System helps humans predict when self-driving cars will make mistakes
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
Read at sourceA Cone-Constrained Bilinear Decomposition for Total Scaled-Gradient Variation Models
arXiv:2609.00036v1 Announce Type: new Abstract: The total scaled-gradient variation (TSGV) regularizer, derived from sparse modeling of piecewise-linear structures, has been shown to preserve edges and corners in image restoration. However, its highly nonconvex and nonlinear nature poses severe computational challenge…
Read at sourceQwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
arXiv:2609.00111v1 Announce Type: new Abstract: We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of the pretrained vision-language model (VLM) and integrates 3D perception, visual question answering, and motion plannin…
Read at sourceZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
arXiv:2609.00188v1 Announce Type: new Abstract: Robotic manipulation faces a fundamental scaling challenge: robust generalization demands broad physical experience, yet action-labeled robot trajectories are expensive to collect and inherently limited in diversity. Egocentric videos offer a far more scalable source of…
Read at sourceA Lagrangian View of Flow Matching
arXiv:2609.00198v1 Announce Type: new Abstract: Modern explicit-time generative models, such as Flow Matching [Lipman et al., 2023] and Rectified Flow [Liu et al., 2023], are typically derived top-down via Optimal Transport and the continuity equation. This standard Eulerian approach focuses on the macroscopic transpo…
Read at sourceDistributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation
arXiv:2609.00206v1 Announce Type: new Abstract: Despite their growing use in video moderation, multimodal large language models (MLLMs) exhibit a compositional safety blind spot: videos composed of seemingly benign components can convey harmful meaning when interpreted as a whole. We refer to this phenomenon as Distri…
Read at sourceBeyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM
arXiv:2609.00231v1 Announce Type: new Abstract: Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as over-reliance on textual co-occurrence statistics. We challenge this view by presenting quantitative evidence for a compl…
Read at sourceBeyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning
arXiv:2609.00232v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmarks. Yet existing evaluations largely assume that every task is valid and answerable. In real-world OCR scenarios, this a…
Read at sourceCoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Prediction
arXiv:2609.00242v1 Announce Type: new Abstract: Long-tail autonomous driving failures are often framed as rare-object recognition errors. We argue that this view is incomplete: the decision-critical question is not only whether a model recognizes an unusual object, but whether it infers how that object changes the ego…
Read at sourceCrossFeat: Bridging Imaging Modalities in Feature Descriptor Space
arXiv:2609.00272v1 Announce Type: new Abstract: Most advances in keypoint descriptions address monomodal settings, where image variations arise from viewpoint, illumination, or contrast changes. Multimodal scenarios involve images produced by fundamentally different sensing processes, such as multispectral imaging, RG…
Read at sourceStreamScout: Learning When to Look Deeper for Streaming Video Understanding
arXiv:2609.00291v1 Announce Type: new Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily focus on what to retain in a bounded memory, yet access that memory using the same fixed-cost procedure for every query…
Read at sourceTRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening
arXiv:2609.00300v1 Announce Type: new Abstract: Reducing the review of clearly cancer-negative screening mammograms could lower radiologist workload without compromising cancer detection. We propose a closed-loop threshold-aware training strategy in which the dismissal threshold is recalculated during training and use…
Read at sourceWhere Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers
arXiv:2609.00358v1 Announce Type: new Abstract: Vision Transformers provide strong visual representations but typically rely on slowly updated parameters, limiting their ability to organize newly acquired information across different memory timescales. This work proposes \textit{Hierarchical Hebbian Memory}, a three-l…
Read at sourcePuppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation
arXiv:2609.00369v1 Announce Type: new Abstract: Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging. Prior speech-driven gesture models emphasize audio-gesture alignment but do not explicitly account for posture constra…
Read at sourceFoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos
arXiv:2609.00377v1 Announce Type: new Abstract: We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origami demonstration videos. Our framework leverages the reasoning power of a pre-trained Vision-Language Model (VLM) equipped with a suite of specialized tool…
Read at sourceSlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling
arXiv:2609.00396v1 Announce Type: new Abstract: Histopathological whole slide images (WSIs) are central to cancer diagnosis, but their gigapixel scale, tissue heterogeneity, weak slide-level supervision, sparse diagnostic regions, and multi-scale evidence make robust automated analysis challenging. Multiple instance l…
Read at sourceUnmasking Face Embeddings: Reading, Rendering and Naming with Foundation Models
arXiv:2609.00411v1 Announce Type: new Abstract: Modern face recognition (FR) owes much of its success to deep neural networks that learn to extract compact identity embeddings from face images. These models are typically trained for identity discrimination, producing embeddings that are highly effective for biometric…
Read at sourceInstance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CT
arXiv:2609.00447v1 Announce Type: new Abstract: Accurate 3D abnormality segmentation in chest CT requires dense spatial supervision, but obtaining expert voxel-level labels is costly. Radiology reports, however, are routinely generated during clinical interpretation and contain instance-specific descriptions that can…
Read at source