SearcharxivSearch

arXiv subjects

Search papers

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

At least 199 records · Page 11Linked to original sources

CFR-Net:Collaborative Feature Refinement Network for Medical Image Anomaly Detection

Medical image anomaly detection is central to timely diagnosis and clinical decision support, yet abnormal samples are costly to collect because of disease rarity, privacy concerns, and expert workload. This motivates unsupervised learning from normal images, where abnormalities are detected as deviations from learned normal patterns. However, medical anomalies are often subtle, local, and intertwined with normal anatomical variations, which complicates reliable normality modeling. Distillation-based methods support normality modeling by using frozen pretrained teachers as stable feature references, yet mismatches between generic teacher priors and student representations adapted to medical images can produce residuals unrelated to abnormalities in conventional distillation pipelines. To address this limitation, we propose the Collaborative Feature Refinement Network, which learns normality through a coupled process of shared feature conditioning before decoding and cross-space consistency after decoding. Shared feature conditioning performs medical-aware conditioning on teacher and student features under common rules, while cross-space consistency constrains each decoded stream with the complementary encoder representation for reciprocal normal reconstruction. The coupled process is further stabilized by the homework set reorganization strategy, which periodically refreshes normal training subsets. Experiments on six medical image benchmarks show competitive anomaly classification and strong anomaly localization performance.

cs.CV

Population demographics of post-interaction WDMS binaries: From common envelope evolution to stable mass transfer

Close white dwarf (WD) + main-sequence (MS) binaries are end products of mass transfer (MT) that occurred prior to WD formation, making their population demographics a powerful probe of binary evolution. Several recent works have constructed samples of WD+MS binaries with well-understood selection functions using data from wide-field surveys. These include (a) AU-scale astrometric binaries from Gaia that can be shown to contain a WD on dynamical grounds, (b) AU-scale astrometric binaries in which a hot WD is detected through a GALEX UV excess, and (c) close binaries discovered through eclipses. Together, these samples probe outcomes of both stable MT and common-envelope evolution, and interactions on both the red giant branch (RGB) and asymptotic giant branch (AGB). We forward model the three observed samples simultaneously. This approach produces robust constraints on uncertain binary evolution parameters because binaries removed from one population are predicted to appear in another. Our modeling includes a realistic initial binary population and treatments of the selection effects affecting all samples. We confirm that MT from AGB donors requires a critical accretor-to-donor mass ratio of $\sim0.4$ as found in previous work, and find that this is more stable than MT from RGB donors, for which we constrain a critical ratio $\gtrsim0.65$. A common envelope efficiency of $αλ\sim0.3$ matches the relative numbers of close and wide systems and the period distribution of close systems. Most stable MT products in the sample, including those with RGB donors, retain nonzero eccentricities ($\simeq0.1$). The model does not fully reproduce the mass distribution of main-sequence stars in post-common envelope binaries, which shows a cliff below the fully convective limit, possibly pointing to missing physics that may warrant future work.

astro-ph.SR

XScientist: A Git-Like Research Protocol for Long-Running Autonomous Scientific Discovery

Autonomous research systems can generate plausible papers while losing the decisions, failed branches, and evidence needed to inspect or continue the work. We present XScientist, a local-first, git-like protocol that treats research state, rather than a manuscript, as the unit of continuation. Hypotheses, experiment attempts, observations, claims, reviews, and handoffs are represented as typed, content-addressed objects in an exploration graph. Immutable checkpoints, explicit negative outcomes, claim-evidence closure, replay boundaries, and authority-aware gates make each transition inspectable without treating a passing integrity check as scientific truth. The protocol exports a portable Agent-Native Research Artifact (ARA) that another agent or human can inspect, fork, verify, and extend. A reference implementation integrates planning, execution, review, repair, and supervised long-running operation while preserving provenance across these stages. We evaluate the protocol with controlled artifact-integrity workloads and matched external task pilots, keeping native task performance separate from evidence and audit claims. The result is an interoperability and accountability layer for long-running autonomous science, with explicit boundaries where human judgment and independent evaluation remain necessary.

cs.SE

How to Recover Oscillation-Free Pressure in Real Fluids: The RFQC Method and Its Liquid-Upwind Anomaly

From the perspective of continuum thermodynamics, we revisit the pressure oscillation problem in finite-volume methods for multiphase real fluids and clarify the physical counterpart of the Real Fluid Quasi-Conservative (RFQC) method. The pressure oscillation in conservative finite-volume methods originates from their implicit thermodynamic equilibrium assumption, whereas recovering an oscillation-free pressure requires additional physical information. The RFQC method achieves this by evolving the affine parameters xi and E0 of the isentropic internal-energy-pressure relation along pathlines, while the thermodynamic re-projection converts the deviation from the isentropic trajectory into an internal-energy error, thereby ensuring the thermodynamic consistency and numerical stability of the method. We then investigate the applicability limit of the RFQC method and identify a Liquid-upwind Anomaly (LUA) in extreme phase-change cases. For a Riemann problem involving liquid-vapor phase change, a numerical anomaly may occur if a liquid-upwind translational velocity is initially superimposed. Theoretical analysis reveals that this anomaly is initiated by the jump in the affine slope xi during phase change, which delays pressure rise in the downstream vapor cell. Concurrently, the re-projection removes the positive pressure increment, repeatedly generating large internal-energy errors and trapping the vapor cell in a cycle of delayed pressure recovery. The analysis indicates that the LUA is a start-up anomaly, which can be resolved by introducing a regularization strategy at the initial discontinuity. With the proposed regularization strategy, the RFQC method is equipped with enhanced accuracy and robustness for extreme thermodynamic flows, such as sonic phase-change jets.

math-ph

Searching for long-lived ALPs with a laser-assisted optical dump

The feeble interactions of light axion-like particles (ALPs) render them long-lived. Probing long-lived ALPs therefore demands facilities with a macroscopic decay volume to match their potentially long decay lengths, such as high-intensity beam dump experiments. An optical dump setup was proposed by utilizing hard photons from the collision of a high-energy electron beam and a high-intensity laser pulse. In this work, we revisit the probe of long-lived ALPs with MeV$\sim$ GeV mass via a laser-assisted optical dump. We consider the low-energy effective Lagrangian for ALPs incorporating the ALP-photon and ALP-fermion interactions. The scope of optical dump searches is extended to both the ALP-photon coupling induced Primakoff process and the Compton-like scattering via the ALP-electron coupling. We also investigate the correlation between Primakoff process and Compton scattering, and exhibit the interplay of two ALP couplings in light of optical dump experiment.

hep-ph

From Plausible to Actionable: A Position on LLM Self-Explanations

Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior. However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.

cs.CL

Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models

Training agents that generalize to unseen, stateful environments requires a massive dataset of state-changing trajectories covering a vast and diverse set of APIs. However, scaling this broad supervision is severely bottlenecked by the immense effort required to implement and populate fully-executable environments across a broad spectrum of domains. To bypass this barrier, we introduce a data generation pipeline that decouples data synthesis from environment construction by leveraging LLMs as digital world models. Starting from only a list of broad domain names, our automated pipeline synthesizes diverse APIs and tasks. To produce trajectories, a teacher agent iteratively solves these tasks while an LLM simulator dynamically tracks state and provides coherent API responses on-the-fly. Finally, an automated judge filters the trajectories for quality. Fine-tuning on our broad synthetic dataset yields significant performance gains on AppWorld and OfficeBench, two challenging stateful benchmarks featuring environments completely unseen during training. These results establish our LLM world model-based synthesis approach as a highly scalable path for training generalizable, stateful API-calling agents.

cs.AI

Superconductivity in MgHCu3 perovskite revisited

We reexamine the crystal structure, electronic structure, lattice dynamics, phonon dispersion, electron-phonon coupling, and superconducting properties of MgHCu3 perovskite using the PBEsol and PBE functionals. This perovskite phase was recently proposed to exhibit superconductivity with the critical superconducting temperature, TC, of 42 K, which falls slightly over the classical 40 K limit for the phonon driven superconductivity. We show that although the crystal and electronic structure of this hypothetical compound are quite robust with respect to the k point mesh and functional used, yet the phonons and phonon related properties are extremely sensitive to the density of the grid chosen as well as functional used for calculations. Correspondingly, the values of the critical superconducting temperature calculated here for different Gaussian broadenings vary in a broad range of ca. 10 to 31 K and they do not exceed the classical limit. We suggest that the properties of this and many other high TC hydrides claimed should be thoroughly scrutinized using a variety of functionals, and benchmarked with experiment, to provide more reliable values of TC.

cond-mat.supr-con

Coset representatives corresponding to Yetter-Drinfeld modules of modular group and continued fraction

We give complete conjugacy classes of modular group SL(2,Z). Particularly, the conjugacy classes of hyperbolic elements are decided by the proper equivalence classes of indefinite forms, and we give an example. Finally, we describe the coset representatives of centralizer of S, ST, T and hyperbolic elements of SL(2,Z) by regular continued fraction. In conclusion, most Nichols algebras over modular group are infinite-dimensional except Proposition 4.10.

math.QA

DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making

A financial agent can repeat a decision while changing the work behind it. DFAH-Bench operationalizes the Determinism--Faithfulness Assurance Harness (DFAH), pairing decision agreement with tool-path agreement on the same qualified replays, then extends that qualification principle to evidence, authorization, execution and task outcomes. Retrospective and prospective replay analyses expose process variation behind stable decisions. Across 570 eligible prospective episodes, decision agreement is 94.2-95.1%, while agreement on ordered tools, arguments and results is 45.0-51.5%; one stratum falls one group below its prespecified coverage minimum. A separate capture diagnostic shows that systematic omissions can preserve perfect replay agreement. Using the $τ$-Knowledge banking environment, we retain 1,080 scheduled episodes and 1,033 known native outcomes across separate cohorts with open-weight and frontier generators. Missing outcomes prevented the planned tests, so comparisons are descriptive. On the primary schedule, structural checks alone yield more successes than either gate-and-recovery bundle. The typed-choice bundle has lower mean episode cost than the generative bundle on complete task pairs, but produces fewer successes under every assignment of unknown outcomes. Input limits and recovery behavior materially shape these results. Fixed-state probes reveal higher decision agreement alongside lower agreement with constructed policy labels, and separately expose sensitivity to retained generator rationale in a selected authorization case. Together, the findings connect replay observability to evidence, authorization, completion and cost: evidence sufficiency needs direct assessment alongside repeatability.

cs.AI

Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion

Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis. However, the clinical applicability of models that use multimodal learning is hampered by their poor performance under noisy or uninformative data streams. Present fusion approaches often lack robust mechanisms for the dynamic assessment of data quality and for the provision of a trustable confidence score on the final prediction. This dissuades their deployment in safety-critical settings. To address these limitations, we introduce Adaptive Confidence-weighted Expansion (ACE), a novel framework to enhance the trustworthiness of multimodal fusion models. ACE first enhances the multimodal space by generating new, complementary modalities from intra-modality correlations. It then employs a dual-level confidence mechanism that (1) adaptively reweighs all modalities by their reliability before fusion and (2) estimates a global trust score over the fused, final decision. To evaluate ACE, we used four challenging multi-omics datasets (BRCA, KIPAN, LGG, and ROSMAP). ACE significantly outperforms existing state-of-the-art algorithms in both classification performance and confidence calibration. Our framework provides a more stable and robust data fusion method that facilitates the use of multimodal learning in addressing high-stakes problems.

cs.LG

VisCanvas: A Node-Based Interface for Exploratory Visualization Authoring with LLMs

Visual data analysis involves both open-ended exploration and targeted question answering. Visualization authoring tools support this process by enabling users to create visualizations for these tasks. With the rise of large language models (LLMs), substantial effort has been devoted to developing visualization authoring tools that use natural language instructions. However, existing systems are typically based on a linear chat interface, which is not well suited to exploratory visual analysis workflows. In this paper, we introduce VisCanvas, a node-based interface for exploratory visualization authoring with LLMs. VisCanvas allows users to create, revise, branch, and merge visualizations in a non-linear way, enabling more efficient exploration of multiple analytical directions. We conducted a user study with 20 participants to evaluate the effectiveness of VisCanvas compared to a baseline chat-based interface. The results show that VisCanvas facilitates more diverse data interaction while maintaining performance levels (i.e., cognitive load and usability) that are indistinguishable from current prevailing methods. We then distill design principles for future AI-assisted visualization authoring environments. All supplemental materials required to reproduce the study are available at https://osf.io/gsxhn.

cs.HC

Printed but not benchmarkable: most building-decarbonisation disclosure cannot be matched to the pathways that stranding regulation assumes

Cities are beginning to enforce carbon limits on existing buildings. Science-based decarbonisation pathways set those limits one asset type and one jurisdiction at a time. Owners, however, report for the whole firm. We measure what that mismatch costs on two sets of public corporate reports: a census of 502 reports from the 119 listed built-environment firms with a collected report inside a 2,246-firm panel (2003-2023), and 519 real-estate reports from 101 firms (2007-2024). BeDA, a multimodal language-model tool whose reliability we test first, read them. Running the pathway frameworks' own entry tests over published disclosure: 16.5% of census reports (43.7% of real-estate reports) print an operational carbon intensity per square metre; 6.6% (25.0%) can be matched to a pathway for their property type in a covered jurisdiction; and only 5.0% (16.4%) disclose the floor area they divided by. Of the failures at the pathway test, 82-84% follow from reports lumping the portfolio together and 16-18% from a missing curve in the pathway library. The obstacle is the reporting unit, not missing data. The rate is roughly twice as high for European as for US listings (65-71% versus 35% in listed real estate). We also show that a US portfolio's carbon verdict cannot be worked out from disclosure at all. Within one climate zone, the pathway's carbon limit varies by up to 2.79-fold with the electricity subregion, which no report names; its energy limit does not move. Extraction is checked against the source PDFs (97.3% of extracted intensities appear verbatim) and repeats on a second extractor (kappa = 0.97). Recall of the non-disclosing class was 95.1% in a blinded hand audit of 122 reports. The fix follows from the measurement: split intensity by asset type and jurisdiction, and report floor area.

cs.CY

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining

Multi-branch architectures and CNN-Transformer fusion are widely believed to improve vehicle re-identification (Re-ID) by combining complementary representations. We revisit this for a DINOv3-pretrained backbone. A single DINOv3-pretrained ConvNeXt with a tuned recipe reaches 88.19 mAP on VeRi-Wild Small and 77.47 on Large from visual cues alone, within the combined evaluation and optimization noise of the strongest protocol-verified metadata-dependent multi-branch baseline, and 92.38/83.68 with training-free re-ranking. Using this baseline and retrieval-level branch diagnostics, we ask whether representational diversity still pays at this scale. In our runs, it does not. Across both benchmarks and every converged configuration, concatenating multiple heads over a shared backbone moves the best single head by under one mAP point in either direction while costing four times the embedding dimension; 99.7% of the concatenation's variance lies in 512 principal components, so the heads not only duplicate one another but each occupies a quarter of its nominal 2048 dimensions. Pushing diversity to its architectural limit, CNN versus Transformer, we grant fusion every advantage through an asymmetric frozen-anchor scheme. Every Transformer configuration still lands at least 13 mAP below the ConvNeXt backbone (13-15 for the two strongest, up to 46 for the weakest), and a paired per-query bootstrap bounds the fusion gain at +0.11 mAP (95% CI) even for the most favourable snapshot we obtained. One strong backbone with the right recipe and re-ranking is the efficiency frontier. All results use single-seed training and one foundation-model family; differences of this size are therefore reported as bounds rather than orderings, and we list falsifiers.

cs.CV

Charge-dependent atmospheric muon flux at 17 GV geomagnetic cutoff with the mini-ICAL detector

The Iron CALorimeter (ICAL) detector at the India-Based Neutrino Observatory (INO) was conceived as an underground experiment designed to measure atmospheric neutrino oscillation parameters. As part of the R\&D programme, a scaled prototype (mini-ICAL), 85\,ton, approximately 1/600$^{\mathrm{th}}$ the mass of the full detector, was constructed at the IICHEP Transit Campus, Madurai (altitude 150\,m; latitude 9.9372$^\circ$\,N; longitude 78.013$^\circ$\,E; geomagnetic latitude 1.44$^\circ$\,N; vertical cutoff rigidity 17\,GV) and operated between 2018 and 2022. The prototype enabled measurements of charge-dependent cosmic muon spectra in the vicinity of the geomagnetic equator and provided an important validation of detector performance, reconstruction algorithms, and simulation frameworks for the ICAL experiment. Differential fluxes of $μ^{-}$ and $μ^{+}$ were measured over the momentum range $\sim$\,1--5\,GeV/c. The obtained momentum spectra are systematically lower than those reported at sites with smaller geomagnetic cutoff rigidities, consistent with the suppression of low- and intermediate-rigidity primary cosmic rays at the 17\,GV cutoff. The measurements are compared with predictions from different hadronic interaction models available in CORSIKA simulations.

hep-ex

DailyBench: A Unified Benchmark for AI-Generated and Manipulated Images from Modern Generative Models

Recent advances in generative models have shifted AI-generated image detection from identifying easily distinguishable, fully synthetic images to identifying highly realistic content generated by both modern generation and manipulation pipelines. However, existing detection benchmarks are often built with outdated generative models and primarily emphasize full-image synthesis, creating a growing mismatch between benchmark data and the images encountered in real-world generation and editing scenarios. To bridge this gap, we introduce DailyBench, a high-quality unified benchmark for evaluating whether AI-generated image detectors can generalize across both modern full-image synthesis and object-level manipulation. DailyBench contains two complementary subsets: FakeBench, which includes high-quality images synthesized by recent open-source and commercial generative models, and ManipulationBench, which introduces challenging object-level edits applied to real images using advanced image-conditional models. This design makes DailyBench a realistic testbed for studying both generator-level generalization and manipulation-aware detection under subtle local edits. Experiments on DailyBench reveal substantial robustness gaps in current detectors: methods reporting 91-96% balanced accuracy on GenImage drop to 52-79% on FakeBench and 43-67% on ManipulationBench. These results show that existing detectors remain poorly generalized to realistic synthesis and manipulation, highlighting DailyBench as a rigorous testbed for developing robust and manipulation-aware AI-generated image detection methods. The project is available at https://dailybench.github.io/

cs.CV

Chaos Is a LADDER: Domain Generalization Beyond Invariance via Reweighting

Domain generalization (DG) aims to learn from multiple source domains and generalize to unseen target domains. Most DG methods pursue invariance: they seek a causal representation whose prediction rule is invariant across domains. This principle is effective when the causal mechanism is stable, but becomes restrictive when the domain itself modulates how causal content maps to the response. In this case, directly feeding domain style into the predictor can create misleading shortcuts, since style does not by itself cause the response. Yet the apparent chaos of multiple styles can become a ladder: style can locate the unseen target domain among source domains and guide which domain-dependent prediction rules should be trusted. We propose \emph{Latent Adaptive Domain Disentanglement and Environment Reweighting} (LADDER), a fixed-model DG pipeline that learns causal/style representations, freezes the encoders, fits source-specific classifiers, and uses an unlabeled target-domain covariate set only at inference to compute weights over these fixed classifiers, with no target labels or model-state updates. We establish theoretical guarantees for source reweighting and validate LADDER on simulations, FMoW, and a location-grouped iWildCam protocol, with gains in overall and group-averaged accuracy.

stat.ML