ToolGrad: Efficient tool-use dataset generation with textual "gradients"
Machine Intelligence
Read at sourceEvidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence
arXiv:2609.09184v1 Announce Type: new Abstract: Vision-language model (VLM) confidence may change in aggregate when visual evidence is degraded while remaining structurally inconsistent within individual examples. We study answer-level reliability along five-step, question-conditioned evidence-loss trajectories. Using…
Read at sourceIntegrating Unimodal and Vision-Language Representations in Latent Space for Multi-Label Chest X-Ray Classification
arXiv:2609.09185v1 Announce Type: new Abstract: Multi-label chest X-ray classification has attracted considerable attention in recent years, with the effective use of visual representations and clinical semantic knowledge playing an important role. This study proposes a framework that combines unimodal representations…
Read at sourceM2LG-DG: A Multi-modal Local-Global Domain Generalization Framework for Cross-site Major Depressive Disorder Classification
arXiv:2609.09186v1 Announce Type: new Abstract: Classification models based on resting-state functional magnetic resonance imaging (rs-fMRI) often show lower performance at imaging sites not included during model development, which can limit their use in clinical settings. Domain generalization (DG) addresses this iss…
Read at sourceAgenticGen: Reward-Guided Agentic Video Generation for Advertising
arXiv:2609.09187v1 Announce Type: new Abstract: Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realistic clips from multimodal conditions, yet they do not…
Read at sourceLensless Gaze Is Not Private by Default: Auditing Identity Leakage Across Disclosure Surfaces
arXiv:2609.09188v1 Announce Type: new Abstract: Lensless near-eye sensing is often described as privacy-friendly because its coded measurements are visually unintelligible. Yet visual unintelligibility reflects human interpretation, not what a learned adversary can recover. We therefore treat identity privacy as a sys…
Read at sourceMLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
arXiv:2609.09206v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) often struggle with hallucinations, thus hindering their reliable practical applications. Existing attention-based mitigation methods mainly rely on indirect signals (e.g., attention weights) that fail to accurately reflect the ac…
Read at sourceVideo-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
arXiv:2609.09300v1 Announce Type: new Abstract: Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reasoning, which are difficult to jointly optimize within a single model. We introduce Video-MOPD-8B, an open-weight model dedicated to video un…
Read at sourceDensePol: Dense-Angle Polarization Dataset for Learning-Based Polarimetric Vision
arXiv:2609.09359v1 Announce Type: new Abstract: Polarimetric vision is gaining increasing attention because it provides physical cues about scene shape, material, and reflection that are difficult to recover from RGB alone. Recent work has therefore explored predicting polarization directly from conventional RGB image…
Read at sourceThe Living Library: Transforming Archival Collections into Conversational Knowledge Systems -- Lessons from the Theodore Roosevelt Presidential Library
arXiv:2609.09368v1 Announce Type: new Abstract: We present the Living Library, an end-to-end framework for transforming fragmented digital archives into governed, conversational, in-person exhibit experiences. Developed and deployed at the Theodore Roosevelt Presidential Library, the framework comprises four layers: d…
Read at sourceOmniPoint: Universal Monocular Metric Pointcloud from Any Camera
arXiv:2609.09394v1 Announce Type: new Abstract: Recovering metric 3D geometry from monocular images is a fundamental computer vision task, yet current methods remain heavily fragmented by fixed camera model assumptions and inflexible input schemes. We present OmniPoint, a unified framework designed to generalize metri…
Read at sourceVANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models
arXiv:2609.09396v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) advance toward physical deployment, the focus has remained on action-oriented Embodied AI evaluated on subject-centric consumer video. This overlooks a pervasive class of Physical AI: Infrastructure AI, which relies on fixed cameras for o…
Read at sourceVision-language models know more about agriculture than they show and rubric-grounded verifications close the gap
arXiv:2609.09417v1 Announce Type: new Abstract: Vision-language models (VLMs) show promise for agricultural classification, but zero-shot performance on disease, pest, damage, quality, and species identification remains poor, and it is unclear whether this reflects weak visual features or a failure to connect them to…
Read at sourceLongitudinal tracking of multiple sclerosis lesions in the spinal cord: A validation study
arXiv:2609.09424v1 Announce Type: new Abstract: Longitudinal characterization of multiple sclerosis (MS) lesions remains constrained by the lack of frameworks capable of establishing consistent instance-level correspondences across time. Conventional segmentation approaches produce semantic lesion masks at each visit…
Read at sourceLow-Rank Prompt Learning for Vision-Language Models with Fixed-Token Bases
arXiv:2609.09462v1 Announce Type: new Abstract: Prompt learning adapts CLIP to downstream recognition by replacing hand-written templates with learned continuous context vectors, which in Context Optimization (CoOp) form a dense prompt matrix $\mathbf{P}\in\mathbb{R}^{m\times d}$ trained from only a few examples per c…
Read at sourceLeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation
arXiv:2609.09477v1 Announce Type: new Abstract: Delineating lung tumours on computed tomography (CT) takes a considerable share of the time spent on radiotherapy planning, and a contour proposed by a model can be refined interactively by the clinician. Promptable foundation models such as SAM 3 support this workflow b…
Read at sourceInfra-Bench CLS: A Global, Open-Source Benchmark for Critical Infrastructure Classification with Earth Observation Foundation Models
arXiv:2609.09482v1 Announce Type: new Abstract: Critical infrastructure location data is often incomplete and unevenly distributed globally, especially in developing regions. Earth observation foundation models are proposed as a new step in enabling us to more efficiently understand the natural and built environment…
Read at sourceLearning Global Camera Poses from Noisy View-Graphs for Structure from Motion
arXiv:2609.09491v1 Announce Type: new Abstract: Camera pose estimation is a key step in 3D reconstruction and view-synthesis pipelines. We present a deep, global Structure-from-Motion framework based on learned view-graph aggregation. Our method employs a permutation-equivariant, edge-conditioned graph neural network…
Read at source