arXiv subjects

Bowen Shi

Publications and source records attributed to Bowen Shi.

At least 19 recordsLinked to original sources

arXiv2026

Rapid Earthquake-to-Tsunami Waveform Generation via Large-Scale Multi-GPU FFT Convolution Applied to the Cascadia Subduction Zone

Data-driven methods for earthquake and tsunami early warning rely on large ensembles of rupture scenarios and their resulting waveforms, but generating such datasets with repeated high-fidelity seismic and tsunami simulations is prohibitively expensive. We exploit the linear time-invariant structure of both dynamics to precompute elastic Green's functions and acoustic-gravity adjoint responses, reducing the source-to-waveform map to two consecutive convolution operators. We evaluate these convolutions with a distributed, FFT-accelerated GPU pipeline that partitions the large seafloor grid across GPUs and directly generates the final observation waveforms. We demonstrate the scalability of this pipeline for the Cascadia Subduction Zone with 963 subfaults, 2,416,530 seafloor grid points, 64 observation locations, and 256 timesteps, requiring 9.45 TiB of aggregate GPU memory. On 64 GB200 GPUs within one NVL72 domain, the pipeline generates waveforms in 24 ms per rupture once the response operators are resident, enabling large rupture ensembles to be evaluated within minutes.

cs.DC↗

arXiv2026

Approximate Quantum Error Correction at Chiral Topological Edges

Topologically ordered phases naturally realize quantum error correction through nonlocal encoding of quantum information. More recently, conformal field theories have been shown to realize approximate quantum error-correcting codes, but such constructions generally require fine tuning to criticality. Here we introduce a family of approximate quantum error-correcting codes realized by the chiral edges of two-dimensional topologically ordered phases. The proposed encoding combines the robustness of a gapped topological bulk with the flexibility of gapless edge conformal field theories. To characterize its robustness, we study coherent-information loss under local erasure. We derive an exact expression relating coherent-information loss to relative entropy, reducing the recoverability problem to universal properties of the edge theory. This leads to power-law scaling of coherent-information loss with the size of the erased region. We further show that, for geometrically local erasures near one edge, the two-dimensional chiral edge code is at least as robust as the dimensionally reduced CFT code, and is strictly more robust in several representative examples. For Abelian code subspaces, we further construct a power-law-range recovery map supported on the erased region together with a power-law-range buffer; this recovery map depends only on the code subspace, not on the unknown encoded state. We provide numerical calculations for lattice realizations of compact free boson and Ising CFT examples that support the theoretical predictions of the power-law exponents.

quant-ph↗

arXiv2026

RadSight: Towards Perceptually Reliable Multimodal Radiology Image Understanding

Medical multimodal large language models (MLLMs) are increasingly expected to perform complex image understanding tasks, yet their reliability is often compromised by frequent errors in visual interpretation. To systematically trace these failures, we traverse the hierarchy from high-level clinical tasks down to fundamental visual perception. We therefore introduce Perception-Bench, a large-scale benchmark comprising 1.13 million samples that assesses medical MLLMs across six dimensions: attribute judgment, spatial grounding, spatial understanding, disease prediction, anomaly detection, and report generation, spanning both 2D and 3D radiology images. Our analysis on Perception-Bench reveals that existing MLLMs lack the ability to capture even the most basic lesion attributes, such as location, size, and density. This inability to ground clinical outputs in primary visual evidence reveals that the models' diagnostic unreliability is rooted in a critical but overlooked bottleneck in low-level visual perception. Motivated by this, we propose RadSight, a perception-driven MLLM built upon a dual 2D/3D encoder architecture that preserves native imaging spatial structures. RadSight formulates medical image understanding as a four-stage progressive process: visual-language alignment, fine-grained visual perception, clinical diagnosis, and diagnostic interpretation. The model is trained on an 8.37 million perception-oriented corpus using progressive curriculum learning. On Perception-Bench, RadSight consistently outperforms existing MLLMs across all six evaluation dimensions, with particularly strong gains in spatial grounding and clinical diagnosis. It also achieves consistent improvements on public 2D and 3D medical benchmarks, further demonstrating that robust low-level visual perception is a critical foundation for reliable clinical understanding. Code and model will be publicly available.

cs.CV↗

arXiv2026

AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation

Traditional metrics for Medical Report Generation (MRG) predominantly rely on surface-level n-gram overlap, which fails to capture clinical factual accuracy and often overlooks catastrophic diagnostic errors. We address this fundamental limitation by proposing \textbf{AtomiMed}, a universal, modality-agnostic evaluation framework that decomposes complex medical narratives into a standardized, multi-level hierarchy of Atomic Clinical Facts, encompassing Disease-level entities and Attribute-level descriptors, including location, morphology, and severity. By implementing an Agentic Cross-Verification loop between ground-truth and predicted reports, AtomiMed simulates a multi-radiologist peer-review process to verify clinical consistency, thus enabling the decoupled assessment of diagnostic detection and descriptive accuracy. To facilitate standardized evaluation, we introduce \textbf{MRGEvalKit}, an open-source toolkit for automated hierarchical extraction, and curate \textbf{OmniMRG-Bench}, a comprehensive multi-modal benchmark covering X-ray, CT, MRI, and Ultrasound. Extensive experiments on multiple expert-annotated reader studies demonstrate that AtomiMed achieves significantly higher correlation with human radiologist judgment compared to traditional and model-based metrics. Our code are release at https://github.com/Venn2336/MRGEvalkit

cs.CE↗

arXiv2026

Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography

Vision-language pre-training (VLP) holds great promise for general-purpose medical AI by leveraging radiology reports as rich textual supervision, yet existing methods struggle with 3D CT imaging due to inefficient visual backbones and coarse semantic alignment. To address these issues, we propose a tailored VLP framework featuring three key components: (1) a CNN-ViT hybrid encoder that replaces ViT's patch embedding with a 3D CNN backbone to efficiently capture local anatomical details while preserving global attention and compatibility with pre-trained cross-modal priors; (2) a disease-level contrastive learning mechanism using learnable query tokens to dynamically extract disease-specific semantics from full reports and align them with corresponding visual features, thereby disentangling distinct diseases within the same anatomical region; and (3) a diagnosis-aware prompt strategy that employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap and enhance zero-shot diagnostic reliability. Our model achieves state-of-the-art performance on CT-RATE (84.4% AUC, +5.1%) and Rad-ChestCT (75.4% AUC, +5.4%), with even larger gains (+9.8% AUC) on a challenging 60-disease benchmark, and demonstrates strong transferability to radiology report generation, underscoring the generality and clinical utility of our approach.

cs.CV↗

arXiv2026

Evolutionary origin of the bipartite architecture of dissipative cellular networks

Recently, plenty research has been done on discovering the role of energy dissipation in biological networks, most of which focus on the relationship of dissipation and functionality. However, the development of networks science urged us to fathom the systematic architecture of biological networks and their evolutionary advantages. We found the dissipation of biological dissipative networks is highly related to their structure. By interrogating these well-adapted networks, we find that the energy producing module is relatively isolated in all situations. We applied evolutionary simulation and analysis on premature networks of classic dissipative networks, namely kinetic proofreading, activator-inhibitor oscillator and two typical adaptative response models. We found despite that selection was imposed merely on the network function, the networks tended to decouple high energy molecules as fuels from the functional module, to achieve higher overall dissipation during the course of evolution. Furthermore, we find that decoupled fuel modules can increase the robustness of the networks towards parameter or structure perturbations. We provide theoretical analysis on the kinetic proofreading networks and the general case of energy-driven networks. We find fuel decoupling can guarantee higher dissipation and, in most cases when considering dissipative networks, higher performance. We conclude that fuel decoupling is an evolutionary outcome and bears benefits during evolution.

physics.bio-ph↗

arXiv2026

JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions

The rapid advancement of generative audio models has outpaced the development of robust evaluation methodologies. Existing objective metrics and general multimodal large language models (MLLMs) often struggle with domain generalization, zero-shot capabilities, and instructional flexibility. To address these bottlenecks, we propose JASTIN, a generalizable, instruction-driven audio evaluation framework that formulates audio assessment as a self-instructed reasoning task. JASTIN bridges a frozen high-performance audio encoder with a fine-tuned LLM backbone via a trainable audio adapter. To ensure robust zero-shot generalization, we introduce a comprehensive instruction following data preparation pipeline, incorporating Multi-Source, Multi-Task, Multi-Calibration, and Multi-Description data. Experimental results demonstrate that JASTIN achieves state-of-the-art Pearson and Spearman correlations with human subjective ratings. It consistently outperforms general MLLMs across speech, sound, music, and out-of-domain evaluation tasks without the need for task-specific retraining.

eess.AS↗

arXiv2026

CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation

The evaluation of generated reports remains a critical challenge in Computed Tomography (CT) report generation, due to the large volume of text, the diversity and complexity of findings, and the presence of fine-grained, disease-oriented attributes. Conventional evaluation metrics offer only coarse measures of lexical overlap or entity matching and fail to reflect the granular diagnostic accuracy required for clinical use. To address this gap, we propose CT-FineBench, a benchmark built from CT-RATE and Merlin to evaluate the fine-grained factual consistency of CT reports, constructed from CT-RATE and Merlin. Our benchmark is constructed through a meticulous, Question-Answering (QA) based process: first, we identify and structure key, finding-specific clinical attributes (like location, size, margin). Second, we systematically transform these attributes into a QA dataset, where questions probe for specific clinical details grounded in gold-standard reports. The evaluation protocol for CT-FineBench involves using this QA dataset to query a machine-generated report and scoring the correctness of the answers. This allows for a comprehensive, interpretable, and clinically-relevant assessment, moving beyond superficial lexical overlap to pinpoint specific clinical errors. Experiments show that CT-FineBench correlates better with expert clinical assessment and is substantially more sensitive to fine-grained factual errors than prior metrics.

cs.AI↗

arXiv2026

Finite elements for symmetric and traceless tensors in three dimensions

We construct a family of finite element sub-complexes of the conformal complex on tetrahedral meshes and show their exactness on contractible domains. This complex includes vector fields and symmetric and traceless tensor fields, connected through the conformal Killing operator, the linearized Cotton-York operator, and the divergence operator, respectively. This leads to discrete versions of transverse traceless (TT) tensors, i.e., symmetric, traceless and divergence-free matrix fields, in continuum mechanics and general relativity. We also show the inf-sup stability of the $H(\operatorname{div})$-conforming finite element symmetric and traceless tensors paired with discontinuous vectors.

math.NA↗

arXiv2026

SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation

The performance evaluation remains a complex challenge in audio separation, and existing evaluation metrics are often misaligned with human perception, course-grained, relying on ground truth signals. On the other hand, subjective listening tests remain the gold standard for real-world evaluation, but they are expensive, time-consuming, and difficult to scale. This paper addresses the growing need for automated systems capable of evaluating audio separation without human intervention. The proposed evaluation metric, SAM Audio Judge (SAJ), is a multimodal fine-grained reference-free objective metric, which shows highly alignment with human perceptions. SAJ supports three audio domains (speech, music and general sound events) and three prompt inputs (text, visual and span), covering four different dimensions of evaluation (recall, percision, faithfulness, and overall). SAM Audio Judge also shows potential applications in data filtering, pseudo-labeling large datasets and reranking in audio separation models. We release our code and pre-trained models at: https://github.com/facebookresearch/sam-audio.

eess.AS↗

arXiv2026

Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming

Diffusion-based large language models (dLLMs) have emerged as a promising paradigm, utilizing simultaneous denoising to enable global planning and iterative refinement. While these capabilities are particularly advantageous for long-context generation, deploying such models faces a prohibitive memory capacity barrier stemming from severe system inefficiencies. We identify that existing inference systems are ill-suited for this paradigm: unlike autoregressive models constrained by the cumulative KV-cache, dLLMs are bottlenecked by transient activations recomputed at every step. Furthermore, general-purpose memory reuse mechanisms lack the global visibility to adapt to dLLMs' dynamic memory peaks, which toggle between logits and FFNs. To address these mismatches, we propose Mosaic, a memory-efficient inference system that shifts from local, static management to a global, dynamic paradigm. Mosaic integrates a mask-only logits kernel to eliminate redundancy, a lazy chunking optimizer driven by an online heuristic search to adaptively mitigate dynamic peaks, and a global memory manager to resolve fragmentation via virtual addressing. Extensive evaluations demonstrate that Mosaic achieves an average 2.71$\times$ reduction in the memory peak-to-average ratio and increases the maximum inference sequence length supportable on identical hardware by 15.89-32.98$\times$. This scalability is achieved without compromising accuracy and speed, and in fact reducing latency by 4.12%-23.26%.

cs.LG↗

arXiv2025

SAM Audio: Segment Anything in Audio

General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separation models are either domain-specific, designed for fixed categories such as speech or music, or limited in controllability, supporting only a single prompting modality such as text. In this work, we present SAM Audio, a foundation model for general audio separation that unifies text, visual, and temporal span prompting within a single framework. Built on a diffusion transformer architecture, SAM Audio is trained with flow matching on large-scale audio data spanning speech, music, and general sounds, and can flexibly separate target sources described by language, visual masks, or temporal spans. The model achieves state-of-the-art performance across a diverse suite of benchmarks, including general sound, speech, music, and musical instrument separation in both in-the-wild and professionally produced audios, substantially outperforming prior general-purpose and specialized systems. Furthermore, we introduce a new real-world separation benchmark with human-labeled multimodal prompts and a reference-free evaluation model that correlates strongly with human judgment.

eess.AS↗

arXiv2025

MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generation

A key challenge in music generation models is their lack of direct alignment with human preferences, as music evaluation is inherently subjective and varies widely across individuals. We introduce MR-FlowDPO, a novel approach that enhances flow-matching-based music generation models - a major class of modern music generative models, using Direct Preference Optimization (DPO) with multiple musical rewards. The rewards are crafted to assess music quality across three key dimensions: text alignment, audio production quality, and semantic consistency, utilizing scalable off-the-shelf models for each reward prediction. We employ these rewards in two ways: (i) By constructing preference data for DPO and (ii) by integrating the rewards into text prompting. To address the ambiguity in musicality evaluation, we propose a novel scoring mechanism leveraging semantic self-supervised representations, which significantly improves the rhythmic stability of generated music. We conduct an extensive evaluation using a variety of music-specific objective metrics as well as a human study. Results show that MR-FlowDPO significantly enhances overall music generation quality and is consistently preferred over highly competitive baselines in terms of audio quality, text alignment, and musicality. Our code is publicly available at https://github.com/lonzi/mrflow_dpo. Samples are provided in our demo page at https://lonzi.github.io/mr_flowdpo_demopage/.

cs.SD↗

arXiv2025

Strict area law entanglement versus chirality

Chirality is a property of a gapped phase of matter in two spatial dimensions that can be manifested through non-zero thermal or electrical Hall conductance. In this paper, we prove two no-go theorems that forbid such chirality for a quantum state in a finite dimensional local Hilbert space with strict area law entanglement entropies. As a crucial ingredient in the proofs, we introduce a new quantum information-theoretic primitive called instantaneous modular flow, which has many other potential applications.

quant-ph↗

arXiv2025

GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs

Vision encoders are indispensable for allowing impressive performance of Multi-modal Large Language Models (MLLMs) in vision language tasks such as visual question answering and reasoning. However, existing vision encoders focus on global image representations but overlook fine-grained regional analysis. They are limited in fine grained perception due to the scarcity of fine grained annotated data and the lack of a fine grained pre-training paradigm. In this paper, we propose GranViT, a novel Vision Transformer that integrates fine-grained feature extraction with semantic alignment to Large Language Models (LLMs) via region level autoregressive training. We first construct Gran-29M, a dataset comprising 2million natural and OCR images paired with over 180 million high-quality region-level annotations, to enable large scale fine grained pretraining. Consequently, we develop a pretraining-adaptation framework along with a self distillation mechanism to train fine-grained GranViT on Gran-29M. We sufficiently exploit the fine-grained annotations from Gran-29M to resort to bounding-box-to-caption regression to enhance localized visual representation of the vision encoder in the pretraining and caption-to-bounding-box regression to improve vision feature utilization and localization for LLM in the adaptation. We further incorporate a self distillation mechanism that imposes explicit localization constraints on the vision encoder to strengthen its regional reasoning capability. Extensive experiments show that GranViT surpasses existing vision encoders and attains strong transferability to varying LLMs. Remarkably, it achieves state-of-the-art results on fine-grained recognition, multimodal VQA, and OCR understanding.

cs.CV↗

arXiv2025

Topological Mixed States: Phases of Matter from Axiomatic Approaches

For closed quantum systems, topological orders are understood through the equivalence classes of ground states of gapped local Hamiltonians. The generalization of this conceptual paradigm to open quantum systems, however, remains elusive, often relying on operational definitions without fundamental principles. Here, we fill this gap by proposing an approach based on three axioms: ($i$) local recoverability, ($ii$) absence of long-range correlations, and ($iii$) spatial uniformity. States that satisfy these axioms are fixed points; requiring the axioms only after coarse-graining promotes each fixed point to an equivalence class, i.e., a phase, presenting the first step towards the axiomatic classification of mixed-state phases of matter: mixed-state bootstrap program. From these axioms, a rich set of topological data naturally emerges; importantly, these data are robust under relaxation of axioms. For example, each topological mixed state supports locally indistinguishable classical and/or quantum logical memories with distinct responses to topological operations. These data label distinct mixed-state phases, allowing one to distinguish them. We further uncover a hierarchy of secret-sharing constraints: in non-Abelian phases, reliable recovery-even of information that looks purely classical-demands a specific coordination among spatial subregions, a requirement different across non-Abelian classes. This originates from non-Abelian fusion rules that can stay robust under decoherence. Finally, we performed large-scale numerical simulations to corroborate stability: weakly decohered fixed points respect the axioms once coarse-grained. These results lay the foundation for a systematic classification of topological states in open quantum systems.

cond-mat.str-el↗

arXiv2025

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

Jailbreak attacks bypass the safety alignment of large language models (LLMs) to elicit harmful outputs, yet the vast parameter space makes diagnosing the underlying failure mechanisms extremely challenging. We present NeuroBreak, a visual analytics system that helps experts progressively unpack jailbreak mechanisms from layer-level semantics down to neuron-level behaviors. A layer-wise probing pipeline traces how harmful representations evolve across layers, while a dual-dimensional character--behavior categorization reveals each safety-related neuron's inherent tendency and contextual contribution. These analyses are made interpretable through tailored visualization designs: a task-driven probing projection that reveals safety decision boundaries, a dual-stream semantic evolution flow that traces cross-layer semantic shifts, and a character--behavior chord graph that unifies neuron roles, attribution scores, and collaborative relations in a single view with in-situ causal verification. Quantitative evaluations and case studies show that NeuroBreak uncovers safety failure causes and provides actionable insights for strengthening LLM defenses.

cs.CR↗

arXiv2025

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce prohibitive computational overhead to achieve superior performance using complementary visual representations from multiple vision encoders. To address this, we propose a progressive pruning framework, namely Multi-Encoder collaboraTivE tOken pRuning (METEOR), that eliminates redundant visual tokens across the encoding, fusion, and decoding stages for multi-encoder MLLMs. For multi-vision encoding, we discard redundant tokens within each encoder via a rank guided collaborative token assignment strategy. Subsequently, for multi-vision fusion, we combine the visual features from different encoders while reducing cross-encoder redundancy with cooperative pruning. Finally, we propose an adaptive token pruning method in the LLM decoding stage to further discard irrelevant tokens based on the text prompts with dynamically adjusting pruning ratios for specific task demands. To our best knowledge, this is the first successful attempt that achieves an efficient multi-encoder based vision language model with multi-stage pruning strategies. Extensive experiments on 11 benchmarks demonstrate the effectiveness of our proposed approach. Compared with EAGLE, a typical multi-encoder MLLMs, METEOR reduces 76% visual tokens with only 0.3% performance drop in average. The code is available at https://github.com/YuchenLiu98/METEOR.

cs.CV↗