Contemporary GUI agents, while increasingly capable due to advances in Large Vision-Language Models (VLMs), often operate with a critical limitation: they treat each task in isolation, lacking a mechanism to systematically learn from past successes. This digital ''amnesia'' results in sub-optimal performance, repeated errors, and poor generalization to novel challenges. To bridge this gap, we introduce EchoTrail-GUI, a novel framework designed to mimic human-like experiential learning by equipping agents with a dynamic, accessible memory. Our framework operates in three distinct stages. First, during Experience Exploration, an agent autonomously interacts with GUI environments to build a curated database of successful task trajectories, validated by a reward model. Crucially, the entire knowledge base construction is thus fully automated, requiring no human supervision. Second, in the Memory Injection stage, upon receiving a new task, our system efficiently retrieves the most relevant past trajectories to serve as actionable ''memories''. Finally, during GUI Task Inference, these memories are injected as in-context guidance to inform the agent's reasoning and decision-making process. We demonstrate the efficacy of our approach on benchmarks including Android World and AndroidLab. The results show that EchoTrail-GUI significantly improves the task success rate and operational efficiency of baseline agents, validating the power of structured memory in creating more robust and intelligent GUI automation.

Disease modifying therapies for Alzheimer's disease demand precise timing decisions, yet current predictive models require longitudinal observations and provide no uncertainty quantification, rendering them impractical at the critical first visit when treatment decisions must be made. We developed PROGRESS (PRognostic Generalization from REsting Static Signatures), a dual-model deep learning framework that transforms a single baseline cerebrospinal fluid biomarker assessment into actionable prognostic estimates without requiring prior clinical history. The framework addresses two complementary clinical questions: a probabilistic trajectory network predicts individualized cognitive decline with calibrated uncertainty bounds achieving near-nominal coverage, enabling honest prognostic communication; and a deep survival model estimates time to conversion from mild cognitive impairment to dementia. Using data from over 3,000 participants across 43 Alzheimer's Disease Research Centers in the National Alzheimer's Coordinating Center database, PROGRESS substantially outperforms Cox proportional hazards, Random Survival Forests, and gradient boosting methods for survival prediction. Risk stratification identifies patient groups with seven-fold differences in conversion rates, enabling clinically meaningful treatment prioritization. Leave-one-center-out validation demonstrates robust generalizability, with survival discrimination remaining strong across held-out sites despite heterogeneous measurement conditions spanning four decades of assay technologies. By combining superior survival prediction with trustworthy trajectory uncertainty quantification, PROGRESS bridges the gap between biomarker measurement and personalized clinical decision-making.

Exoskeletons modulate human movement across diverse applications, from performance augmentation to daily-life assistance. These systems often enforce specific kinematic patterns to mitigate injury risks and motivate users to keep moving despite diminished capacity. However, little is known about users' perception of such robot-imposed guidance, especially when personalized to the uniqueness of individual human walk. Given the usually substantial computational cost for personalization, understanding its subjective impact is essential to justify its implementation over standard patterns. Ten unimpaired participants completed a within-subject experiment in a multi-planar treadmill-based exoskeleton that enforced three different gait patterns: personalized, standard, and a randomly selected pattern from a publicly available database. Personalization was achieved using a data-driven framework that predicts hip, knee, and pelvis trajectories from walking speed, anthropometric, and demographic data. The standard pattern was obtained by averaging gait patterns from the aforementioned database. After each condition, participants rated enjoyment, comfort, and perceived naturalness. Knee joint interaction forces were also recorded. Subjective ratings revealed no significant differences among patterns, despite all trajectories being executed with high accuracy. However, gait patterns experienced last were rated as significantly more comfortable and natural, indicating adaptation to the system. Higher interaction forces were observed only for the random vs. standard pattern. Personalizing gait kinematics had minimal short-term influence on user experience relative to the dominant effect of adaptation to the exoskeleton. These findings highlight the importance of integrating subjective feedback and accounting for user adaptation when designing personalized robot controllers.

The Unigram tokenization algorithm offers a probabilistic alternative to the greedy heuristics of Byte-Pair Encoding. Despite its theoretical elegance, its implementation in practice is complex, limiting its adoption to the SentencePiece package and adapters thereof. We bridge this gap between theory and practice by providing a clear guide to implementation and parameter choices. We also identify a simpler algorithm that accepts slightly higher training loss in exchange for improved compression.

Graph-based multi-agent reinforcement learning (MARL) enables coordinated behavior under partial observability by modeling agents as nodes and communication links as edges. While recent methods excel at learning sparse coordination graphs-determining who communicates with whom-they do not address what information should be transmitted under hard bandwidth constraints. We study this bandwidth-limited regime and show that naive dimensionality reduction consistently degrades coordination performance. Hard bandwidth constraints force selective encoding, but deterministic projections lack mechanisms to control how compression occurs. We introduce Bandwidth-constrained Variational Message Encoding (BVME), a lightweight module that treats messages as samples from learned Gaussian posteriors regularized via KL divergence to an uninformative prior. BVME's variational framework provides principled, tunable control over compression strength through interpretable hyperparameters, directly constraining the representations used for decision-making. Across SMACv1, SMACv2, and MPE benchmarks, BVME achieves comparable or superior performance while using 67--83% fewer message dimensions, with gains most pronounced on sparse graphs where message quality critically impacts coordination. Ablations reveal U-shaped sensitivity to bandwidth, with BVME excelling at extreme ratios while adding minimal overhead.

Humans do not just see attribute similarity -- we also see relational similarity. An apple is like a peach because both are reddish fruit, but the Earth is also like a peach: its crust, mantle, and core correspond to the peach's skin, flesh, and pit. This ability to perceive and recognize relational similarity, is arguable by cognitive scientist to be what distinguishes humans from other species. Yet, all widely used visual similarity metrics today (e.g., LPIPS, CLIP, DINO) focus solely on perceptual attribute similarity and fail to capture the rich, often surprising relational similarities that humans perceive. How can we go beyond the visible content of an image to capture its relational properties? How can we bring images with the same relational logic closer together in representation space? To answer these questions, we first formulate relational image similarity as a measurable problem: two images are relationally similar when their internal relations or functions among visual elements correspond, even if their visual attributes differ. We then curate 114k image-caption dataset in which the captions are anonymized -- describing the underlying relational logic of the scene rather than its surface content. Using this dataset, we finetune a Vision-Language model to measure the relational similarity between images. This model serves as the first step toward connecting images by their underlying relational structure rather than their visible appearance. Our study shows that while relational similarity has a lot of real-world applications, existing image similarity models fail to capture it -- revealing a critical gap in visual computing.

Cooperative perception is critical for autonomous driving, overcoming the inherent limitations of a single vehicle, such as occlusions and constrained fields-of-view. However, current approaches sharing dense Bird's-Eye-View (BEV) features are constrained by quadratically-scaling communication costs and the lack of flexibility and interpretability for precise alignment across asynchronous or disparate viewpoints. While emerging sparse query-based methods offer an alternative, they often suffer from inadequate geometric representations, suboptimal fusion strategies, and training instability. In this paper, we propose SparseCoop, a fully sparse cooperative perception framework for 3D detection and tracking that completely discards intermediate BEV representations. Our framework features a trio of innovations: a kinematic-grounded instance query that uses an explicit state vector with 3D geometry and velocity for precise spatio-temporal alignment; a coarse-to-fine aggregation module for robust fusion; and a cooperative instance denoising task to accelerate and stabilize training. Experiments on V2X-Seq and Griffin datasets show SparseCoop achieves state-of-the-art performance. Notably, it delivers this with superior computational efficiency, low transmission cost, and strong robustness to communication latency. Code is available at https://github.com/wang-jh18-SVM/SparseCoop.

Accurate question answering over real spreadsheets remains difficult due to multirow headers, merged cells, and unit annotations that disrupt naive chunking, while rigid SQL views fail on files lacking consistent schemas. We present SQuARE, a hybrid retrieval framework with sheet-level, complexity-aware routing. It computes a continuous score based on header depth and merge density, then routes queries either through structure-preserving chunk retrieval or SQL over an automatically constructed relational representation. A lightweight agent supervises retrieval, refinement, or combination of results across both paths when confidence is low. This design maintains header hierarchies, time labels, and units, ensuring that returned values are faithful to the original cells and straightforward to verify. Evaluated on multi-header corporate balance sheets, a heavily merged World Bank workbook, and diverse public datasets, SQuARE consistently surpasses single-strategy baselines and ChatGPT-4o on both retrieval precision and end-to-end answer accuracy while keeping latency predictable. By decoupling retrieval from model choice, the system is compatible with emerging tabular foundation models and offers a practical bridge toward a more robust table understanding.

Generalizing deepfake detection to unseen manipulations remains a key challenge. A recent approach to tackle this issue is to train a network with pristine face images that have been manipulated with hand-crafted artifacts to extract more generalizable clues. While effective for static images, extending this to the video domain is an open issue. Existing methods model temporal artifacts as frame-to-frame instabilities, overlooking a key vulnerability: the violation of natural motion dependencies between different facial regions. In this paper, we propose a synthetic video generation method that creates training data with subtle kinematic inconsistencies. We train an autoencoder to decompose facial landmark configurations into motion bases. By manipulating these bases, we selectively break the natural correlations in facial movements and introduce these artifacts into pristine videos via face morphing. A network trained on our data learns to spot these sophisticated biomechanical flaws, achieving state-of-the-art generalization results on several popular benchmarks.

Reasoning models leveraging long chains of thought employ various cognitive skills, such as verification of their answers, backtracking, retrying by an alternate method, and more. Previous work has shown that when a base language model exhibits these skills, training that model further with reinforcement learning (RL) can learn to leverage them. How can we get models to leverage skills that aren't exhibited by base models? Our work, SkillFactory, is a method for fine-tuning models to roughly learn these skills during a supervised fine-tuning (SFT) stage prior to RL. Our approach does not rely on distillation from a stronger model, but instead uses samples from the model itself, rearranged to provide training data in the format of those skills. These "silver" SFT traces may be imperfect, but are nevertheless effective for priming a model to acquire skills during RL. Our evaluation shows that (1) starting from SkillFactory SFT initialization helps a model to generalize to harder variants of a task post-RL, despite lower performance pre-RL;(2) cognitive skills are indeed used by the model; (3) RLed SkillFactory models are more robust to regression on out-of-domain tasks than RLed base models. Our work suggests that inductive biases learned prior to RL help models learn robust cognitive skill use.

We introduce ShelfGaussian, an open-vocabulary multi-modal Gaussian-based 3D scene understanding framework supervised by off-the-shelf vision foundation models (VFMs). Gaussian-based methods have demonstrated superior performance and computational efficiency across a wide range of scene understanding tasks. However, existing methods either model objects as closed-set semantic Gaussians supervised by annotated 3D labels, neglecting their rendering ability, or learn open-set Gaussian representations via purely 2D self-supervision, leading to degraded geometry and limited to camera-only settings. To fully exploit the potential of Gaussians, we propose a Multi-Modal Gaussian Transformer that enables Gaussians to query features from diverse sensor modalities, and a Shelf-Supervised Learning Paradigm that efficiently optimizes Gaussians with VFM features jointly at 2D image and 3D scene levels. We evaluate ShelfGaussian on various perception and planning tasks. Experiments on Occ3D-nuScenes demonstrate its state-of-the-art zero-shot semantic occupancy prediction performance. ShelfGaussian is further evaluated on an unmanned ground vehicle (UGV) to assess its in the-wild performance across diverse urban scenarios. Project website: https://lunarlab-gatech.github.io/ShelfGaussian/.

Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memorization-generalization behavior remains poorly understood. In this work, we revisit the flow matching (FM) objective and study its marginal velocity field, which admits a closed-form expression, allowing exact computation of the oracle FM target. Analyzing this oracle velocity field reveals that flow-based diffusion models inherently formulate a two-stage training target: an early stage guided by a mixture of data modes, and a later stage dominated by the nearest data sample. The two-stage objective leads to distinct learning behaviors: the early navigation stage generalizes across data modes to form global layouts, whereas the later refinement stage increasingly memorizes fine-grained details. Leveraging these insights, we explain the effectiveness of practical techniques such as timestep-shifted schedules, classifier-free guidance intervals, and latent space design choices. Our study deepens the understanding of diffusion model training dynamics and offers principles for guiding future architectural and algorithmic improvements. Our project page is available at: https://maps-research.github.io/from-navigation-to-refinement/.

Multimodal large language models (MLLMs) are expected to jointly interpret vision, audio, and language, yet existing video benchmarks rarely assess fine-grained reasoning about human speech. Many tasks remain visually solvable or only coarsely evaluate speech, offering limited insight into whether models can align who speaks, what is said, and when it occurs. We introduce AV-SpeakerBench, a curated benchmark of 3,212 multiple-choice questions focused on speaker-centric audiovisual reasoning in real-world videos. It features: (1) a speaker-centered formulation that treats speakers-not scenes-as the core reasoning unit; (2) fusion-grounded question design embedding audiovisual dependencies into question semantics; and (3) expert-curated annotations ensuring temporal precision and cross-modal validity. Comprehensive evaluations show that the Gemini family consistently outperforms open-source systems, with Gemini 2.5 Pro achieving the best results. Among open models, Qwen3-Omni-30B approaches Gemini 2.0 Flash but remains far behind Gemini 2.5 Pro, primarily due to weaker audiovisual fusion rather than visual perception. We believe AV-SpeakerBench establishes a rigorous foundation for advancing fine-grained audiovisual reasoning in future multimodal systems.

Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by human experts. To complement for the lack of data diversity, we introduce a novel and scalable simulation framework capable of synthesizing massive unseen states upon existing driving logs. Our pipeline utilizes advanced neural rendering with a reactive environment to generate high-fidelity multi-view observations controlled by the perturbed ego trajectory. Furthermore, we develop a pseudo-expert trajectory generation mechanism for these newly simulated states to provide action supervision. Upon the synthesized data, we find that a simple co-training strategy on both real-world and simulated samples can lead to significant improvements in both robustness and generalization for various planning methods on challenging real-world benchmarks, up to +8.6 EPDMS on navhard and +2.9 on navtest. More importantly, such policy improvement scales smoothly by increasing simulation data only, even without extra real-world data streaming in. We further reveal several crucial findings of such a sim-real learning system, which we term SimScale, including the design of pseudo-experts and the scaling properties for different policy architectures. Simulation data and code have been released at https://github.com/OpenDriveLab/SimScale.

Reading scene text, that is, text appearing in images, has numerous application areas, including assistive technology, search, and e-commerce. Although scene text recognition in English has advanced significantly and is often considered nearly a solved problem, Indian language scene text recognition remains an open challenge. This is due to script diversity, non-standard fonts, and varying writing styles, and, more importantly, the lack of high-quality datasets and open-source models. To address these gaps, we introduce the Bharat Scene Text Dataset (BSTD) - a large-scale and comprehensive benchmark for studying Indian Language Scene Text Recognition. It comprises more than 100K words that span 11 Indian languages and English, sourced from over 6,500 scene images captured across various linguistic regions of India. The dataset is meticulously annotated and supports multiple scene text tasks, including: (i) Scene Text Detection, (ii) Script Identification, (iii) Cropped Word Recognition, and (iv) End-to-End Scene Text Recognition. We evaluated state-of-the-art models originally developed for English by adapting (fine-tuning) them for Indian languages. Our results highlight the challenges and opportunities in Indian language scene text recognition. We believe that this dataset represents a significant step toward advancing research in this domain. All our models and data are open source.

Autoregressive (AR) image generation has recently emerged as a powerful paradigm for image synthesis. Leveraging the generation principle of large language models, they allow for efficiently generating deceptively real-looking images, further increasing the need for reliable detection methods. However, to date there is a lack of work specifically targeting the detection of images generated by AR image generators. In this work, we present PRADA (Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images), a simple and interpretable approach that can reliably detect AR-generated images and attribute them to their respective source model. The key idea is to inspect the ratio of a model's conditional and unconditional probability for the autoregressive token sequence representing a given image. Whenever an image is generated by a particular model, its probability ratio shows unique characteristics which are not present for images generated by other models or real images. We exploit these characteristics for threshold-based attribution and detection by calibrating a simple, model-specific score function. Our experimental evaluation shows that PRADA is highly effective against eight class-to-image and four text-to-image models. We release our code and data at github.com/jonasricker/prada.

Open-vocabulary semantic segmentation (OVSS) underpins many vision and robotics tasks that require generalizable semantic understanding. Existing approaches either rely on limited segmentation training data, which hinders generalization, or apply zero-shot heuristics to vision-language models (e.g CLIP), while the most competitive approaches combine multiple models to improve performance at the cost of high computational and memory demands. In this work, we leverage an overlooked agglomerative vision foundation model, RADIO, to improve zero-shot OVSS along three key axes simultaneously: mIoU, latency, and parameter efficiency. We present the first comprehensive study of RADIO for zero-shot OVSS and enhance its performance through self-correlating recursive attention, self-correlating global aggregation, and computationally efficient RADIO SAM mask refinement. Our approach, RADSeg, achieves 6-30% mIoU improvement in the base ViT class while being 3.95x faster and using 2.5x fewer parameters. Surprisingly, RADSeg-base (106M) outperforms previous combinations of huge vision models (850-1350M) in mIoU, achieving state-of-the-art accuracy with substantially lower computational and memory cost.

The brain's Path Integration (PI) mechanism offers substantial guidance and inspiration for Brain-Inspired Navigation (BIN). However, the PI capability constructed by the Continuous Attractor Neural Networks (CANNs) in most existing BIN studies exhibits significant computational redundancy, and its operational efficiency needs to be improved; otherwise, it will not be conducive to the practicality of BIN technology. To address this, this paper proposes an efficient PI approach using representation learning models to replicate CANN neurodynamic patterns. This method successfully replicates the neurodynamic patterns of CANN-modeled Head Direction Cells (HDCs) and Grid Cells (GCs) using lightweight Artificial Neural Networks (ANNs). These ANN-reconstructed HDC and GC models are then integrated to achieve brain-inspired PI for Dead Reckoning (DR). Benchmark tests in various environments, compared with the well-known NeuroSLAM system, demonstrate that this work not only accurately replicates the neurodynamic patterns of navigation cells but also matches NeuroSLAM in positioning accuracy. Moreover, efficiency improvements of approximately 17.5% on the general-purpose device and 40~50% on the edge device were observed, compared with NeuroSLAM. This work offers a novel implementation strategy to enhance the practicality of BIN technology and holds potential for further extension.

The rapid advancement of generative models has made real and synthetic images increasingly indistinguishable. Although extensive efforts have been devoted to detecting AI-generated images, out-of-distribution generalization remains a persistent challenge. We trace this weakness to spurious shortcuts exploited during training and we also observe that small feature-space perturbations can mitigate shortcut dominance. To address this problem in a more controllable manner, we propose the Positive-Incentive Noise for CLIP (PiN-CLIP), which jointly trains a noise generator and a detection network under a variational positive-incentive principle. Specifically, we construct positive-incentive noise in the feature space via cross-attention fusion of visual and categorical semantic features. During optimization, the noise is injected into the feature space to fine-tune the visual encoder, suppressing shortcut-sensitive directions while amplifying stable forensic cues, thereby enabling the extraction of more robust and generalized artifact representations. Comparative experiments are conducted on an open-world dataset comprising synthetic images generated by 42 distinct generative models. Our method achieves new state-of-the-art performance, with notable improvements of 5.4 in average accuracy over existing approaches.

With the increasing prevalence of video content, effectively understanding and answering questions about long form videos has become essential for numerous applications. Although large vision language models (LVLMs) have enhanced performance, they often face challenges with nuanced queries that demand both a comprehensive understanding and detailed analysis. To overcome these obstacles, we introduce AVATAAR, a modular and interpretable framework that combines global and local video context, along with a Pre Retrieval Thinking Agent and a Rethink Module. AVATAAR creates a persistent global summary and establishes a feedback loop between the Rethink Module and the Pre Retrieval Thinking Agent, allowing the system to refine its retrieval strategies based on partial answers and replicate human-like iterative reasoning. On the CinePile benchmark, AVATAAR demonstrates significant improvements over a baseline, achieving relative gains of +5.6% in temporal reasoning, +5% in technical queries, +8% in theme-based questions, and +8.2% in narrative comprehension. Our experiments confirm that each module contributes positively to the overall performance, with the feedback loop being crucial for adaptability. These findings highlight AVATAAR's effectiveness in enhancing video understanding capabilities. Ultimately, AVATAAR presents a scalable solution for long-form Video Question Answering (QA), merging accuracy, interpretability, and extensibility.

Patients with acute kidney injury (AKI) are at high risk of developing chronic kidney disease (CKD), but identifying those at greatest risk remains challenging. We used electronic health record (EHR) data to dynamically track AKI patients' clinical evolution and characterize AKI-to-CKD progression. Post-AKI clinical states were identified by clustering patient vectors derived from longitudinal medical codes and creatinine measurements. Transition probabilities between states and progression to CKD were estimated using multi-state modeling. After identifying common post-AKI trajectories, CKD risk factors in AKI subpopulations were identified through survival analysis. Of 20,699 patients with AKI at admission, 3,491 (17%) developed CKD. We identified fifteen distinct post-AKI states, each with different probabilities of CKD development. Most patients (75%, n=15,607) remained in a single state or made only one transition during the study period. Both established (e.g., AKI severity, diabetes, hypertension, heart failure, liver disease) and novel CKD risk factors, with their impact varying across these clinical states. This study demonstrates a data-driven approach for identifying high-risk AKI patients, supporting the development of decision-support tools for early CKD detection and intervention.

Kernel-based learning methods can dramatically increase the storage capacity of Hopfield networks, yet the dynamical mechanisms behind this enhancement remain poorly understood. We address this gap by combining a geometric characterization of the attractor landscape with the spectral theory of kernel machines. Using a novel metric, Pinnacle Sharpness, we empirically uncover a rich phase diagram of attractor stability, identifying a Ridge of Optimization where the network achieves maximal robustness under high-load conditions. Phenomenologically, this ridge is characterized by a Force Antagonism, in which a strong driving force is counterbalanced by a collective feedback force. We theoretically interpret this behavior as a consequence of a specific reorganization of the weight spectrum, which we term Spectral Concentration. Unlike a simple rank-1 collapse, our analysis shows that the network on the ridge self-organizes into a critical regime: the leading eigenvalue is amplified to enhance global stability (Direct Force), while the trailing eigenvalues remain finite to sustain high memory capacity (Indirect Force). Together, these results suggest a spectral mechanism by which learning reconciles stability and capacity in high-dimensional associative memory models.

Adversarial patches have emerged as a popular privacy-preserving approach for resisting AI-driven surveillance systems. However, their conspicuous appearance makes them difficult to deploy in real-world scenarios. In this paper, we propose a thermally activated adversarial wearable designed to ensure adaptability and effectiveness in complex real-world environments. The system integrates thermochromic dyes with flexible heating units to induce visually dynamic adversarial patterns on clothing surfaces. In its default state, the clothing appears as an ordinary black T-shirt. Upon heating via an embedded thermal unit, hidden adversarial patterns on the fabric are activated, allowing the wearer to effectively evade detection across both visible and infrared modalities. Physical experiments demonstrate that the adversarial wearable achieves rapid texture activation within 50 seconds and maintains an adversarial success rate above 80\% across diverse real-world surveillance environments. This work demonstrates a new pathway toward physically grounded, user-controllable anti-AI systems, highlighting the growing importance of proactive adversarial techniques for privacy protection in the age of ubiquitous AI surveillance.

Restless Multi-Armed Bandits (RMABs) are powerful models for decision-making under uncertainty, yet classical formulations typically assume fixed dynamics, an assumption often violated in nonstationary environments. We introduce MARBLE (Multi-Armed Restless Bandits in a Latent Markovian Environment), which augments RMABs with a latent Markov state that induces nonstationary behavior. In MARBLE, each arm evolves according to a latent environment state that switches over time, making policy learning substantially more challenging. We further introduce the Markov-Averaged Indexability (MAI) criterion as a relaxed indexability assumption and prove that, despite unobserved regime switches, under the MAI criterion, synchronous Q-learning with Whittle Indices (QWI) converges almost surely to the optimal Q-function and the corresponding Whittle indices. We validate MARBLE on a calibrated simulator-embedded (digital twin) recommender system, where QWI consistently adapts to a shifting latent state and converges to an optimal policy, empirically corroborating our theoretical findings.

Time series forecasting plays a crucial role in decision-making across many real-world applications. Despite substantial progress, most existing methods still treat forecasting as a static, single-pass regression problem. In contrast, human experts form predictions through iterative reasoning that integrates temporal features, domain knowledge, case-based references, and supplementary context, with continuous refinement. In this work, we propose Alphacast, an interaction-driven agentic reasoning framework that enables accurate time series forecasting with training-free large language models. Alphacast reformulates forecasting as an expert-like process and organizes it into a multi-stage workflow involving context preparation, reasoning-based generation, and reflective evaluation, transforming forecasting from a single-pass output into a multi-turn, autonomous interaction process. To support diverse perspectives commonly considered by human experts, we develop a lightweight toolkit comprising a feature set, a knowledge base, a case library, and a contextual pool that provides external support for LLM-based reasoning. Extensive experiments across multiple benchmarks show that Alphacast generally outperforms representative baselines. Code is available at this repository: https://github.com/echo01-ai/AlphaCast.

LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and task failures. Existing approaches operate in unstructured language spaces, generating clarifying questions through prompting strategies that lack principled criteria for determining which questions to ask and when to stop. We introduce a principled formulation of structured uncertainty that operates directly over tool parameters and their domains, cleanly separating specification uncertainty (what the user wants) from model uncertainty (what the LLM predicts). Our formulation uses Expected Value of Perfect Information (EVPI) to quantify the disambiguation value of each potential question, balanced against aspect-based cost modeling that prevents redundant questioning. We demonstrate the versatility of this formulation through two applications. First, SAGE-Agent uses structured uncertainty for inference-time question selection, achieving 7-39% higher coverage on ambiguous tasks while reducing clarification questions by 1.5-2.7x compared to strong prompting and uncertainty-based baselines. Second, we show that structured uncertainty provides effective training signals: uncertainty-guided reward modeling boosts When2Call accuracy from 36.5% to 65.2% (3B model) and 36.7% to 62.9% (7B model) through uncertainty-weighted GRPO training, demonstrating more sample-efficient reinforcement learning for tool-calling agents. To enable evaluation, we present ClarifyBench, the first multi-turn dynamic tool-calling disambiguation benchmark. Our results establish structured uncertainty as a principled framework that improves both inference-time interaction efficiency and training-time sample efficiency in tool-augmented agents.

Over-smoothing remains a fundamental challenge in deep Graph Neural Networks (GNNs), where repeated message passing causes node representations to become indistinguishable. While existing solutions, such as residual connections and skip layers, alleviate this issue to some extent, they fail to explicitly model how node representations evolve in a node-specific and progressive manner across layers. Moreover, these methods do not take global information into account, which is also crucial for mitigating the over-smoothing problem. To address the aforementioned issues, in this work, we propose a Dual Mamba-enhanced Graph Convolutional Network (DMbaGCN), which is a novel framework that integrates Mamba into GNNs to address over-smoothing from both local and global perspectives. DMbaGCN consists of two modules: the Local State-Evolution Mamba (LSEMba) for local neighborhood aggregation and utilizing Mamba's selective state space modeling to capture node-specific representation dynamics across layers, and the Global Context-Aware Mamba (GCAMba) that leverages Mamba's global attention capabilities to incorporate global context for each node. By combining these components, DMbaGCN enhances node discriminability in deep GNNs, thereby mitigating over-smoothing. Extensive experiments on multiple benchmarks demonstrate the effectiveness and efficiency of our method.

Vision foundation models achieve strong performance on both global and locally dense downstream tasks. Pretrained on large images, the recent DINOv3 model family is able to produce very fine-grained dense feature maps, enabling state-of-the-art performance. However, computing these feature maps requires the input image to be available at very high resolution, as well as large amounts of compute due to the squared complexity of the transformer architecture. To address these issues, we propose BRIXEL, a simple knowledge distillation approach that has the student learn to reproduce its own feature maps at higher resolution. Despite its simplicity, BRIXEL outperforms the baseline DINOv3 models by large margins on downstream tasks when the resolution is kept fixed. We also apply BRIXEL to other recent dense-feature extractors and show that it yields substantial performance gains across model families. Code and model weights are available at https://github.com/alexanderlappe/BRIXEL.

Autonomous Vehicles (AVs) are transforming the future of transportation through advances in intelligent perception, decision-making, and control systems. However, their success is tied to one core capability, reliable object detection in complex and multimodal environments. While recent breakthroughs in Computer Vision (CV) and Artificial Intelligence (AI) have driven remarkable progress, the field still faces a critical challenge as knowledge remains fragmented across multimodal perception, contextual reasoning, and cooperative intelligence. This survey bridges that gap by delivering a forward-looking analysis of object detection in AVs, emphasizing emerging paradigms such as Vision-Language Models (VLMs), Large Language Models (LLMs), and Generative AI rather than re-examining outdated techniques. We begin by systematically reviewing the fundamental spectrum of AV sensors (camera, ultrasonic, LiDAR, and Radar) and their fusion strategies, highlighting not only their capabilities and limitations in dynamic driving environments but also their potential to integrate with recent advances in LLM/VLM-driven perception frameworks. Next, we introduce a structured categorization of AV datasets that moves beyond simple collections, positioning ego-vehicle, infrastructure-based, and cooperative datasets (e.g., V2V, V2I, V2X, I2I), followed by a cross-analysis of data structures and characteristics. Ultimately, we analyze cutting-edge detection methodologies, ranging from 2D and 3D pipelines to hybrid sensor fusion, with particular attention to emerging transformer-driven approaches powered by Vision Transformers (ViTs), Large and Small Language Models (SLMs), and VLMs. By synthesizing these perspectives, our survey delivers a clear roadmap of current capabilities, open challenges, and future opportunities.

Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a predefined camera trajectory, this limitation leads to collisions with the generated scene, after which autoregression quickly collapses. To address this, we propose Generative View Stitching (GVS), which samples the entire sequence in parallel such that the generated scene is faithful to every part of the predefined camera trajectory. Our main contribution is a sampling algorithm that extends prior work on diffusion stitching for robot planning to video generation. While such stitching methods usually require a specially trained model, GVS is compatible with any off-the-shelf video model trained with Diffusion Forcing, a prevalent sequence diffusion framework that we show already provides the affordances necessary for stitching. We then introduce Omni Guidance, a technique that enhances the temporal consistency in stitching by conditioning on both the past and future, and that enables our proposed loop-closing mechanism for delivering long-range coherence. Overall, GVS achieves camera-guided video generation that is stable, collision-free, frame-to-frame consistent, and closes loops for a variety of predefined camera paths, including Oscar Reutersvärd's Impossible Staircase. Results are best viewed as videos at https://andrewsonga.github.io/gvs.