New method enables AI for safety-critical situations
The “HardFlow” algorithm could help generative AI models produce high-quality outputs that obey strict requirements when “pretty close” doesn’t cut it.
Read at sourceMIT spinout turns plastic waste into resilient building materials
Atlas Building Composites is commercializing MIT research to turn plastic waste into parts for buildings and other infrastructure.
Read at sourceFeature Recovery for Object Understanding After Irreversible Fire Damage
arXiv:2609.12078v1 Announce Type: new Abstract: Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, material state, and visual appearance. Detecting and identifying these remnants is critical for locating hazards, reconstructing pre-incident contents, and i…
Read at sourceDoes Video Memory Use What It Retrieves? A Causal Audit of Memory Specificity
arXiv:2609.12090v1 Announce Type: new Abstract: Video models increasingly use memory to preserve information over long sequences, with the assumption that gains come from retrieving and using the correct past content. Standard memory ablations test whether memory helps, but not whether the retrieved content is respons…
Read at sourceBeyond Argmax: A Mechanistic Study of Semantic Retention in Frozen Foundation-Model Composition for Generalized Few-Shot 3D Segmentation
arXiv:2609.12099v1 Announce Type: new Abstract: Classical classifier-combination work distinguishes score-level fusion from hard decision-level voting. We revisit this distinction where independently pretrained, frozen foundation models are composed at inference time for generalized few-shot 3D segmentation. We ask: h…
Read at sourceHSI-Road Relabeled: Surface-Aware Road-Scene Segmentation
arXiv:2609.12151v1 Announce Type: new Abstract: The HSI-Road dataset provides paired RGB and 25-channel NIR (600--960~nm) images with binary masks but no surface-level labels.~This paper introduces a manually labeled six-class taxonomy: Background, Asphalt, Concrete, Dirt, Water, and Grass, and an RGB-to-NIR registrat…
Read at sourceSingle-Query Person-Centric Bimanual Hand-Object Interaction Detection
arXiv:2609.12155v1 Announce Type: new Abstract: Understanding person-level bi-manual interactions requires not only detecting hands, but also identifying which two hands belong to the same person and what each hand interacts with. Existing hand--object interaction methods are mostly hand-centric: they treat each hand…
Read at sourceUSPLIT-VQA: U-Shaped Split Learning for Visual Question Answering with Contribution-Aware Weighted Aggregation
arXiv:2609.12168v1 Announce Type: new Abstract: Visual Question Answering (VQA) systems, jointly interpreting images and natural language queries, hold significant promise across many domains, yet the privacy-sensitive nature of user data creates a fundamental barrier. Centralized training requires access to all data…
Read at sourceWhen Ground-Truth Fidelity Matters: An Orchestrated UAS Framework for Wheat Streak Mosaic Virus Detection Using Vision Transformers and Machine Learning
arXiv:2609.12169v1 Announce Type: new Abstract: Wheat streak mosaic virus (WSMV) is a destructive pathogen of sweet corn and other cereal crops, causing yield losses and complicating early detection because symptoms are spatially variable and subtle. In sweet corn seed production, WSMV also has regulatory importance…
Read at sourcePhysics as the label for measuring and correcting materials reasoning in multimodal models
arXiv:2609.12181v1 Announce Type: new Abstract: Vision-language and language models increasingly interpret materials data, yet benchmarks report that they hallucinate invalid properties and violate physical law. Evaluation matches final answers to scarce human labels, while discovery agents verify final proposals or d…
Read at sourceQuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterization
arXiv:2609.12202v1 Announce Type: new Abstract: Characterizing two-dimensional (2D) quantum materials by optical microscopy requires localizing exfoliated flakes and determining their layer thickness from subtle optical contrast and interference color to select suitable flakes for device fabrication. However, models f…
Read at sourceRevisiting Multi-Object Tracking Baselines: Hyperparameter Optimization with Multi-Fidelity Greedy Coordinate Search
arXiv:2609.12261v1 Announce Type: new Abstract: Multi-object tracking (MOT) is dominated by the tracking-by-detection paradigm, whose methods typically rely on a small set of hyperparameters that are conventionally chosen by hand. Tuning them requires repeated expert-guided experimentation, while the procedures used t…
Read at sourceUniMo: Unifying Human and Animal Motion Generation
arXiv:2609.12342v1 Announce Type: new Abstract: The conditional generation of 3D motion has emerged as a key research topic due to its wide applicability across robotics, AR/VR, gaming, and content creation. However, extending recent advances in text-driven human motion generation to the animal domain remains challeng…
Read at sourceVS-Splat: Voxel-Selective feed-forward Gaussian Splatting for end-to-end 3D object reconstruction from sparse-views
arXiv:2609.12343v1 Announce Type: new Abstract: Feed-forward Gaussian splatting models have demonstrated remarkable effectiveness in reconstructing three-dimensional (3D) objects from a few two-dimensional (2D) images, even if they are unseen. As existing methods typically predict Gaussian primitives uniformly across…
Read at sourceEgoMaize: A First-Person Maize Instance Segmentation Benchmark under Severe Field Occlusion
arXiv:2609.12350v1 Announce Type: new Abstract: Close-range first-person field images are important for mobile maize phenotyping because many plant-level traits depend on in-canopy structures that are difficult to ob serve from overhead views. However, post-seedling maize fields create a difficult in stance segmentati…
Read at sourceContext-Aware Causal Gaze Forecasting for Human-Vehicle Interaction During In-Cabin Tracking Dropouts
arXiv:2609.12374v1 Announce Type: new Abstract: Dashboard-mounted gaze trackers often lose sight of the driver's eyes during large head rotations, including shoulder checks, mirror glances, and intersection scanning. These maneuvers occur when information about the driver's visual attention is most useful. Offline gap…
Read at sourceUFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
arXiv:2609.12397v1 Announce Type: new Abstract: Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement of generative models, their evaluation remains largely lagging. Existing methods, whether embedding-based or Multi-modal…
Read at sourceGSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes
arXiv:2609.12408v1 Announce Type: new Abstract: Hazardous-freight operations at petrochemical logistics nodes are safety-critical for intelligent transportation systems, yet existing vision benchmarks rarely address procedural compliance under realistic deployment constraints. In large infrastructure networks, cameras…
Read at source