DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual contexts. But this pipeline requires rendering token embeddings to pixels and compressing from there -- discarding learned representations in favor of an image the vision encoder must then recover from. We ask whether this detour helps. Comparing DeepSeek-OCR's vision encoder against near-zero-parameter mean pooling and a learned hierarchical encoder, we find it does not. For reconstruction, simple direct methods match or surpass vision at every compression ratio. For language modeling, vision performs comparably to truncation -- a baseline that simply discards context -- and loses to the hierarchical encoder at every compression ratio. As expected, all compression methods outperform truncation for factual recall, but vision never surpasses the best direct baseline. The excitement around optical context compression outpaces the evidence. Code and checkpoints are available at https://github.com/ivnle/bad-autoencoding.

3D functionality segmentation aims to identify the interactive element in a 3D scene required to perform an action described in free-form language (e.g., the handle to ``Open the second drawer of the cabinet near the bed''). Progress has been constrained by the scarcity of annotated real-world data, as collecting and labeling fine-grained 3D masks is prohibitively expensive. To address this limitation, we introduce SynthFun3D, the first method for generating 3D functionality segmentation data directly from action descriptions. Given an action description, SynthFun3D constructs a plausible 3D scene by retrieving objects with part-level annotations from a large-scale asset repository and arranging them under spatial and semantic constraints. SynthFun3D renders multi-view images and automatically identifies the target functional element, producing precise ground-truth masks without manual annotation. We demonstrate the effectiveness of the generated data by training a VLM-based 3D functionality segmentation model. Augmenting real-world data with our synthetic data consistently improves performance, with gains of +2.2 mAP, +6.3 mAR, and +5.7 mIoU over real-only training. This shows that action-guided synthetic data generation provides a scalable and effective complement to manual annotation for 3D functionality understanding. Project page: tev-fbk.github.io/synthfun3d.

We present a unified framework for reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs. Our method tackles three bottlenecks: pose- and framing-sensitive feature representations, limited scalable data, and unreliable proxy-mesh estimation. We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches, eliminating pose- and framing-induced token shifts. We also build a factorized synthetic data manifold combining 2D generative diversity with geometry-consistent 3D renderings, supported by a training scheme that improves realism and identity consistency. A robust proxy-mesh tracker maintains stability under partial visibility. Together, these components enable strong in-the-wild generalization. Trained only on half-body synthetic data, our model achieves state-of-the-art head and upper-body reconstruction and competitive full-body results. Extensive experiments and analyses further validate the effectiveness of our approach.

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for 3D scenes, widely adopted due to its exceptional efficiency and high-fidelity visual quality. Given the significant value of 3DGS assets, recent works have introduced specialized watermarking schemes to ensure copyright protection and ownership verification. However, can existing 3D Gaussian watermarking approaches genuinely guarantee robust protection of the 3D assets? In this paper, for the first time, we systematically explore and validate possible vulnerabilities of 3DGS watermarking frameworks. We demonstrate that conventional watermark removal techniques designed for 2D images do not effectively generalize to the 3DGS scenario due to the specialized rendering pipeline and unique attributes of each gaussian primitives. Motivated by this insight, we propose GSPure, the first watermark purification framework specifically for 3DGS watermarking representations. By analyzing view-dependent rendering contributions and exploiting geometrically accurate feature clustering, GSPure precisely isolates and effectively removes watermark-related Gaussian primitives while preserving scene integrity. Extensive experiments demonstrate that our GSPure achieves the best watermark purification performance, reducing watermark PSNR by up to 16.34dB while minimizing degradation to original scene fidelity with less than 1dB PSNR loss. Moreover, it consistently outperforms existing methods in both effectiveness and generalization. Our code is available at https://github.com/insightlab-CG-3DV/GSPure.

Business Email Compromise (BEC) is a high-impact social engineering threat with extreme operational asymmetry: false negatives can trigger large financial losses, while false positives primarily incur investigation and delay costs. This paper compares two BEC detection paradigms under a cost-sensitive decision framework: (i) a semantic transformer approach (DistilBERT) for contextual language understanding, and (ii) a forensic psycholinguistic approach (CatBoost) using engineered linguistic and structural cues. We evaluate both on a hybrid dataset (N = 7,990) combining legitimate corporate email and AI-synthesised adversarial fraud generated across 30 BEC taxonomies, including character-level Unicode obfuscations. We add classical baselines (TF-IDF+LogReg and character n-gram+Linear SVM), an ablation study for the Smiling Assassin Score, and a homoglyph-map sensitivity analysis. DistilBERT achieves AUC = 1.0000 and F1 = 0.9981 at 7.403 ms per email on GPU; CatBoost achieves AUC = 0.9860 and F1 = 0.9382 at 0.855 ms on CPU. A three-way cost-sensitive decision policy (auto-allow, auto-block, manual review) optimises expected financial loss under a 1:5,167 false-negative-to-false-positive cost ratio.

Egocentric perception on smart glasses could transform how we learn new skills in the physical world, but automatic skill assessment remains a fundamental technical challenge. We introduce SkillSight for power-efficient skill assessment from first-person data. Central to our approach is the hypothesis that skill level is evident not only in how a person performs an activity (video), but also in how they direct their attention when doing so (gaze). Our two-stage framework first learns to jointly model gaze and egocentric video when predicting skill level, then distills a gaze-only student model. At inference, the student model requires only gaze input, drastically reducing power consumption by eliminating continuous video processing. Experiments on three datasets spanning cooking, music, and sports establish, for the first time, the valuable role of gaze in skill understanding across diverse real-world settings. Our SkillSight teacher model achieves state-of-the-art performance, while our gaze-only student variant maintains high accuracy using 73x less power than competing methods. These results pave the way for in-the-wild AI-supported skill learning.

This paper presents a novel framework to accelerate score-based diffusion models. It first converts the standard stable diffusion model into the Fokker-Planck formulation which results in solving large linear systems for each image. For training involving many images, it can lead to a high computational cost. The core innovation is a cross-matrix Krylov projection method that exploits mathematical similarities between matrices, using a shared subspace built from ``seed" matrices to rapidly solve for subsequent ``target" matrices. Our experiments show that this technique achieves a 15.8\% to 43.7\% time reduction over standard sparse solvers. Additionally, we compare our method against DDPM baselines in denoising tasks, showing a speedup of up to 115$\times$. Furthermore, under a fixed computational budget, our model is able to produce high-quality images while DDPM fails to generate recognizable content, illustrating our approach is a practical method for efficient generation in resource-limited settings.

Obstacle avoidance in complex and dynamic environments is a critical challenge for real-time robot navigation. Model-based and learning-based methods often fail in highly dynamic scenarios because traditional methods assume a static environment and cannot adapt to real-time changes, while learning-based methods rely on single-frame observations for motion constraint estimation, limiting their adaptability. To overcome these limitations, this paper proposes a novel framework that leverages multi-frame point constraints, including current and future frames predicted by a dedicated module, to enable proactive end-to-end navigation. By incorporating a prediction module that forecasts the future path of moving obstacles based on multi-frame observations, our method allows the robot to proactively anticipate and avoid potential dangers. This proactive planning capability significantly enhances navigation robustness and efficiency in unknown dynamic environments. Simulations and real-world experiments validate the effectiveness of our approach.

A structured understanding of intraoral 3D scans is essential for digital orthodontics. However, existing deep-learning approaches rely heavily on modality-specific training, large annotated datasets, and controlled scanning conditions, which limit generalization across devices and hinder deployment in real clinical workflows. Moreover, raw intraoral meshes exhibit substantial variation in arch pose, incomplete geometry caused by occlusion or tooth contact, and a lack of texture cues, making unified semantic interpretation highly challenging. To address these limitations, we propose ArchMap, a training-free and knowledge-guided framework for robust structured dental understanding. ArchMap first introduces a geometry-aware arch-flattening module that standardizes raw 3D meshes into spatially aligned, continuity-preserving multi-view projections. We then construct a Dental Knowledge Base (DKB) encoding hierarchical tooth ontology, dentition-stage policies, and clinical semantics to constrain the symbolic reasoning space. We validate ArchMap on 1060 pre-/post-orthodontic cases, demonstrating robust performance in tooth counting, anatomical partitioning, dentition-stage classification, and the identification of clinical conditions such as crowding, missing teeth, prosthetics, and caries. Compared with supervised pipelines and prompted VLM baselines, ArchMap achieves higher accuracy, reduced semantic drift, and superior stability under sparse or artifact-prone conditions. As a fully training-free system, ArchMap demonstrates that combining geometric normalization with ontology-guided multimodal reasoning offers a practical and scalable solution for the structured analysis of 3D intraoral scans in modern digital orthodontics.

Antagonistic artificial muscles can decouple joint torque and stiffness, but contact transients often degrade this independence. We present a unified real-time framework applicable across pneumatic, electrohydraulic, and dielectric elastomer artificial muscle families: a separable Padé force model with a minimal two-state dynamic wrapper, a cascaded inverse-dynamics controller in co-contraction/bias coordinates, and a bio-inspired depth-adaptive interaction policy that schedules stiffness based on penetration depth. The controller runs in under 1 ms per control tick and demonstrates independent torque and stiffness tracking, including a fixed-torque stiffness-step test that preserves torque regulation through stiffness transitions. In a coupled impedance contact protocol simulated across soft-to-rigid environments, comparing depth-adaptive stiffness to fixed-stiffness baselines reveals a shock/load versus stability tradeoff. These results provide a control-oriented foundation for musculoskeletal antagonistic robots to execute adaptive impedance behaviors in dynamic interactions.

Efficient large-scale retrieval requires representations that are both compact and discriminative. Foundation models provide powerful visual and multimodal embeddings, but nearest neighbor search in these high-dimensional spaces is computationally expensive. Hashing offers an efficient alternative by enabling fast Hamming distance search with binary codes, yet existing approaches often rely on complex pipelines, multi-term objectives, designs specialized for a single learning paradigm, and long training times. We introduce CroVCA (Cross-View Code Alignment), a simple and unified principle for learning binary codes that remain consistent across semantically aligned views. A single binary cross-entropy loss enforces alignment, while coding-rate maximization serves as an anti-collapse regularizer to promote balanced and diverse codes. To implement this, we design HashCoder, a lightweight MLP hashing network with a final batch normalization layer to enforce balanced codes. HashCoder can be used as a probing head on frozen embeddings or to adapt encoders efficiently via LoRA fine-tuning. Across benchmarks, CroVCA achieves state-of-the-art results in just 5 training epochs. At 16 bits, it performs particularly well; for instance, unsupervised hashing on COCO completes in under 2 minutes and supervised hashing on ImageNet100 in about 3 minutes on a single GPU. These results highlight CroVCA's efficiency, adaptability, and broad applicability.

While Large Language Models (LLMs) are increasingly used in agentic frameworks to assist individual users, there is a growing need for agents that can proactively manage complex, multi-party collaboration. Systematic evaluation methods for such proactive agents remain scarce, limiting progress in developing AI that can effectively support multiple people together. Negotiation offers a demanding testbed for this challenge, requiring socio-cognitive intelligence to navigate conflicting interests between multiple participants and multiple topics and build consensus. Here, we present ProMediate, the first framework for evaluating proactive AI mediator agents in complex, multi-topic, multi-party negotiations. ProMediate consists of two core components: (i) a simulation testbed based on realistic negotiation cases and theory-driven difficulty levels (ProMediate-Easy, ProMediate-Medium, and ProMediate-Hard), with a plug-and-play proactive AI mediator grounded in socio-cognitive mediation theories, capable of flexibly deciding when and how to intervene; and (ii) a socio-cognitive evaluation framework with a new suite of metrics to measure consensus changes, intervention latency, mediator effectiveness, and intelligence. Together, these components establish a systematic framework for assessing the socio-cognitive intelligence of proactive AI agents in multi-party settings. Our results show that a socially intelligent mediator agent outperforms a generic baseline, via faster, better-targeted interventions. In the ProMediate-Hard setting, our social mediator increases consensus change by 3.6 percentage points compared to the generic baseline (10.65\% vs 7.01\%) while being 77\% faster in response (15.98s vs. 3.71s). In conclusion, ProMediate provides a rigorous, theory-grounded testbed to advance the development of proactive, socially intelligent agents.

Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web, software, and physical environments creates new and amplified security risks, distinct from both traditional AI safety and conventional software security. This survey outlines a taxonomy of threats specific to agentic AI, reviews recent benchmarks and evaluation methodologies, and discusses defense strategies from both technical and governance perspectives. We synthesize current research and highlight open challenges, aiming to support the development of secure-by-design agent systems.

Learning mappings between functional spaces, also known as function-on-function regression, is a fundamental problem in functional data analysis with broad applications, including spatiotemporal forecasting, curve prediction, and climate modeling. Existing approaches often struggle to capture complex nonlinear relationships and/or provide reliable uncertainty quantification when data are noisy, sparse, or irregularly sampled. To address these challenges, we propose Deep Gaussian Processes for Functional Maps (DGPFM). Our method constructs a sequence of GP-based linear and nonlinear transformations directly in function space, leveraging kernel integral transforms, GP conditional means, and nonlinear activations sampled from Gaussian processes. A key insight enables a simplified and flexible implementation: under fixed evaluation locations, discrete approximations of kernel integral transforms reduce to direct functional integral transforms, allowing seamless integration of diverse transform designs. To support scalable probabilistic inference, we adopt inducing points and whitening transformations within a variational learning framework. Empirical results on both real-world and synthetic benchmark datasets demonstrate the advantages of DGPFM in terms of predictive accuracy and uncertainty calibration.

In this work, we present the first finite-time analysis of Q-learning with time-varying learning policies (i.e., on-policy sampling) for discounted Markov decision processes under minimal assumptions, requiring only the existence of a policy that induces an irreducible Markov chain over the state space. We establish a last-iterate convergence rate for $\mathbb{E}[\|Q_k - Q^*\|_\infty^2]$, implying a sample complexity of order $\mathcal{O}(1/ξ^2)$ for achieving $\mathbb{E}[\|Q_k - Q^*\|_\infty]\le ξ$. This matches the rate of off-policy Q-learning, but with worse dependence on exploration-related parameters. We also derive a finite-time rate for $\mathbb{E}[\|Q^{π_k} - Q^*\|_\infty^2]$, where $π_k$ is the learning policy at iteration $k$, highlighting the exploration-exploitation trade-off in on-policy Q-learning. While exploration is weaker than in off-policy methods, on-policy learning enjoys an exploitation advantage as the learning policy converges to an optimal one. Numerical results support our theory. Technically, rapidly time-varying learning policies induce time-inhomogeneous Markovian noise, creating significant analytical challenges under minimal exploration. To address this, we develop a Poisson-equation-based decomposition of the Markovian noise under a lazy transition matrix, separating it into a martingale-difference term and residual terms. The residuals are controlled via sensitivity analysis of the Poisson equation solution with respect to both the Q-function estimate and the learning policy. These techniques may extend to other RL algorithms with time-varying policies, such as single-timescale actor-critic methods and learning-in-games algorithms.

Omni-modal large language models (OLLMs) aim to unify audio, vision, and text understanding within a single framework. While existing benchmarks primarily evaluate general cross-modal question-answering ability, it remains unclear whether OLLMs achieve modality-invariant reasoning or exhibit modality-specific biases. We introduce XModBench, a large-scale tri-modal benchmark explicitly designed to measure cross-modal consistency. XModBench comprises 60,828 multiple-choice questions spanning five task families and systematically covers all six modality compositions in question-answer pairs, enabling fine-grained diagnosis of an OLLM's modality-invariant reasoning, modality disparity, and directional imbalance. Experiments show that even the strongest model, Gemini 2.5 Pro, (i) struggles with spatial and temporal reasoning, achieving less than 60% accuracy, (ii) reveals persistent modality disparities, with performance dropping substantially when the same semantic content is conveyed through audio rather than text, and (iii) shows systematic directional imbalance, exhibiting lower consistency when vision serves as context compared to text. These findings indicate that current OLLMs remain far from truly modality-invariant reasoning and position XModBench as a fundamental diagnostic tool for evaluating and improving cross-modal competence. All data and evaluation tools will be available at https://xingruiwang.github.io/projects/XModBench/.

The rapid progress of image-to-video (I2V) generation models has introduced significant risks by enabling deceptive or malicious video synthesis from a single image. Prior defenses such as I2VGuard attempt to immunize images by inducing spatio-temporal degradation, which does not necessarily provide meaningful protection, since residual motion can still convey malicious intent. In this work, we introduce Vid-Freeze -- a novel adversarial defense that adds imperceptible perturbations to enforce temporal freezing in generated videos. Our method explicitly targets attention dynamics in I2V models to suppress motion synthesis. As a result, immunized images produce standstill or near-static videos, effectively blocking malicious content generation. Experiments demonstrate strong protection across models and support temporal freezing as a promising direction for proactive and meaningful defense against I2V misuse.

Model-based reinforcement learning (MBRL) has achieved remarkable success in robotics due to its high sample efficiency and planning capability. However, extending MBRL to physical multi-robot cooperation remains challenging due to the complexity of joint dynamics. To address this challenge, we propose the Sequential World Model (SeqWM), a novel framework that integrates the sequential paradigm into multi-robot MBRL. SeqWM employs independent, autoregressive agent-wise world models to represent joint dynamics, where each agent generates its future trajectory and plans its actions based on the predictions of its predecessors. This design lowers modeling complexity and enables the emergence of advanced cooperative behaviors through explicit intention sharing. Experiments on Bi-DexHands and Multi-Quadruped demonstrate that SeqWM outperforms existing state-of-the-art model-based and model-free baselines in both overall performance and sample efficiency, while exhibiting advanced cooperative behaviors such as predictive adaptation, temporal alignment, and role division. Furthermore, SeqWM has been successfully deployed on physical quadruped robots, validating its effectiveness in real-world multi-robot systems. Demos and code are available at: https://github.com/zhaozijie2022/seqwm

Quantile Partial Effect (QPE) is a statistic associated with conditional quantile regression, measuring the effect of covariates at different levels. Our theory demonstrates that when the QPE of cause on effect is assumed to lie in a finite linear span, cause and effect are identifiable from their observational distribution. This generalizes previous identifiability results based on Functional Causal Models (FCMs) with additive, heteroscedastic noise, etc. Meanwhile, since QPE resides entirely at the observational level, this parametric assumption does not require considering mechanisms, noise, or even the Markov assumption, but rather directly utilizes the asymmetry of shape characteristics in the observational distribution. By performing basis function tests on the estimated QPE, causal directions can be distinguished, which is empirically shown to be effective in experiments on a large number of bivariate causal discovery datasets. For multivariate causal discovery, leveraging the close connection between QPE and score functions, we find that Fisher Information is sufficient as a statistical measure to determine causal order when assumptions are made about the second moment of QPE. We validate the feasibility of using Fisher Information to identify causal order on multiple synthetic and real-world multivariate causal discovery datasets.

This paper addresses the problem of collaborative formation control for multi-agent systems with limited resources. We consider a team of robots tasked with achieving a desired formation from an arbitrary initial configuration. To reduce unnecessary control updates and conserve resources, we propose a distributed event-triggered formation controller. Unlike the well-studied linear formation control strategies, the proposed controller is nonlinear and relies on inter-agent distance measurements. Control updates are triggered only when the measurement error exceeds a predefined threshold, ensuring system stability while minimizing actuation effort. We also employ a distributed control barrier function to guarantee inter-agent collision avoidance. The proposed controller is validated through extensive simulations and real-world experiments involving different formations, communication topologies, scalability tests, and variations in design parameters, while also being compared against periodic triggering strategies. Results demonstrate that the event-triggered approach significantly reduces control effort while preserving formation performance.

Mechanistic interpretability has identified functional subgraphs within large language models (LLMs), known as Transformer Circuits (TCs), that appear to implement specific algorithms. Yet we lack a formal, single-pass way to quantify when an active circuit is behaving coherently and thus likely trustworthy. Building on prior systems-theoretic proposals, we specialize a sheaf/cohomology and causal emergence perspective to TCs and introduce the Effective-Information Consistency Score (EICS). EICS combines (i) a normalized sheaf inconsistency computed from local Jacobians and activations, with (ii) a Gaussian EI proxy for circuit-level causal emergence derived from the same forward state. The construction is white-box, single-pass, and makes units explicit so that the score is dimensionless. We further provide practical guidance on score interpretation, computational overhead (with fast and exact modes), and a toy sanity-check analysis. Empirical validation on LLM tasks is deferred.

Accurate segmentation of carotid artery structures in histopathological images is vital for cardiovascular disease research. This study systematically evaluates ten deep learning segmentation models including classical architectures, modern CNNs, a Vision Transformer, and foundation models, on a limited dataset of nine cardiovascular histology images. We conducted ablation studies on data augmentation, input resolution, and random seed stability to quantify sources of variance. Evaluation on an independent generalization dataset ($N=153$) under distribution shift reveals that foundation models maintain performance while classical architectures fail, and that rankings change substantially between in-distribution and out-of-distribution settings. Training on the second dataset at varying sample sizes reveals dataset-specific ranking hierarchies confirming that model rankings are not generalizable across datasets. Despite rigorous Bayesian hyperparameter optimization, model performance remains highly sensitive to data splits. The bootstrap analysis reveals substantially overlapping confidence intervals among top models, with differences driven more by statistical noise than algorithmic superiority. This instability exposes limitations of standard benchmarking in low-data clinical settings and challenges assumptions that performance rankings reflect clinical utility. We advocate for uncertainty-aware evaluation in low-data clinical research scenarios from two perspectives. First, the scenario is not niche and is rather widely spread; and second, it enables pursuing or discontinuing research tracks with limited datasets from incipient stages of observations.

Generating synthetic datasets that accurately reflect real-world observational data is critical for evaluating causal estimators, but it remains a challenging task. Existing generative methods offer a solution by producing synthetic datasets anchored in the observed data (source data) while allowing variation in key parameters such as the treatment effect and amount of confounding bias. However, it is often unclear which generative methods to use and which values of parameters to choose when generating synthetic datasets. Moreover, existing methods typically require users to provide fixed point estimates of such parameters. This denies users the ability to express uncertainty over both generative methods and parameter values and removes the potential for posterior inference, potentially leading to unreliable estimator comparisons. We introduce simulation-based inference for causal evaluation (SBICE), a framework that treats the generative method and its corresponding generative parameters as uncertain and infers their posterior distribution given a source dataset. Leveraging techniques in simulation-based inference, SBICE identifies suitable generative methods and infers distributions over its parameter configurations to produce synthetic datasets closely aligned with the source data distribution. Empirical results demonstrate that SBICE improves the reliability of estimator evaluations by generating realistic datasets whose causal estimates closely match the estimates of the source data, making it a robust and uncertainty-aware approach to selecting causal estimators.

The escalating intensity and frequency of wildfires demand innovative computational methods for rapid and accurate property damage assessment. Traditional methods are often time-consuming, while modern computer vision approaches typically require extensive labeled datasets, hindering immediate post-disaster deployment. This research introduces a novel, zero-shot framework leveraging pre-trained multimodal large language models (MLLMs) to classify damage from ground-level imagery. Using Generative Pre-trained Transformer 4o (GPT-4o) as the primary model with comparative validation against Qwen2.5-Vision-Language-32-Billion-Instruct (Qwen), the research evaluates two pipelines applied to the 2025 Eaton and Palisades fires in California. These pipelines include an end-to-end inference method (Pipeline A) and a decoupled workflow where visual cues drive text-based classification (Pipeline B). A primary contribution of this study is demonstrating the efficacy of MLLMs in synthesizing information from multiple perspectives. The findings show that while single-view assessments struggle to classify intermediate damage, a multi-view analysis yields dramatic improvements. To explore the impact of prompting methods, the research benchmarked a baseline zero-shot and heuristic approach against advance reasoning strategies (Structured-Chain-of-Thought and Self-Consistency). The results indicate that simple prompting methods achieve a comparable accuracy to the reasoning strategies.

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming (online or real-time) transcription, due to limitations in their architecture and training methodology. We propose a method to turn the transformer encoder-decoder model into a low-latency streaming model. The encoder is made causal to process audio incrementally, while the decoder conditions on partial encoder states to generate tokens aligned with the available temporal context. This requires explicit synchronization between encoded input frames and token emissions. Since tokens are produced only after sufficient acoustic evidence is observed, an inherent latency arises, necessitating fine-tuning of the encoder-decoder alignment mechanism. We propose an updated inference mechanism that utilizes the fine-tuned causal encoder and decoder to yield greedy and beam-search decoding, and is shown to be locally optimal. Experiments on low-latency chunk sizes (less than 300 msec) show that our fine-tuned model outperforms existing non-fine-tuned streaming approaches in most cases, while using a lower complexity. We release our training and inference code, along with the fine-tuned models, to support further research and development in streaming ASR.

Multivariate time series classification supports applications from wearable sensing to biomedical monitoring and demands models that can capture both short-term patterns and multi-scale temporal dependencies. Despite recent advances, Transformer and CNN models often remain computationally heavy and rely on many parameters. This work presents PRISM(Per-channel Resolution Informed Symmetric Module), a lightweight fully convolutional classifier. Operating in a channel-independent manner, in its early stage it applies a set of multi-resolution symmetric convolutional filters. This symmetry enforces structural constraints inspired by linear-phase FIR filters from classical signal processing, effectively halving the number of learnable parameters within the initial layers while preserving the full receptive field. Across the diverse UEA multivariate time-series archive as well as specific benchmarks in human activity recognition, sleep staging, and biomedical signals, PRISM matches or outperforms state-of-the-art CNN and Transformer models while using significantly fewer parameters and markedly lower computational cost. By bringing a principled signal processing prior into a modern neural architecture, PRISM offers an effective and computationally economical solution for multivariate time series classification. Code and data are available at https://github.com/fedezuc/PRISM

Fire scene datasets are crucial for training robust computer vision models, particularly in tasks such as fire early warning and emergency rescue operations. However, among the currently available fire-related data, there is a significant shortage of annotated data specifically targeting building units.To tackle this issue, we introduce an annotated dataset of building units captured by drones, which incorporates multiple enhancement techniques. We construct backgrounds using real multi-story scenes, combine motion blur and brightness adjustment to enhance the authenticity of the captured images, simulate drone shooting conditions under various circumstances, and employ large models to generate fire effects at different locations.The synthetic dataset generated by this method encompasses a wide range of building scenarios, with a total of 1,978 images. This dataset can effectively improve the generalization ability of fire unit detection, providing multi-scenario and scalable data while reducing the risks and costs associated with collecting real fire data. The dataset is available at https://github.com/boilermakerr/FireUnitData.

There is a broad consensus that the inability to form long-term plans is one of the key limitations of current foundational models and agents. However, the existing planning benchmarks remain woefully inadequate to truly measure their planning capabilities. Most existing benchmarks either focus on loosely defined tasks like travel planning or end up leveraging existing domains and problems from international planning competitions. While the former tasks are hard to formalize and verify, the latter were specifically designed to test and challenge the weaknesses of existing automated planners. To address these shortcomings, we propose a procedure for creating a planning benchmark centered around the game called Countdown, where a player is expected to form a target number from a list of input numbers through arithmetic operations. From a world-model perspective, each instance induces a fully specified transition model (dynamics) over states and actions, enabling evaluation of planning with verifiable outcomes. We discuss how this problem meets many of the desiderata associated with an ideal benchmark for planning capabilities evaluation. Specifically, the domain allows for an intuitive, natural language description for each problem instance, it is computationally challenging (NP-complete), and the instance space is rich enough that we do not have to worry about memorization. We perform an extensive theoretical analysis, establishing the computational complexity result and demonstrate the advantage of our instance generation procedure over public benchmarks. We evaluate a variety of existing LLM-assisted planning methods on instances generated using our procedure. Our results show that, unlike other domains like 24 Game (a special case of Countdown), our proposed dynamic benchmark remains extremely challenging for existing LLM-based approaches.

RGB-based semantic segmentation has become a mainstream approach for visual perception and is widely applied in a variety of downstream tasks. However, existing methods typically rely on high-resolution RGB inputs, which may expose sensitive visual content in privacy-critical environments. Ultra-low-resolution RGB sensing suppresses sensitive information directly during image acquisition, making it an attractive privacy-preserving alternative. Nevertheless, recovering semantic segmentation from ultra-low-resolution RGB inputs remains highly challenging due to severe visual degradation. In this work, we introduce a novel fully joint-learning framework to mitigate the optimization conflicts exacerbated by visual degradation for ultra-low-resolution semantic segmentation. Experiments demonstrate that our method outperforms representative baselines in semantic segmentation performance and our ultra-low-resolution RGB input achieves a favorable trade-off between privacy preservation and semantic segmentation performance. We deploy our privacy-preserving semantic segmentation method in a real-world robotic object-goal navigation task, demonstrating successful downstream task execution even under severe visual degradation.

Evaluating LLMs with a single prompt has proven unreliable, with small changes leading to significant performance differences. However, generating the prompt variations needed for a more robust multi-prompt evaluation is challenging, limiting its adoption in practice. To address this, we introduce PromptSuite, a framework that enables the automatic generation of various prompts. PromptSuite is flexible - working out of the box on a wide range of tasks and benchmarks. It follows a modular prompt design, allowing controlled perturbations to each component, and is extensible, supporting the addition of new components and perturbation types. Through a series of case studies, we show that PromptSuite provides meaningful variations to support strong evaluation practices. All resources, including the Python API, source code, user-friendly web interface, and demonstration video, are available at: https://eliyahabba.github.io/PromptSuite/.