Vision-Language-Action (VLA) models are increasingly used for end-to-end driving due to their world knowledge and reasoning ability. Most prior work, however, inserts textual chains-of-thought (CoT) as intermediate steps tailored to the current scene. Such symbolic compressions can blur spatio-temporal relations and discard fine visual cues, creating a cross-modal gap between perception and planning. We propose FSDrive, a visual spatio-temporal CoT framework that enables VLAs to think in images. The model first acts as a world model to generate a unified future frame that overlays coarse but physically-plausible priors--future lane dividers and 3D boxes--on the predicted future image. This unified frame serves as the visual CoT, capturing both spatial structure and temporal evolution.

In recent years, face-based deep-learning gaze estimation methods have achieved significant advancements. However, while face images provide supplementary information beneficial for gaze inference, the substantial extraneous information they contain also increases the risk of overfitting during model training and compromises generalization capability. To alleviate this problem, we propose the 3DPE-Gaze framework, explicitly modeling 3D facial priors for feature decoupling and generalized gaze estimation. The 3DPE-Gaze framework consists of two core modules: the 3DGeometric Prior Module (3DGP) incorporating the FLAME model to parameterize facial structures and gaze-irrelevant facial appearances while extracting gaze features; the Semantic Concept Alignment Module (SCAM) separates gaze-related and unrelated concepts through CLIP-guided contrastive learning. Finally, the 3DPE-Gaze framework combines 3D facial landmark as prior for generalized gaze estimation. Experimental results show that 3DPE-Gaze outperforms existing state-of-the-art methods on four major cross-domain tasks, with particularly outstanding performance in challenging scenarios such as lighting variations, extreme head poses, and glasses occlusion.

Occupancy prediction aims to estimate the 3D spatial distribution of occupied regions along with their corresponding semantic labels. Existing vision-based methods perform well on daytime benchmarks but struggle in nighttime scenarios due to limited visibility and challenging lighting conditions. To address these challenges, we propose LIAR, a novel framework that learns illumination-affined representations. LIAR first introduces Selective Low-light Image Enhancement (SLLIE), which leverages the illumination priors from daytime scenes to adaptively determine whether a nighttime image is genuinely dark or sufficiently well-lit, enabling more targeted global enhancement. Building on the illumination maps generated by SLLIE, LIAR further incorporates two illumination-aware components: 2DIllumination-guided Sampling (2D-IGS) and 3DIllumination-driven Projection (3D-IDP), to respectively tackle local underexposure and overexposure. Specifically, 2D-IGS modulates feature sampling positions according to illumination maps, assigning larger offsets to darker regions and smaller ones to brighter regions, thereby alleviating feature degradation in underexposed areas. Subsequently, 3D-IDP enhances semantic understanding in overexposed regions by constructing illumination intensity fields and supplying refined residual queries to the BEV context refinement process. Extensive experiments on both real and synthetic datasets demonstrate the superior performance of LIAR under challenging nighttime scenarios. The source code and pretrained models are available here.

Sarah O'Connor's We Are Not Machines explores how we are contorting ourselves to fit AI into our working lives - and what to do about it, finds Tom Knowles Employers wanting staff to be more like machines isn't new, says O'Connor If you are a fan of translated films, you may have noticed the subtitles on streaming platforms have changed in recent years. They aren't wrong exactly, but they can come across as a bit, well, flat. "You get the meaning, but the language? It's not as rich," Petr Čermoch, a translator in the Czech Republic, tells Sarah O'Connor in We Are Not Machines, which explores how artificial intelligence is changing the way we work. That lack of richness is usually because the streaming platform has used AI to translate a script, then had a professional translator like Čermoch finesse it.

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through iterative error corrections and quality checks to ensure high quality. Unlike existing benchmarks that are limited to specific domains of sound, music, or speech, MMAR extends them to a broad spectrum of real-world audio scenarios, including mixedmodality combinations of sound, music, and speech. Each question in MMAR is hierarchically categorized across four reasoning layers: Signal, Perception, Semantic, and Cultural, with additional sub-categories within each layer to reflect task diversity and complexity. To further foster research in this area, we annotate every question with a Chain-of-Thought (CoT) rationale to promote future advancements in audio reasoning.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

Below we describe a few other prevalent multi-label datasets and explain how the ML48S differs800 from them, hence they were excluded from comparison in this paper.801 PASCALVOC [11] was created for object detection and classification, covering 20 basic-level802 classes across 4,574 images, with most images containing a single prominent object. This dataset is803 much smaller than ML48S and also contains much fewer classes which are all coarse-grained.804 VG500 is a modification of the Visual Genome dataset [19], a dataset focused on dense annotations805 linking images to respective captions. This dataset is not intended to be bounded by categories806 but has open-vocabulary annotations.

L48 stands out among similar datasets as being at country-wide, year-round scale while still maintaining high-quality bounding box annotations (see Table 1a).

Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG requires specific training procedures and is limited to conditional generation. To address these limitations, we propose Token Perturbation Guidance (TPG), a novel method that applies perturbation matrices directly to intermediate token representations within the diffusion network. TPG employs a norm-preserving shuffling operation to provide effective and stable guidance signals that improve generation quality without architectural changes. As a result, TPG is training-free and agnostic to input conditions, making it readily applicable to both conditional and unconditional generation. We further analyze the guidance term provided by TPG and show that its effect on sampling more closely resembles CFG compared to existing training-free guidance techniques. Extensive experiments on SDXL and Stable Diffusion 2.1 show that TPG achieves nearly a 2 improvement in FID for unconditional generation over the SDXL baseline, while closely matching CFG in prompt alignment. These results establish TPG as a general, condition-agnostic guidance method that brings CFG-like benefits to a broader class of diffusion models.

Automatic summarization systems have advanced rapidly with large language models (LLMs), yet they still lack reliable guarantees on inclusion of critical content in high-stakes domains like healthcare, law, and finance. In this work, we introduce Conformal Importance Summarization, the first framework for importance-preserving summary generation which uses conformal prediction to provide rigorous, distribution-free coverage guarantees. By calibrating thresholds on sentence-level importance scores, we enable extractive document summarization with user-specified coverage and recall rates over critical content. Our method is model-agnostic, requires only a small calibration set, and seamlessly integrates with existing black-box LLMs. Experiments on established summarization benchmarks demonstrate that Conformal Importance Summarization achieves the theoretically assured information coverage rate. Our work suggests that Conformal Importance Summarization can be combined with existing techniques to achieve reliable, controllable automatic summarization, paving the way for safer deployment of AI summarization tools in critical applications.