provide insight into structural disparities in complex social systems.

stat.AP↗
arXiv2026

Anti-bullying Adaptive Cruise Control: A proactive right-of-way protection approach

Adaptive Cruise Control (ACC) systems have been widely commercialized in recent years. However, existing ACC systems remain vulnerable to close-range cut-ins, a behavior that resembles "road bullying". To address this issue, this research proposes an Anti-bullying Adaptive Cruise Control (AACC) approach, which is capable of proactively protecting right-of-way against such "road bullying" cut-ins. To handle diverse "road bullying" cut-in scenarios smoothly, the proposed approach first leverages an online Inverse Optimal Control (IOC) based algorithm for individual driving style identification. Then, based on Stackelberg competition, a game-theoretic-based motion planning framework is presented in which the identified individual driving styles are utilized to formulate cut-in vehicles' reaction functions. By integrating such reaction functions into the ego vehicle's motion planning, the ego vehicle could consider cut-in vehicles' all possible reactions to find its optimal right-of-way protection maneuver. To the best of our knowledge, this research is the first to model vehicles' interaction dynamics and develop an interactive planner that adapts cut-in vehicle's various driving styles. Simulation results show that the proposed approach can prevent "road bullying" cut-ins and be adaptive to different cut-in vehicles' driving styles. It can improve safety and comfort by up to 79.8% and 20.4%. The driving efficiency has benefits by up to 19.33% in traffic flow. The proposed approach can also adopt more flexible driving strategies. Furthermore, the proposed approach can support real-time field implementation by ensuring less than 50 milliseconds computation time.

eess.SY↗
arXiv2026

SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement

Generative Universal Speech Enhancement (USE) methods aim to leverage generative models to improve speech quality under various types of distortions. However, existing generative speech enhancement methods often suffer from semantic inconsistency in the generated outputs. Therefore, we propose SenSE, a novel two-stage generative universal speech enhancement framework, by modeling semantic priors with a language model, the flow matching-based speech enhancement process is guided to generate semantically faithful speech, thereby effectively improving context fidelity. In addition, we introduce a dual-path masked conditioning training strategy that enables flow matching-based enhancement to flexibly integrate multi-source conditioning signals from degraded speech, semantic tokens, and reference speech, thereby improving model flexibility and adaptability. Experimental results demonstrate that SenSE achieves state-of-the-art performance among generative speech enhancement models and exhibits a high performance ceiling, particularly under challenging distortion conditions. Codes and demos are available at https://github.com/ASLP-lab/SenSE.

eess.AS↗
arXiv2026

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration

Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model could select and execute a correct single tool call. As agent systems evolve, however, the central problem has shifted from isolated invocation to multi-tool orchestration over long trajectories with intermediate state, execution feedback, changing environments, and practical constraints such as safety, cost, and verifiability. We comprehensively review recent progress in multi-tool LLM agents and analyzes the state of the art in this rapidly developing area. First, we unify task formulations and distinguish single-call tool use from long-horizon orchestration. Then, we organize the literature around six core dimensions: inference-time planning and execution, training and trajectory construction, safety and control, efficiency under resource constraints, capability completeness in open environments, and benchmark design and evaluation. We further summarize representative applications in software engineering, enterprise workflows, graphical user interfaces, and mobile systems. Finally, we discuss major challenges and outline future directions for building reliable, scalable, and verifiable multi-tool agents.

cs.SE↗
arXiv2026

Multi-Period Texture Contrast Enhancement for Low-Contrast Wafer Defect Detection and Segmentation

Wafer defect segmentation is pivotal for semiconductor yield optimization yet remains challenged by the intrinsic conflict between microscale anomalies and highly periodic, overwhelming background textures. Existing deep learning paradigms often falter due to feature dilution during downsampling and the lack of explicit mechanisms to disentangle low-contrast defects from process-induced noise. To transcend these limitations, we propose TexWDS, a texture-aware framework that harmonizes multi-scale feature retention with frequency-domain perturbation modeling. Our methodology incorporates three strategic innovations: (1) A Multi-scale Receptive Field Reweighting strategy is introduced to mitigate aliasing effects and preserve high-frequency details of micro-defects often lost in standard pyramidal architectures. (2) The Multi-scale Unified Semantic Enhancer (MUSE) integrates local appearance with global context encoding, effectively enhancing feature discriminability in low-visibility regions. (3) Crucially, we design a plug-and-play Multi-Periodic Texture Contrast Enhancement (MPTCE) module. By modeling texture disruptions in the frequency domain, MPTCE explicitly decouples non-periodic anomalies from structured backgrounds, boosting contrast for camouflaged defects. Extensive experiments on real-world industrial datasets demonstrate that TexWDS achieves a new state-of-the-art, surpassing the baseline by 8.3% in mAP50-95 and 7.7% in recall, while reducing the false positive rate by approximately 8.6%. These results underscore the framework's robustness in handling complex periodic patterns and its suitability for high-precision manufacturing inspection.

cs.CV↗
arXiv2026

Variance-Driven Mean Temperature Reduction in Nonuniformly Heated Radiative-Conductive Systems

Radiative-conductive systems are intrinsically nonlinear due to the quartic temperature dependence of thermal radiation. Under fixed total heating power, convexity arguments imply that nonuniform temperature distributions radiate more efficiently and therefore exhibit a lower mean temperature than their isothermal counterparts. However, this conclusion remains qualitative, and an explicit quantitative relation between temperature heterogeneity and mean temperature reduction has been lacking. Here we derive a variance-based analytical expression linking the area-averaged temperature to the corresponding isothermal equilibrium temperature in a nonuniformly heated radiative--conductive system. By integrating the governing equation and performing a systematic second-order expansion about the ambient temperature, we show that the decrease of the mean temperature relative to the isothermal equilibrium value is linearly proportional to the temperature variance, with a proportionality coefficient set solely by the ambient temperature. This result transforms the convexity-based inequality into a quantitative statistical relation within the perturbative regime and provides a physically transparent framework for describing nonlinear radiative averaging in thermally heterogeneous systems.

quant-ph↗
arXiv2026

Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^π$ Realizability for Deterministic Dynamics

We study computationally and statistically efficient reinforcement learning under the linear $Q^π$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this setting are either computationally intractable, or require (local) access to a simulator. In this paper, we propose a computationally efficient online RL algorithm, named Frozen Policy Iteration, under the linear $Q^π$ realizability setting that works for Markov Decision Processes (MDPs) with stochastic initial states, stochastic rewards and deterministic transitions. Our algorithm achieves a regret bound of $\widetilde{O}(\sqrt{d^2H^6T})$, where $d$ is the dimensionality of the feature space, $H$ is the horizon length, and $T$ is the total number of episodes. Our regret bound is optimal for linear (contextual) bandits which is a special case of our setting with $H = 1$. Existing policy iteration algorithms under the same setting heavily rely on repeatedly sampling the same state by access to the simulator, which is not implementable in the online setting with stochastic initial states studied in this paper. In contrast, our new algorithm circumvents this limitation by strategically using only high-confidence part of the trajectory data and freezing the policy for well-explored states, which ensures that all data used by our algorithm remains effectively on-policy during the whole course of learning. We further demonstrate the versatility of our approach by extending it to the Uniform-PAC setting and to function classes with bounded eluder dimension.

cs.LG↗
arXiv2026

MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acoustically similar sources. We introduce a preference alignment perspective, analogous to aligning LLMs with human intent. To address this, we introduce MARS-Sep, a reinforcement learning framework that reformulates separation as decision making. Instead of simply regressing ground-truth masks, MARS-Sep learns a factorized Beta mask policy that is steered by a preference reward model and optimized by a stable, clipped trust-region surrogate. The reward, derived from a progressively-aligned audio-text-vision encoder, directly incentivizes semantic consistency with query prompts. Extensive experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation, with notable improvements in signal metrics and semantic quality. Our code is available at https://github.com/mars-sep/MARS-Sep. Sound separation samples are available at https://mars-sep.github.io/.

cs.SD↗
arXiv2026

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Post-training quantization (PTQ) compresses the weights and activations of large language models (LLMs) into low-precision representations to reduce memory footprint and accelerate inference. However, the presence of outliers in weights and activations often leads to large quantization errors and severe accuracy degradation, especially in recent reasoning LLMs where errors accumulate across long chains of thought. Existing PTQ methods either fail to sufficiently suppress outliers or introduce significant overhead during inference. In this paper, we propose Pairwise Rotation Quantization (ParoQuant), a PTQ method that combines hardware-efficient and optimizable independent Givens rotations with channel-wise scaling to even out the magnitudes across channels and narrow the dynamic range within each quantization group, effectively addressing the outlier issue. We further co-design the inference kernel to fully exploit GPU parallelism and keep the rotations and scaling lightweight at runtime. Under weight-only quantization, ParoQuant achieves an average 2.4% accuracy improvement over AWQ on reasoning tasks, with less than 10% overhead. ParoQuant also matches the accuracy of state-of-the-art weight-activation quantization methods. This paves the way for more efficient and accurate deployment of reasoning LLMs.

cs.CL↗