arXiv subjects

Hanchen Wang

Publications and source records attributed to Hanchen Wang.

At least 19 recordsLinked to original sources

arXiv2026

ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex reasoning paths of multi-hop question answering (QA). Graph-based RAG captures multi-step relationships but suffers from severe semantic drift and high online latency due to noisy global graph traversals. Thus, we propose ISO-RAG (ISOperimetric Retrieval-Augmented Generation), a geometry-aware RAG framework. By projecting the underlying knowledge graph into a hyperbolic Poincare ball to precompute node-wise isoperimetric profiles, ISO-RAG prunes spurious edges during retrieval, restricting the search space to a strictly localized subgraph. This topological purification regulates Personalized PageRank (PPR) diffusion driving the retrieval process, ensuring exact and low-latency convergence. Experiments on multi-hop QA benchmarks demonstrate that ISO-RAG outperforms state-of-the-art baselines by average absolute gains of 10.0% in retrieval recall and 4.3% in downstream exact match, achieving a superior accuracy-efficiency trade-off by fundamentally eliminating the latency bottleneck of global traversals. Our source code is available at https://github.com/ZaiizaiZHANG/ISO-RAG.

cs.AI↗

arXiv2026

MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques

Long-form song generation models continue to improve in duration, structural integrity, and acoustic complexity, making reliable aesthetic rewards increasingly important for aligning these models with human preferences. However, reward models for complete songs remain limited, and existing evaluators typically predict scores in a single forward pass without providing readable explanations. We introduce MUSECRITIC, a semi-scalar reward model that generates a natural-language critique covering five aesthetic dimensions and uses it as an intermediate representation to predict continuous reward scores. MUSECRITIC follows a two-stage training pipeline: a teacher model first provides high-quality critiques for supervised fine-tuning, after which the fine-tuned model generates its own critiques for reward learning, mitigating distribution shift between training and inference. On an in-domain test set of 200 SongEval songs, MUSECRITIC reduces macro-averaged mean squared error from 0.2875 to 0.2316 and improves macro-averaged LCC, SRCC, and Kendall's tau to 0.9068, 0.8838, and 0.7178, respectively. On the out-of-domain Music Arena benchmark with 733 preference pairs, it achieves the highest accuracy of 71.35%. Moreover, using MUSECRITIC with GRPO improves Muse-0.6B on all nine aesthetic metrics from SongEval and Audiobox Aesthetics. These results demonstrate that critique-conditioned reward modeling reduces scoring error and provides an effective optimization signal for song generation. The project repository is available at https://github.com/WuqnEl/MuseCritic.

cs.SD↗

arXiv2026

Multivariate Time Series Forecasting needs Cross Variable Loss

Multivariate time series forecasting presents unique challenges because future variables often co-evolve under shared system dynamics. While existing studies mainly focus on cross-variable dependencies in historical observations, dependencies among future values are much less explored. Specifically, modern forecasting models largely follow the Direct Forecasting (DF) paradigm, generating multi-step forecasts with point-wise objectives that do not explicitly constrain cross-variable structure. In this work, we show that the DF objective is mismatched in the presence of cross-variable and lagged dependencies, revealing an objective gap. To address this issue, we propose \textbf{C}ross-\textbf{V}ariable \textbf{Loss} (CvLoss), a plug-in structural regularizer that constrains forecast residuals on a cross-variable graph. CvLoss penalizes inconsistent edge-wise residual differences over forecast patches, encouraging consistency across both synchronous and asynchronous interactions. Our experiments show that CvLoss consistently improves competitive forecasting models, outperforms representative learning objectives, and is compatible with a variety of forecasting backbones.

cs.LG↗

arXiv2026

MUX-USCT: A Noise-Robust Neural Network for Ultrasound Computed Tomography

Deep neural networks (DNNs) have shown strong potential for ultrasound computed tomography (USCT) reconstruction in ideal noise-free environments, yet existing DNNs are vulnerable to the noisy conditions in clinical practice, as they equally treat inputs that suffer mild, moderate, or severe noise. More challenging, the distributions of noise shift along with the environment, indicating the less effectiveness of noise-aware training, which injects a specific noise distribution into the training data. We rethink these challenges and observe that the DNN models can become more robust to noise if we know the noise sources and filter them out. This filtering operation is very alike the Multiplexers (or MUX), a fundamental combinational circuit in digital logic design. However, the challenge here is that noise can happen randomly during inference; as a result, the manually predefined MUX cannot work. To address these challenges, we propose MUX-USCT, a novel encoder-decoder DNN architecture that encodes the known acoustic acquisition geometry with an "adaptive MUX" that can automatically identify and filter noise, where the attention mechanism is applied in reconstructing the speed-of-sound map. On the OpenPros benchmark, MUX-USCT reaches 6.88 m/s MAE with 17% fewer parameters than the leading baseline with 7.65 m/s of MAE. Under simulated clinical noise, it remains stable across diverse degradation types that cause geometry-agnostic baselines to fail. Results show that the attention distributions in MUX-USCT provide interpretable indicators of the signal quality between pairs of transducers.

eess.IV↗

arXiv2026

Algebraic Subgraph Counting

Subgraph isomorphism counting is a fundamental problem in graph analytics, which aims to find the number of subgraph isomorphisms of a query graph in a data graph. The candidate tree-based framework provides a promising foundation for subgraph counting tasks, offering a unified counting paradigm that can be extended beyond tree patterns. However, supporting subgraph isomorphism within this framework remains challenging, as it requires handling both the non-tree edge constraint and the injective mapping constraint. Although existing solutions employ sampling or learning techniques to address these constraints in this framework, they still either suffer from inherent sampling failures or rely heavily on supervision. In this paper, we propose ASC, an algebraic subgraph counting approach built on the candidate tree-based counting framework. In our method, the non-tree edge constraint is directly incorporated into the candidate tree-based counting process through a matrix-based computation method, enabling subgraph homomorphism counting with high accuracy in polynomial time. Based on the resulting subgraph homomorphism count, we further apply a local sampling method to address the injective mapping constraint, thereby obtaining the final subgraph isomorphism count. Extensive experiments show that ASC can achieve substantially better and more stable performance over the baselines across various datasets, while scaling to billion-edge graphs. Most impressively, as a non-learning method, ASC can even achieve more than an order of magnitude higher average accuracy than the state-of-the-art learning-based method FlowSC with similar efficiency. This paper is the full version of the work accepted at SIGMOD 2027. The code is available at https://github.com/EricaGuoQiuyu/AlgebraicSubgraphCounting.

cs.DB↗

arXiv2026

OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios

Hallucination detection is essential for the reliable deployment of large language models (LLMs). However, existing evaluations face two core challenges: inconsistent inference configuration and evaluation, and limited coverage of downstream domains and tasks. Consequently, reported detector performance is often difficult to compare, reproduce, and generalize beyond specific experimental settings. We introduce OpenHalDet, a unified benchmark for hallucination detection across diverse generation scenarios. OpenHalDet standardizes the evaluation pipeline, from prompt construction and response generation to truthfulness annotation, detector scoring, and metric computation. It supports heterogeneous detector families under different access settings, including black-box methods that use only generated outputs, gray-box methods that rely on probability-based signals, and white-box methods that exploit internal model signals. By bringing diverse tasks, models, and detectors into a shared framework, OpenHalDet enables controlled comparison and provides a systematic view of how different detection paradigms behave in LLM applications. We release OpenHalDet as an open and extensible codebase to facilitate reproducible evaluation and future development of hallucination detection methods. The code and datasets are available at https://github.com/Nellie179/Hallucination-Detection.

cs.CL↗

arXiv2026

Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution.

cs.MA↗

arXiv2026

EXG: Self-Evolving Agents with Experience Graphs

Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during execution rarely translating into systematic improvement over time. In response, a growing line of work on self-evolving agents explores how agents can improve through experience during deployment, but most existing approaches either rely on ad hoc reflection limited to single-task correction or adopt unstructured memory that accumulates fragmented experience with delayed usability. To address this limitation, we introduce EXG, an experience graph framework for self-evolving agents that explicitly organizes accumulated successes and failures into a structured, relational representation. EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module. This design also enables EXG to serve as a plug-and-play component for existing self-evolving agents, organizing prior experience into a unified experience graph and improving both solution quality and resource efficiency as deployment progresses. Extensive experiments across code generation and reasoning benchmarks show that EXG attains more favorable performance-efficiency trade-offs than reflection- and memory-based baselines in both online and offline evaluations. Our results suggest that structuring experience as a graph provides a principled foundation for scalable and transferable self-evolving agent behavior.

cs.AI↗

arXiv2026

GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model

Conditional generative models, particularly diffusion-based methods, have recently been applied to graph prediction by modeling the target as a conditional distribution given the input graph, yielding competitive results compared to deterministic predictor. However, existing diffusion-based prediction methods typically require expensive iterative denoising at inference and often suffer from unstable sampling, which motivates recent efforts to reduce inference denoising steps and enable stable sampling via techniques such as consistency training. Despite this progress, we find that existing consistency training methods for graph prediction could potentially fall into a shortcut solution: the model may attempt to satisfy the self-consistency constraint by ignoring the noisy target (i.e., assigning it negligible weight), ultimately collapsing into a purely deterministic predictor. To mitigate such shortcut solution, we propose GCCM, a graph contrastive consistency model that goes beyond isolated pairwise matching between the same target at different noise levels by introducing negative pairs into a contrastive consistency objective. This adds an additional separation requirement, making the shortcut solution no longer trivially sufficient to satisfy the proposed objective. Moreover, we apply feature perturbation to the input node/edge features to break identical conditioning on the input graph, so that the shortcut no longer yields the same predictions across noise levels and becomes less attractive. Extensive experiments on benchmark datasets demonstrate that GCCM mitigates the shortcut solution and yields consistent performance improvements in graph prediction compared to deterministic predictors.

cs.AI↗

arXiv2026

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training

Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In this work, we challenge this assumption and introduce NoiseRater, a meta-learning framework for instance-level noise valuation in diffusion model training. We propose a parametric noise rater that assigns importance scores to individual noise realizations conditioned on data and timestep, enabling adaptive reweighting of the training objective. The rater is trained via bilevel optimization to improve downstream validation performance after inner-loop diffusion updates. To enable efficient deployment, we further design a decoupled two-stage pipeline that transitions from soft weighting during meta-training to hard noise selection during standard training. Extensive experiments on FFHQ and ImageNet demonstrate that not all noise samples contribute equally, and that prioritizing informative noise improves both training efficiency and generation quality. Our results establish noise valuation as a complementary and previously underexplored axis for improving diffusion model training. Our code is available at: https://anonymous.4open.science/r/NoiseRater-DEB116.

cs.LG↗

arXiv2026

Proteo-R1: Reasoning Foundation Models for De Novo Protein Design

Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or interactions are functionally essential. As a result, design decisions are entangled with continuous sampling dynamics, limiting interpretability, controllability, and systematic reuse of biochemical knowledge. We introduce Proteo-R1, a reasoning-guided protein design framework that explicitly decouples molecular understanding from geometric generation. Proteo-R1 adopts a dual-expert architecture in which a multimodal large language model (MLLM) serves as an understanding expert, analyzing protein sequences, structures, and textual context to identify key functional residues that govern binding and specificity. These residue-level decisions are then passed as hard constraints to a separate diffusion-based generation expert, which performs conditional co-design while respecting the fixed interaction anchors. This factorization mirrors how human experts approach molecular engineering: first, reasoning about critical interactions, then optimizing geometry subject to those constraints. By operationalizing reasoning as explicit residue-level commitments rather than latent textual guidance, Proteo-R1 achieves stable, interpretable, and modular integration of LLM reasoning with state-of-the-art geometric generative models. Code, data, and demos are available at https://smiles724.github.io/r1/.

cs.LG↗

arXiv2026

Coherent Microwave Driving of Domain Wall Depinning in a Ferrimagnetic Garnet

Coherent control of domain wall dynamics offers a route to fast manipulation of magnetic textures beyond thermally activated motion. We demonstrate resonant excitation of linear and nonlinear dynamics of a pinned domain wall in a ferrimagnetic garnet thin film driven by a microwave field. Using scanning nitrogen-vacancy magnetometry and nonlocal spin-pumping measurements, we identify a low-frequency mode inside the magnon gap, originating from the localized oscillatory motion of a domain wall across a pinning line defined by a Pt stripline. Upon increasing the microwave drive into the nonlinear regime, this mode enables domain wall depinning at reduced external magnetic fields. Micromagnetic simulations reveal a progression from localized oscillations to partial relocation between pinning sites and, ultimately, complete escape from the pinning region with increasing driving power. These results establish resonant excitation of domain walls at engineered pinning sites as a mechanism for manipulating magnetic textures via localized nonlinear dynamics.

cond-mat.mes-hall↗

arXiv2026

Disambiguating electrical detection of magnetization dynamics in magnetic insulators

Electrical detection of magnetization dynamics in magnetic insulators underpins both fundamental studies of magnon transport and the development of low-loss magnonic devices. In heavy-metal/magnetic-insulator heterostructures, spin pumping and spin-torque ferromagnetic resonance (ST-FMR) are widely used for this purpose and are often treated separately in different measurement geometries. In practice, the competition between these two effects gives rise to electrical voltage signals of opposite signs, which can lead to ambiguous interpretations of the underlying physics. Here, we show how to disambiguate their respective contributions and provide a framework for interpreting experiments involving microwave excitation of magnetic insulators and detection of magnetization dynamics via spin-charge conversion in heavy metals. We systematically investigate spin pumping and ST-FMR in nonlocal and local devices using Pt-capped thin films of thulium and bismuth-yttrium iron garnets. We show how spin-wave character, magnetic dissipation, magnetic field orientation and device geometry govern the sign and magnitude of the resulting signals. In several cases, the voltage generated by microwave excitation changes sign between an out-of-plane or in-plane magnetic configuration. We disentangle a contribution due to spin pumping, induced by exponentially decaying propagating spin waves, and a weakly distance-dependent contribution from ST-FMR, remotely induced by inductive coupling. We show that both the spin wave excitation profile across the film thickness and magnetic damping largely determine which of the two contributions dominates. Hence, the sign of the electrical signal cannot be uniquely assigned to the chirality of the magnon modes.

cond-mat.mes-hall↗

arXiv2026

Advancing AI Research Assistants with Expert-Involved Learning

Large language models (LLMs) and large multimodal models (LMMs) promise to accelerate biomedical discovery, yet their reliability remains unclear. We introduce ARIEL (AI Research Assistant for Expert-in-the-Loop Learning), an open-source evaluation and optimization framework that pairs a curated multimodal biomedical corpus with expert-vetted tasks to probe two capabilities: full-length article summarization and fine-grained figure interpretation. Using uniform protocols and blinded PhD-level evaluation, we find that state-of-the-art models generate fluent but incomplete summaries, whereas LMMs struggle with detailed visual reasoning. We later observe that prompt engineering and lightweight fine-tuning substantially improve textual coverage, and a compute-scaled inference strategy enhances visual question answering. We build an ARIEL agent that integrates textual and visual cues, and we show it can propose testable mechanistic hypotheses. ARIEL delineates current strengths and limitations of foundation models, and provides a reproducible platform for advancing trustworthy AI in biomedicine.

cs.AI↗

arXiv2026

RLMiner: Finding the Most Frequent k-sized Subgraph via Reinforcement Learning

Identifying the most frequent induced subgraph of size $k$ in a target graph is a fundamental graph mining problem with direct implications for Web-related data mining and social network analysis. Despite its importance, finding the most frequent induced subgraph remains computationally expensive due to the NP-hard nature of the subgraph counting task. Traditional exact enumeration algorithms often suffer from high time complexity, especially for a large graph size $k$. To mitigate this, existing approaches often utilize frequency measurement with the Downward Closure Property to reduce the search space, imposing additional constraints on the task. In this paper, we first formulate this task as a Markov Decision Process and approach it using a multi-task reinforcement learning framework. Specifically, we introduce RLMiner, a novel framework that integrates reinforcement learning with our proposed task-state-aware Graph Neural Network to find the most frequent induced subgraph of size $k$ with a time complexity linear to $k$. Extensive experiments on real-world datasets demonstrate that our proposed RLMiner effectively identifies subgraphs with frequencies closely matching the ground-truth most frequent induced subgraphs, while achieving significantly shorter and more stable running times compared to traditional methods.

cs.DB↗

arXiv2026

TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins

Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 93,054 patients across 20 cancer types. In benchmarks, GDT significantly reduces forecasting error, achieving a median Mean Absolute Scaled Error (MASE) of 0.87 compared to 0.97 for the strongest time-series baseline (p<0.001). Furthermore, GDT improves risk stratification, achieving an average concordance index (C-index) of 0.703 across survival, progression, and therapy switching tasks, surpassing the best baseline of 0.662. GDT also generalizes to out-of-distribution clinical trials, matching trained baselines at zero-shot and surpassing them with fine-tuning, achieving a median MASE of 0.75-0.88 and outperforming the strongest baseline in event prediction with an average C-index of 0.672 versus 0.648. Finally, TwinWeaver enables an interpretable clinical reasoning extension, providing a scalable and transparent foundation for longitudinal clinical modeling.

cs.LG↗

arXiv2026

OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography

Prostate cancer is one of the most prevalent and deadly cancers among men, motivating the development of accurate and accessible imaging technologies for early detection. Ultrasound computed tomography (USCT) reconstructs quantitative tissue parameters such as speed-of-sound (SOS) and is a promising low-cost alternative to existing modalities. However, prostate USCT remains challenging due to limited-angle acquisition, strong tissue heterogeneity, bone-induced wave distortion, and the lack of large-scale, anatomically realistic datasets for method development and evaluation. We introduce OPENPROS, the first large-scale benchmark dataset for limited-angle prostate USCT, designed to systematically evaluate machine learning methods for quantitative inverse problems. OPENPROS contains over 280,000 paired samples of realistic 2D SOS maps and corresponding ultrasound full-waveform data, generated from anatomically accurate 3D digital prostate models derived from 4 clinical MRI/CT scans and 62 ex vivo prostate specimens with experimental ultrasound measurements. Wave propagation is simulated under clinically realistic configurations using open-source finite-difference time-domain and Runge-Kutta solvers. We provide standardized training, in-distribution, and out-of-distribution benchmarks and evaluate representative deep learning baselines. While learning-based methods substantially improve inference speed and reconstruction accuracy over physics-based approaches, results highlight persistent challenges in robustness, generalization, and high-resolution reconstruction quality. By publicly releasing OPENPROS, we establish a rigorous benchmark to support research in inverse problems, physics-guided learning, and operator learning, and to bridge the gap between machine learning research and practical USCT deployment. The dataset is available at https://open-pros.github.io/.

physics.med-ph↗

arXiv2026

Small Shifts, Large Gains: Unlocking Traditional TSP Heuristic Guided-Sampling via Unsupervised Neural Instance Modification

The Traveling Salesman Problem (TSP) is one of the most representative NP-hard problems in route planning and a long-standing benchmark in combinatorial optimization. Traditional heuristic tour constructors, such as Farthest or Nearest Insertion, are computationally efficient and highly practical, but their deterministic behavior limits exploration and often leads to local optima. In contrast, neural-based heuristic tour constructors alleviate this issue through guided-sampling and typically achieve superior solution quality, but at the cost of extensive training and reliance on ground-truth supervision, hindering their practical use. To bridge this gap, we propose TSP-MDF, a novel instance modification framework that equips traditional deterministic heuristic tour constructors with guided-sampling capability. Specifically, TSP-MDF introduces a neural-based instance modifier that strategically shifts node coordinates to sample multiple modified instances, on which the base traditional heuristic tour constructor constructs tours that are mapped back to the original instance, allowing traditional tour constructors to explore higher-quality tours and escape local optima. At the same time, benefiting from our instance modification formulation, the neural-based instance modifier can be trained efficiently without any ground-truth supervision, ensuring the framework maintains practicality. Extensive experiments on large-scale TSP benchmarks and real-world benchmarks demonstrate that TSP-MDF significantly improves the performance of traditional heuristics tour constructors, achieving solution quality comparable to neural-based heuristic tour constructors, but with an extremely short training time.

cs.AI↗