Searcharxiv⌕ Search

arXiv subjects

Jiale Chen

Publications and source records attributed to Jiale Chen.

At least 19 recordsLinked to original sources
arXiv2026

LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents

As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning errors cascade into fabricated holdings and miscited authority. However, existing legal benchmarks evaluate only single-turn QA with outcome-level metrics, while agentic hallucination benchmarks lack legal-specific diagnostic capability. Neither answers to what extent and how a legal agent hallucinates along its trajectory. To address these limitations, we introduce LexAgentHallu, a legal agentic hallucination benchmark designed to evaluate to what extent and how legal agents fail along multi-step trajectories. Built through a four-stage expert-in-the-loop pipeline, LexAgentHallu contains 3414 instances across 17 legal categories and 6 task types. Each instance is annotated under a dual-layer hallucination taxonomy of 7 high-level categories and 27 fine-grained subclasses, covering both substantive errors and agent-procedural failures. We further design fine-grained metrics that quantify to what extent and localize how each failure occurs along an agent's execution path. Our evaluation across 18 proprietary and open-source agents uncovers a Right-Answer-Wrong-Reason effect and reveals that hallucination subclasses cluster rather than scatter, forming distinct agentic framework, legal task, and category profiles. These findings, invisible to outcome-level evaluation, validate the diagnostic power of LexAgentHallu for evaluating agentic hallucination in law.

cs.AI↗
arXiv2026

Area operators on Hardy spaces of Dirichlet series II: counterexamples and compactness criteria

We study the area operators $\mathbb{A}_{\mu,l}$, $0<l<\infty$, induced by positive Borel measures on the right half-plane and acting on the Hardy spaces of Dirichlet series $\mathscr H^p$, $0<p<\infty$. We first disprove a conjecture proposed by the present authors in an earlier work by constructing a probability measure, valid for all $0<p,l<\infty$, for which the associated area operator is bounded although the measure fails the proposed Carleson conditions. We next investigate compactness of these operators. For every $0<p<\infty$, we characterize boundedness and compactness of $\mathbb{A}_{\mu,p}$ on both $\mathscr H^p$ and the Hardy space $\mathscr H^p_0$ of Dirichlet series vanishing at $+\infty$; in particular, boundedness and compactness coincide for these operators. For general $0<p,l<\infty$, we further establish sufficient conditions for compactness in terms of vanishing Carleson measures and compact $H_{\mathrm i}^p$-Carleson embeddings. As an application, we also give a different proof of a known compactness result for Volterra operators on $\mathscr H^p$ with Dirichlet series symbols in $\operatorname{VMOA}(\mathbb C_0)$.

math.FA↗
arXiv2026

The Power of Local Marginals: An $O(\varepsilon^{-1})$-Aspect-Ratio Reduction for Dynamic Weighted Matching

We study dynamic maximum weight matching (MWM) under edge insertions and deletions in two settings: maintaining a $(1\pm\varepsilon)$-approximation to the optimum weight, and maintaining an explicit $(1-\varepsilon)$-approximate matching. Our main result is a reduction that transforms instances of polynomial aspect ratio into instances of aspect ratio $O(\varepsilon^{-1})$. The reduction applies to general graphs in both settings and is compatible with partially dynamic updates. The reduction is based on a structural property of local marginals. After grouping edges into weight classes, the global marginal contribution of one class relative to all lower classes is approximated by its marginal contribution within a local weight window of aspect ratio $O(\varepsilon^{-1})$. Summing these local marginals yields a value composition lemma that uses only approximate optimum values of the local windows. This improves the value reduction of Gupta and Peng (FOCS 2013), whose local aspect ratio is $\varepsilon^{-\Theta(\varepsilon^{-1})}$. The same structural property yields an improved matching composition lemma for explicit matchings, reducing the local aspect ratio of Bernstein--Chen--Dudeja--Langley--Sidford--Tu (SODA 2025) from $O(\varepsilon^{-2})$ to $O(\varepsilon^{-1})$.

cs.DS↗
arXiv2026

GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding

Adaptive rounding methods such as GPTQ, or equivalently Babai's nearest plane algorithm, round a real matrix to integers under a quadratic metric. They process the entries in a fixed order, one at a time, propagating each rounding error to the entries not yet processed through a triangular feedback matrix. We study the two-sided version of this task, in which fixed nonsingular basis matrices act on both the left and the right of the residual; the familiar one-sided case is the special case of an identity right basis. Vectorizing the matrix turns the two-sided objective into a quadratic metric whose Gram matrix is a Kronecker product, so the one-dimensional algorithm applies verbatim, but takes quartic time in the matrix dimension. We present GPTQ-2D, which produces the identical rounded matrix in cubic time. It rounds the entries anti-diagonal by anti-diagonal; entries on the same anti-diagonal are independent and are rounded in parallel.

cs.DS↗
arXiv2026

Biodegradable, Millimeter-Scale Light-Emitting Sensors for Distributed Environmental Monitoring-Functional Pixie Dust

Methods for large-area, precise monitoring across natural environments are of growing interest due to pressing needs for sustainable management of rapidly increasing anthropogenic activities. Established approaches involve sparse spatial sampling and/or sequential measurements, while emerging techniques exploit miniaturized electronics or passive optical methods. Various constraints in scalability, costs, robustness, operational range and other factors create a need for alternatives. Here, we introduce a concept that overcomes many of these limitations through the combined use of chemically induced light emission and chemically responsive optical filter elements in millimeter-scale systems that we refer to as functional pixie dust (fPD) sensors, designed specifically for monitoring natural water systems during nighttime to eliminate background optical interference and to enhance remote analysis. These floating devices act as Lagrangian tracers to follow surface flows and to simultaneously measure the concentrations of key chemical species along their trajectories. Optimized designs exploit environmentally compatible constituent materials that are also degradable through natural processes to benign end products, thereby eliminating the need for recovery. Spatially and spectrally resolved ratiometric measurement schemes ensure robust operation and ability to address practical requirements in range, operational lifetime, time response and sensitivity. Demonstrations include distributed measurements of pH, Hg2+, and NO2-, each of relevance to industrial discharge, toxic metal contamination, and nitrogen-rich runoff, adapted for static concentration gradients, flow-driven transport conditions, and outdoor aquatic settings. The results establish a framework for environmental sensing using degradable, self-powered microsystems capable of scalable deployment and remote readout.

physics.app-ph↗
arXiv2026

TopoGS: Planar Reconstruction via Topology-aware 3D Gaussian Splatting

Extracting structured, parametric 3D representations from raw images remains a fundamental challenge in computer vision and graphics. While recent advancements in the 3D Gaussian Splatting (3DGS) pipeline integrate planar primitives to yield compact and editable geometry, these approaches typically treat planes as isolated, discrete sets. This lack of topological connectivity hinders robust geometric reasoning, leading to fragmented reconstructions and misaligned boundaries that fall short of the precision for rigorous spatial analysis and professional design workflows. To address this, we introduce TopoGS, the first 3DGS framework to explicitly integrate both planar and topological constraints for coherent 3D reconstruction. Specifically, we extract global 2D topological relationships from multi-view image segmentations and anchor Gaussian primitives to these structural elements. This formulation enables the joint optimization of plane parameters, rendering fidelity, and topological adjacency. By enforcing strict multi-view consistency alongside these topological constraints, our method significantly mitigates geometric misalignments and produces connected, structured 3D models. Extensive evaluations on the ScanNet++ dataset demonstrate that TopoGS achieves state-of-the-art performance, providing a highly robust solution for generating accurate, topologically sound, and visually faithful scene representations.

cs.CV↗
arXiv2026

Reverse Carleson inequalities for weighted Fock spaces with $A_{\infty}$-type weights

We characterize dominating sets for weighted Fock spaces $F^p_{\alpha,w}$ induced by Muckenhoupt $A_{\infty}$ weights, which leads to a sufficient condition for reverse Carleson measures for the spaces $F^p_{\alpha,w}$ with restricted $A_{\infty}$ weights. Applications to invertibility of Toeplitz operators, closed range property of Volterra operators, and atomic decomposition of $F^p_{\alpha,w}$ are given.

math.CV↗
arXiv2026

AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle

Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review responses across long project cycles. The rise of LLM-based scientific agents creates an opportunity to automate this process. Such a system must support the full research lifecycle, maintain structured persistent memory across projects, and improve its own research procedures over time. However, existing systems either partially satisfy or fail to satisfy these requirements, leaving a gap for a unified automated scientific research system. As a result, we present AutoSci, a memory-centric agentic system for the full scientific research lifecycle. AutoSci is organized around four modules. SciMem provides schema-governed research memory, separating Long-Term Knowledge Memory for reusable scientific knowledge from Active Research Memory for project-level artifacts such as ideas, experiments, manuscripts, and reviews. SciFlow executes a five-stage lifecycle from literature understanding to rebuttal through a harness that controls state, context, verification, feedback, and orchestration. SciDAG augments difficult skills with DAG-shaped multi-agent operators and reusable stage-specific templates. SciEvolve converts feedback signals from users, experiments, reviews, and external environments into versioned updates to SciMem organization, SciFlow skills, and SciDAG templates. Together, these modules make AutoSci a persistent research environment that can execute, remember, and evolve across research projects. The code repository is available at https://github.com/skyllwt/AutoSci.

cs.AI↗
arXiv2026

Hubbard-$U$-corrected electron-phonon interactions in strongly correlated materials via the finite-displacement method

Although the density functional theory plus Hubbard $U$ correction method (DFT+$U$) is broadly used to study electronic structure of strongly correlated materials, the extension of this method to electron-phonon $g$ matrices has received limited attention. Here, we implement an algorithm that integrates DFT+$U$ method with the finite-displacement method for the calculations of phonons and electron-phonon $g$ matrices. The Hubbard $U$ corrections are applied not only to electronic and phonon structures, but, more importantly, also to electron-phonon $g$ matrices. We demonstrate our algorithm in two prototypical correlated materials: infinite-layer nickelates LaNiO$_2$ and ruthenium dioxide RuO$_2$. We find that: i) While the Hubbard $U$ corrections weakly increase the electron-phonon interaction of 20% hole-doped LaNiO$_2$, its total electron-phonon coupling remains small and is insufficient to account for the observed superconducting transition temperature of about 10-30 K. Our results contrast with the recent work showing that the full GW corrections yield an elevated electron-phonon coupling of 20% hole-doped LaNiO$_2$ five times larger than its DFT value. We attribute this discrepancy to the differences in the Fermi surface topology between DFT+$U$ and GW methods. ii) The inclusion of Hubbard $U$ corrections eliminates the imaginary phonon modes of RuO$_2$ under strain on the TiO$_2$ substrate and substantially reduces the electron-phonon coupling. Our results alleviate the discrepancy between the reported large theoretical electron-phonon coupling and the low superconducting transition temperature observed experimentally. Our work provides an algorithm that fully includes the Hubbard $U$ corrections on electron-phonon properties of correlated materials, and highlights the importance of Fermi surface shape and correlation effects on phonon spectrum and electron-phonon $g$ matrices.

cond-mat.str-el↗
arXiv2026

Nearly perfect Fermi surface nesting in hole-doped La$_3$Ni$_2$O$_7$ enables bulk superconductivity without pressure or strain

The discovery of high-temperature superconductivity in Ruddlesden-Popper nickelates has drawn great attention. However, unlike cuprates and iron-based superconductors, Ruddlesden-Popper nickelates exhibit superconductivity either under high pressure in bulk samples or under compressive strain in thin films. Genuine bulk superconductivity under ambient pressure has remained elusive in these materials, precluding key measurements such as specific heat and superfluid density. In this work, we combine density-functional-theory, dynamical-mean-field-theory, and random-phase-approximation to solve the superconducting gap equation for bulk hole-doped bilayer nickelate La$_{3-x}$Sr$_x$Ni$_2$O$_7$ at ambient pressure. We find that hole doping induces a Ni-$d_{3z^2-r^2}$-derived $\gamma$ pocket on the Fermi surface, and serves as a tuning parameter for both its size and \textit{shape}. As $x$ approaches 0.4, the $\gamma$ pocket evolves from circular to diamond-shaped and expands to span half of the Brillouin zone, resulting in nearly perfect Fermi surface nesting with the optimal nesting vector $\textbf{Q} = (\pi, \pi)$. This, in turn, strongly enhances antiferromagnetic spin fluctuations and substantially increases the leading superconducting eigenvalue to a level at which superconductivity becomes experimentally observable. Our work provides both a robust mechanism and an experimentally feasible route to inducing the long-sought bulk superconductivity in La$_3$Ni$_2$O$_7$ without pressure or strain.

cond-mat.supr-con↗
arXiv2026

Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming

We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thinking. During RL training, we observe an approximately log-linear relationship between validation accuracy and the average number of generated reasoning tokens over successive checkpoints, and show two ways to shift this training trajectory: verification RL warmup raises the starting point, while randomized clipping produces a steeper trend in the observed regime. As scaling single-generation reasoning during RL quickly becomes expensive under full attention, we introduce a multi-round parallel thinking pipeline that distributes the token budget across threads and rounds of generation, verification, and refinement. We train the model end-to-end on this pipeline to match the training objective to the test-time structure. Starting from Seed-OSS-36B, the full system with 16 threads and 16 rounds per thread matches the underlying RL model's oracle pass@16 at pass@1 using 7.6 million tokens per problem on average, and surpasses GPT-5-high on 456 hard competitive programming problems from AetherCode.

cs.CL↗
arXiv2026

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

We present MedXIAOHE, a medical vision-language foundation model designed to advance general-purpose medical understanding and reasoning in real-world clinical applications. MedXIAOHE achieves state-of-the-art performance across diverse medical benchmarks and surpasses leading closed-source multimodal systems on multiple capabilities. To achieve this, we propose an entity-aware continual pretraining framework that organizes heterogeneous medical corpora to broaden knowledge coverage and reduce long-tail gaps (e.g., rare diseases). For medical expert-level reasoning and interaction, MedXIAOHE incorporates diverse medical reasoning patterns via reinforcement learning and tool-augmented agentic training, enabling multi-step diagnostic reasoning with verifiable decision traces. To improve reliability in real-world use, MedXIAOHE integrates user-preference rubrics, evidence-grounded reasoning, and low-hallucination long-form report generation, with improved adherence to medical instructions. We release this report to document our practical design choices, scaling insights, and evaluation framework, hoping to inspire further research.

cs.CL↗
arXiv2026

What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the thinking with images paradigm has emerged, enabling models to dynamically edit and re-encode visual information at each reasoning step, mirroring human visual processing. However, this paradigm introduces significant challenges as diverse errors may occur during reasoning processes. This necessitates Process Reward Models (PRMs) for distinguishing positive and negative reasoning steps, yet existing benchmarks for PRMs are predominantly text-centric and lack comprehensive assessment under this paradigm. To address these gaps, this work introduces the first comprehensive benchmark specifically designed for evaluating PRMs under the thinking with images paradigm. Our main contributions are: (1) Through extensive analysis of reasoning trajectories and guided search experiments with PRMs, we define 7 fine-grained error types and demonstrate both the necessity for specialized PRMs and the potential for improvement. (2) We construct a comprehensive benchmark comprising 1,206 manually annotated thinking with images reasoning trajectories spanning 4 categories and 16 subcategories for fine-grained evaluation of PRMs. (3) Our experimental analysis reveals that current LVLMs fall short as effective PRMs, exhibiting limited capabilities in visual reasoning process evaluation with significant performance disparities across error types, positive evaluation bias, and sensitivity to reasoning step positions. These findings demonstrate the effectiveness of our benchmark and establish crucial foundations for advancing PRMs in LVLMs.

cs.CV↗
arXiv2026

Embedding theorems and integration operators on Hardy--Carleson type tent spaces induced by doubling weights

This paper develops the function and operator theory of Hardy--Carleson--type analytic tent spaces $AT_q^\infty(\omega)$ induced by radial weights $\omega$ satisfying a two-sided doubling condition. We first characterize the positive Borel measures $\mu$ for which the embedding from $AT_p^\infty(\omega)$ into the tent space $T_q^\infty(\mu)$ is bounded for all $0 < p, q < \infty$. A Littlewood--Paley formula for $AT_q^\infty(\omega)$ is then established. Using these results, we give a complete characterization of the boundedness (compactness) of Volterra-type integration operators between $AT_p^\infty(\omega)$ and $AT_q^\infty(\omega)$.

math.CV↗
arXiv2026

Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment

Despite remarkable capability in multi-modal understanding, deploying Multi-modal Large Language Models (MLLMs) in open-ended conversational scenarios introduces safety risks that remain poorly addressed by existing alignment methods. Unlike simple malicious visual question and answer (VQA) pairs , multi-turn interactions enable adversaries to incrementally reconstruct harmful intent across dialogues, progressively bypassing safety constraints in ways that are difficult to detect at any individual turn. Meanwhile, conventional reinforcement learning from human feedback (RLHF) approaches are unsuitable for this situation: designed primarily for VQA tasks, they neither capture cross-turn risk dynamics nor scale efficiently without costly manual preference annotation. To close this gap, we introduce \textbf{MINT-Safe}, an open-source visual multi-turn training dataset comprising 11,270 multi-image dialogues and 500 refusal VQA pairs, constructed via multi-agent interaction with text-to-image (T2I) tool-call augmentation. Building on MINT-Safe, we propose \textbf{TAD-Align}, a dialogue safety alignment framework centered on a turn-aware dual-objective reward function. Rather than treating all dialogue turns uniformly, TAD-Align leverages rollout-based safety score variance to dynamically identify turns where the model exhibits inconsistent safety behavior, and adaptively up-weights these turns during optimization. Experiments on Qwen2.5-VL-7B-Instruct and LLaVA-NeXT-7B demonstrate reductions of over 10\% in Attack Success Rate (ASR), alongside improvements of at least 8\% in harmlessness and 13\% in helpfulness on multi-modal multi-turn safety benchmarks, while preserving general model capabilities.

cs.CL↗
arXiv2025

A Comprehensive Study of Bugs in Modern Distributed Deep Learning Systems

In today's data-driven era, deep learning is vital for processing massive datasets, yet single-device training is constrained by computational and memory limits. Distributed deep learning overcomes these challenges by leveraging multiple GPUs or machines in parallel. While general-purpose frameworks (e.g., TensorFlow and PyTorch) provide distributed capabilities, these are often add-on features that demand significant manual effort for advanced parallelism, underscoring the need for specialized frameworks. This study conducts the first large-scale empirical analysis of practitioner challenges in dedicated distributed frameworks. We examine 849 real-world issues from DeepSpeed, Megatron-LM, and Colossal-AI and construct a taxonomy of 34 bug symptoms, 28 root causes, and 6 fix patterns. Crucially, we establish explicit mappings between symptoms, causes, and fixes across distributed training stages, enabling a systematic understanding of how issues emerge and are resolved. Our results show that 45.1\% of bug symptoms are unique to distributed frameworks, with setup failures, memory issues, and performance anomalies being the most prevalent. Moreover, 95\% of issues in the communication setup stage occur exclusively in distributed contexts. We also find over 60\% of cases can be resolved through version and dependency management, and distributed feature, API, and communication tuning. Based on these findings, we provide actionable implications.

cs.SE↗
arXiv2025

Toeplitz operators on weighted Fock spaces with $A_{\infty}$-type weights

By establishing some reproducing kernel estimates, we characterize the bounded, compact and Schatten $p$-class Toeplitz operators with positive measure symbols on the weighted Fock space $F^2_{\alpha,w}$ for $p\geq1$, where $w$ is a weight on the complex plane satisfying an $A_{\infty}$-type condition. Applications to Volterra operators and weighted composition operators are given.

math.FA↗
arXiv2025

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors. Prior transform-based mitigations (e.g., Hadamard rotations) are fixed and data-agnostic, and their optimality for quantization has remained unclear. We derive closed-form optimal linear blockwise transforms for joint weight-activation quantization under standard RTN AbsMax-scaled block quantizers, covering both integer and floating-point formats. The resulting construction, WUSH, combines a Hadamard backbone with a data-dependent second-moment component to form a non-orthogonal transform that is provably near-optimal for FP and INT quantizers under mild assumptions while admitting an efficient fused GPU implementation. Empirically, WUSH improves W4A4 accuracy over the strongest Hadamard-based baselines (e.g., on Llama-3.1-8B-Instruct in MXFP4, it gains +2.8 average points with RTN and +0.7 with GPTQ) while delivering up to 5.8$\times$ per-layer throughput over BF16 via FP4 MatMul. Source code is available at https://github.com/IST-DASLab/WUSH.

cs.LG↗