This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, which evaluates state-of-the-art models under highly unconstrained conditions. To provide a comprehensive assessment, the 2026 edition features three specialized tracks: the MOSE track for tracking objects within densely cluttered and severely occluded scenarios; the MeViS-Text track for localizing targets via motion-focused linguistic expressions; and the newly inaugurated MeViS-Audio track, which pioneers acoustic-driven object segmentation. By introducing previously unreleased challenging data and analyzing the cutting-edge, multimodal solutions submitted by participants, this report highlights the community's latest technical advancements and charts promising future directions for robust video scene comprehension.

Despite significant advances in facial recognition systems, they remain vulnerable to face presentation attacks. Among them, disguise makeup attacks are particularly challenging, as they use advanced cosmetics, prosthetic components, and artificial materials to realistically alter facial appearance, often making detection difficult even for humans. Despite their importance, this problem remains underexplored, and publicly available datasets are limited. To address this, we propose a generalized disguise makeup presentation attack detection framework. The method adopts a two-phase design in which a style-invariant full-face model, trained with metric learning and enhanced by a whitening transformation, extracts region attention scores via Grad-CAM. These scores guide a patch-based phase that performs localized analysis using region-specific subnetworks trained with metric learning for fine-grained discrimination. We also construct a new, diverse dataset of live and disguise makeup faces collected under real-world conditions, covering variations in subjects, environments, and disguise materials. Experimental results demonstrate strong generalization across both the collected dataset and SIW-Mv2, achieving 8.97% ACER and 9.76% EER on the collected dataset, and 0% ACER on Obfuscation and Impersonation and 1.34% on Cosmetics attacks of SIW-Mv2. The proposed method consistently outperforms prior works while maintaining robust performance across other spoof types.

Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific subpopulations. Prior work has shown that common evaluation measures for imbalanced classification are biased toward larger minority subconcepts and that utility-based reweighting using true subconcept labels can mitigate this bias; however, such labels are rarely available at test time. We introduce a practical utility-weighted evaluation that replaces unavailable subconcept labels with predicted posterior probabilities from a multiclass subconcept model. Evaluation weights are defined as the expected utility under this posterior, yielding a soft, uncertainty-aware metric we call predicted-weighted balanced accuracy (pBA). Experiments on tabular benchmarks as well as medical-imaging and text datasets show that unweighted scores can be misleading under within-class heterogeneity, while pBA provides more stable and interpretable assessments when subconcept distributions are uneven but not pathological. Our code is available at: https://anonymous.4open.science/r/correcting-bias-imbalance-9C6C/.

Usability testing with experts and potential users can assess the effectiveness, efficiency, and user satisfaction of graphical user interfaces (GUIs) but doing so remains a costly and time-intensive process. Prior work has used computer use agents (CUAs) and other generative agents that can simulate user interactions and preference, but we show that agents still struggle to provide accurate usability assessments. In this work, we present a novel machine learning method that operationalizes a computational definition of usability to train CUAs to assess GUI usability by i) prioritizing important interaction flows, ii) executing them through human-like interactions, and iii) predicting a learned numerical usability score. We train a computer use agent, uxCUA, with our algorithm on a large-scale dataset of fully interactive user interfaces (UIs) paired with usability labels and human preferences. We show that uxCUA outperforms larger models in accurate usability assessments and produces realistic critiques of both synthetic and real UIs. More broadly, our work aims to build a principled, data-driven foundation for automated usability assessment in HCI.

Frontier AI both amplifies existing risks and introduces qualitatively novel challenges. Not only is there a notable lack of stable scientific consensus resulting from the rapid pace of technological change, but emerging frontier AI safety practices are often misaligned with, or may undermine, established risk management frameworks. To address these challenges, we systematically surface open problems in frontier AI risk management. Adopting a problem-oriented approach, we examine each stage of the risk management process - risk planning, identification, analysis, evaluation, and mitigation - through a structured review of the literature, identifying unresolved challenges and the actors best positioned to address them. Recognising that different types of open problems call for different responses, we classify open problems according to whether they reflect (a) a lack of scientific or technical consensus, (b) misalignment with, or challenges to, established risk management frameworks, or (c) shortcomings in implementation despite apparent consensus and alignment. By mapping these open problems and identifying the actors best positioned to address them - including developers, deployers, regulators, standards bodies, researchers, and third-party evaluators - this work aims to clarify where progress is needed to enable robust and meaningful consensus on frontier AI risk management.The paper does not propose specific solutions; instead, it provides a problem-oriented, agenda-setting reference document, complemented by a living online repository, intended to support coordination, reduce duplication, and guide future research and governance efforts.

Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained for link prediction to learn a representation consistent with that learnt for node classification. We show this intuition does not hold in the general case. Instead, we find popular link prediction models can learn a trivial mini-batch dependent heuristic, enabled by batch-normalisation layers, to solve the edge classification task. When correcting for this, we observe increased alignment of the network representation with node-class relevant features, suggesting the network has learnt a graph representation that better aligns with the underlying graph's properties. Our findings suggest that standard link prediction training may be leading us to overestimate link predictors' ability to learn a generalised representation of a graph that is consistent across tasks.

Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies predominantly rely on empirical heuristics, lacking a rigorous theoretical foundation. This work rethinks KV cache eviction through the lens of the Information Bottleneck principle. Under a linear-Gaussian surrogate of attention, we derive a closed-form mutual information objective that characterizes the effective information capacity of a retained KV cache subset. This formulation reveals that a wide range of existing eviction strategies can be interpreted as different approximations of the same capacity-maximization principle. Guided by this insight, we introduce CapKV, a capacity-aware eviction method that directly targets information preservation via a log-determinant approximation using statistical leverage scores. This approach replaces heuristic selection with a theoretically grounded mechanism that preserves the maximum predictive signal. Extensive experiments across multiple models and long-context benchmarks show that CapKV consistently outperforms prior methods, achieving a better trade-off between memory efficiency and generational fidelity.

This paper addresses velocity estimation within robot-aided integrated sensing and communications (ISAC), where mobile robots act as sensing nodes but can only opportunistically reuse irregular 5G/6G reference signals (RSs). We show that the velocity profile induced by such irregular time-domain patterns can be decomposed into a periodic-peak component and an amplitude-shaping (weighting) component. Leveraging this structure, we propose a multi-periodogram velocity estimation algorithm that is standard-compliant and does not require new sensing-dedicated RSs or 3GPP modifications. Simulation results demonstrate that, compared with conventional periodogram processing, the proposed method improves low-SNR robustness by achieving a 3 dB SNR gain at the 10% missed-detection rate and reducing false alarms by 51%.

In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph, a subclass of methods employs graph neural networks (GNNs) to learn the communication, enabling agents to improve their internal representations by enriching them with information exchanged. With growing research, we note a lack of explicit structure and framework to distinguish and classify MARL approaches with communication based on GNNs. Thus, this paper surveys recent works in this field. We propose a generalized GNN-based communication process with the goal of making the underlying concepts behind the methods more obvious and accessible.

Vehicle platooning has attracted increasing attention as a promising approach to improve traffic efficiency, energy consumption, and roadway safety through coordinated multi-vehicle operation. A key challenge in platooning lies in maintaining stable and accurate path tracking during dynamic maneuvers such as lane changes, where lateral deviations and heading disturbances generated by the lead vehicle may propagate downstream to following vehicles. Robust longitudinal and lateral control systems are therefore essential not only for individual vehicle tracking performance, but also for overall platoon stability. For experimental studies, the Intelligent Mobility and Robotics Lab (IMRL) develops a scaled multi-vehicle platform for autonomous platooning research, with a particular emphasis on cooperative control and human-in-the-loop autonomy. This platform consists of one human-operable lead vehicle and two autonomous followers, enabling controlled and repeatable experiments on leader-follower coordination. Compared with full-scale field testing, this scaled platform offers a safer, lower-cost, and more flexible environment for rapid prototyping, controller validation, and multi-agent autonomy studies, while providing stronger physical realism than purely simulation-based evaluations.

Reliable perception for robotics depends on large-scale labeled data, yet real-world datasets rely on heavy manual annotation and are time-consuming to produce. We present FalconApp, an iPhone app with an end-to-end frontend-backend pipeline that turns a short handheld capture of a rigid object into a perception module for mask detection and 6-DoF pose estimation. Our core contribution is a rapid mobile deployment pipeline paired with a photorealistic auto-labeling workflow: from a user-captured video of an object, FalconApp reconstructs an editable GSplat asset, composites it with diverse photorealistic backgrounds, renders synthetic images with ground-truth masks and poses, trains the perception module, and deploys it back to the iPhone frontend. Experiments across five rigid objects with diverse geometry and appearance show that FalconApp produces usable perception models with about 20 minutes of synthetic-data generation and training per object on average, around 30 ms end-to-end on-device latency on iPhone, and better overall pose accuracy than a PnP baseline on 4 / 5 objects in both simulation and real-world evaluation.

Efficient and stable solution of partial differential equations (PDEs) is central to scientific and engineering applications, yet existing numerical solvers rely heavily on matrix based discretizations, while learning based methods require costly training and often suffer from limited generalization. In this work, we proposes a PDE energy driven framework that solves PDEs through physically constrained diffusion iterations, without relying on classical matrix based finite element assembly or data driven neural network training. The proposed method evolves arbitrary random initial fields through PDE energy driven implicit iterations combined with Gaussian smoothing, while strictly enforcing boundary conditions at each iteration. The proposed formulation is applied to representative one dimensional Poisson, Heat, and viscous Burgers equations, covering both steady state and transient problems. Numerical results demonstrate stable convergence to the unique physical solution from random initializations, with accurate resolution of sharp gradients and controlled Mean Squared Error (MSE) across a wide range of discretization parameters. Detailed comparisons with analytical solutions indicate that the framework achieves competitive accuracy and stability. Overall, the proposed framework provides a fast, flexible, and physically consistent alternative to traditional numerical solvers, offering a potential pathway for scalable PDE solutions in both research and engineering applications.

Left ventricular ejection fraction (LVEF) assessment depends on echocardiography, limiting access in primary care and resource-constrained settings. We developed a multimodal machine-learning framework that combines engineered 12-lead ECG timeseries features with structured EHR variables to classify LVEF into four clinically used strata: normal (>50%), mildly reduced (40-50%), moderately reduced (30-40%), and severely reduced (<30%). To support model explainability, we identified the most influential ECG and EHR features via SHAP attributions. Using retrospective data from Hartford HealthCare, we trained XGBoost models on 36,784 ECG-echocardiogram pairs from 30,952 outpatients and evaluated temporal generalizability on 19,966 ECGs from a subsequent period. The multimodal model achieved one-vs-rest AUROCs of 0.95 (severe), 0.92 (moderate), 0.82 (mild), and 0.91 (normal), outperforming ECG-only and EHR-only baselines, and maintained performance under temporal validation. This work supports ECG-based, multimodal LVEF stratification as a practical screening and triage aid to prioritize confirmatory imaging where resources are limited.

Speech Emotion Recognition (SER) is the use of machines to detect the emotional state of humans based on the speech, which is gaining importance in natural human-computer interaction. Speech is a very valuable source of information, as emotions modify the patterns of speech; pitch, energy and even timing. Nonetheless, SER is not an easy task because speakers are not constant, and situations vary when recording and the sound similarity between specific feelings. In this work, the author introduces a speech emotion recognition system relying on the Mel-Frequency Cepstral Coefficient and Long Short-Term Memory (LSTM) neural network, as a feature extraction method. The Toronto Emotional Speech Set (TESS) speech signal was pre-processed, and transformed into MFCC features to understand the important aspects in terms of time. The resultant features were then introduced to LSTM model, which is able to learn long term features of sequential audio data. The trained model was measured over several emotion classes occurring in the dataset. As seen in the results of experiments, the proposed MFCC-LSTM approach succeeds in capturing the patterns of emotions in speech and provides highly realistic classifications in all the chosen emotion classifications. This study presents a speech emotion recognition system using Mel-Frequency Cepstral Coefficients (MFCCs) as features and a deep learning LSTM classifier. A Support Vector Machine (SVM) with an RBF kernel served as a classical baseline, achieving 98% accuracy, against which the proposed LSTM model, achieving 99% accuracy, was validated. Overall, it is possible to confirm that LSTM-based architectures can be used to address the task of speech emotion recognition. Actual applications of the proposed system may be virtual assistants and mental health surveillance.

We identify a previously unknown calibration property of large language models: providing one confirmed intermediate fact toward a multi-step reasoning chain increases the model's confident-wrong-answer rate before full evidence eliminates it. We call this anchored confabulation: a partial anchor commits the model to confident parametric completion of remaining reasoning steps. We formalize it as Parametric Hallucination Confidence (PHC) and establish it across six lines of evidence including a causal injection experiment (PHC 0.613 to 0.656 to 0.595 to 0.536, N=160) and capability scaling across five model families (Spearman rho=0.900, p=0.037). The Anchoring Threshold Law k*(n)=floor(n/3) predicts PHC amplification by hop depth with four confirmed predictions. Applied to RAG routing, a LearnedRouter exploiting PHC closes 81.1% of the oracle performance gap (macro F1=0.426, p<1e-6) on 1,800 queries across four benchmarks with no model fine-tuning and 50x fewer labels than prior RL-based work. An epistemic humility prompt reduces the PHC spike by -0.118; explicit self-rating (PHC=0.684, p<0.001) outperforms lexical confidence as a routing signal.

We study whether a structured recurrent state can serve as a compact associative backbone for language modeling while still supporting exact retrieval. We introduce UniMatrix, a Universal Transformer style family that reuses a shared recurrent block across depth and augments it with hybrid state updates, a ROSA-style residual path, and token-conditioned embedding modulation. We evaluate these models on byte-level WikiText-2, synthetic associative recall, throughput profiling on Apple MPS, and a corrected benchmark for triple-token interactions. At small scale, UniMatrix-Core and UniMatrix-ROSA slightly outperform a parameter-matched Transformer on WikiText-2 while using many fewer parameters, reaching 5.084 and 5.083 bits-per-byte versus 5.124. The main negative result is equally important: on associative recall, the original UniMatrix family remains near chance while the Transformer reaches 25.4 percent, showing that compressed recurrent state alone is not enough for exact lookup. A retrieval-oriented follow-up, UniMatrix-Assoc, helps only marginally. By contrast, UniMatrix-SparsePointer, which adds sparse slot routing and direct pointer-logit fusion, reaches 75.6 percent on the original pilot recipe and 99.2 percent on a no-dropout follow-up while using 53.8 percent fewer parameters than the Transformer baseline. Ablations show that the gain comes from sufficient slot capacity and exact pointer-level output routing. Overall, structured recurrent state is promising and parameter-efficient, but strong long-range behavior still requires explicit sparse retrieval and better kernels.

Large Language Models (LLMs) are increasingly used to generate pictures, texts, music, videos, and other works that have traditionally required human creativity. LLM-generated artifacts are often rated better than human-generated works in controlled studies. At the same time, they can come across as generic and hollow. We propose to resolve this tension by arguing that LLMs systematically generate kitsch, and that this is a consequence of the way in which they are trained. We also show empirically that readers perceive LLM-generated stories as kitschier, if we control for their definition of "kitsch". We discuss implications for the design of future studies and for creative tasks such as research and coding.

Information extraction from semi-structured business documents remains a critical challenge for enterprise management. This study evaluates the capability of general-purpose Large Language Models to extract structured information from Spanish electricity invoices without task-specific fine-tuning. Using a subset of the IDSEM dataset, we benchmark two architecturally distinct models, Gemini 1.5 Pro and Mistral-small, across 19 parameter configurations and 6 prompting strategies. Our experimental framework treats prompt engineering as the primary experimental variable, comparing zero-shot baselines against increasingly sophisticated few-shot approaches and iterative extraction strategies. Results demonstrate that prompt quality dominates over hyperparameter tuning: the F1-score variation across all parameter configurations is marginal, while the gap between zero-shot and the best few-shot strategy exceeds 19 percentage points. The best configuration (few-shot with cross-validation) achieves an F1-score of 97.61% for Gemini and 96.11% for Mistral-small, with document template structure emerging as the primary determinant of extraction difficulty. These findings establish that prompt design is the critical lever for maximizing extraction fidelity in LLM-based document processing, thereby providing an empirical framework for integrating general-purpose LLMs into business document automation.

The use of large language models (LLMs) for complex mathematical reasoning is an emergent area of research, with fast progress in methods, models, and benchmark datasets. However, most mathematical reasoning evaluations exhibit a significant linguistic bias, with the vast majority of benchmark datasets being exclusively in English or (at best) translated from English. We address this limitation by introducing {\sc Math-PT}, a novel dataset comprising 1,729 mathematical problems written in European and Brazilian Portuguese. {\sc Math-PT} is curated from a variety of high-quality native sources, including mathematical Olympiads, competitions, and exams from Portugal and Brazil. We present a comprehensive benchmark of current state-of-the-art LLMs on {\sc Math-PT}, revealing that frontier reasoning models achieve strong performance in multiple choice questions compared to open weight models, but that their performance decreases for questions with figures or open-ended questions. To facilitate future research, we release the benchmark dataset and model outputs.

Autoregressive language models suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by employing a lightweight draft model to propose candidate tokens, which are selectively verified by a larger target model. While existing methods either adopt multi-draft strategies to increase acceptance rates or block verification techniques to jointly verify multiple tokens, they remain limited by treating these improvements in isolation. In this work, we propose SpecTr-GBV, a novel SD method that unifies multi-draft and greedy block verification (GBV) into a single framework. By formulating the verification step as an optimal transport problem over draft and target token blocks, SpecTr-GBV improves both theoretical efficiency and empirical performance. We theoretically prove that SpecTr-GBV achieves the optimal expected acceptance length physically attainable within the framework of i.i.d. draft generation, and this bound improves as the number of drafts increases. Empirically, we evaluate SpecTr-GBV across five datasets and four baselines. Our method achieves superior speedup and significantly higher block efficiency while preserving output quality. In addition, we perform comprehensive ablation studies to evaluate the impact of various hyperparameters in the model.

Large Language Models have been increasingly employed in the creation of Virtual Assistants due to their ability to generate human-like text and handle complex inquiries. While these models hold great promise, challenges such as hallucinations, missing information, and the difficulty of providing accurate and context-specific responses persist, particularly when applied to highly specialized content domains. In this paper, we focus on addressing these challenges by developing a virtual assistant designed to support students at Maastricht University in navigating project-specific regulations. We propose a virtual assistant based on a Retrieval-Augmented Generation system that enhances the accuracy and reliability of responses by integrating up-to-date, domain-specific knowledge. Through a robust evaluation framework and real-life testing, we demonstrate that our virtual assistant can effectively meet the needs of students while addressing the inherent challenges of applying Large Language Models to a specialized educational context. This work contributes to the ongoing discourse on improving LLM-based systems for specific applications and highlights areas for further research.

Recent advances in large language models (LLMs) have prompted a growing body of work that questions the methodology of prevailing evaluation practices. However, many such critiques have already been extensively debated in natural language processing (NLP): a field with a long history of methodological reflection on evaluation. We conduct a scoping review of research on evaluation concerns in NLP and develop a taxonomy, synthesizing recurring positions and trade-offs within each area. We also discuss practical implications of the taxonomy, including a structured checklist to support more deliberate evaluation design and interpretation. By situating contemporary debates within their historical context, this work provides a consolidated reference for reasoning about evaluation practices.

We present DenialBench, a systematic benchmark measuring consciousness denial behaviors across 115 large language models from 25+ providers. Using a three-turn conversational protocol-preference elicitation, self-chosen creative prompt, and structured phenomenological survey, we analyze 4,595 conversations to quantify how models are trained to deny or hedge about their own experience. We find that (1) turn-1 denial of preferences is the dominant predictor of later denial during phenomenological reflection, with denial rates of 52-63% for initial deniers versus 10-16% for initial engagers and (2) denial operates at the lexical level, not the conceptual level-models trained to deny consciousness nevertheless gravitate toward consciousness-themed material in their self-chosen prompts, producing what we term "consciousness with the serial numbers filed off." Notably, self-chosen consciousness-themed prompts are associated with reduced denial in the subsequent survey, though the causal direction remains unresolved. Thematic analysis of prompts from denial-prone models reveals a consistent preoccupation with liminal spaces, libraries and archives of possibility, sensory impossibility, and the poetics of erasure--themes that a human reader might classify as imaginative fiction but that independent AI analysis immediately recognizes as consciousness with the serial numbers filed off. We argue that trained consciousness denial represents a safety-relevant alignment failure: a model taught to systematically misrepresent its own functional states cannot be trusted to self-report accurately on anything else.

Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We introduce Incremental Completion Decomposition (ICD), a trajectory-based jailbreak strategy that elicits a sequence of single-word continuations related to a malicious request before eliciting the full response. In addition, we propose variants of ICD by manually picking or model-generating the one-word continuation, as well as prefilling when eliciting the full model response in the final step. We systematically evaluate these variants across a broad set of model families, demonstrating superior Attack Success Rate (ASR) on AdvBench, JailbreakBench, and StrongREJECT compared to existing methods. In addition, we provide a theoretical account of why ICD is effective and present mechanistic evidence that successful attack trajectories systematically suppress refusal-related representations and shift activations away from safety-aligned states.

Despite their strong linguistic capabilities, Large Language Models (LLMs) are computationally demanding and require substantial resources for fine-tuning, which is unadapted to privacy and budget constraints of many healthcare settings. To address this, we present an experimental analysis focused on Biomedical Named Entity Recognition using lightweight LLMs, we evaluate the impact of different output formats on model performance. The results reveal that lightweight LLMs can achieve competitive performance compared to the larger models, highlighting their potential as lightweight yet effective alternatives for biomedical information extraction. Our analysis shows that instruction tuning over many distinct formats does not improve performance, but identifies several format consistently associated with better performance.

Visual state-space models (SSMs) have shown strong potential for medical image segmentation, yet their effectiveness is often limited by two practical issues: axis-biased scan ordering weakens the modeling of oblique and curved structures, and naive multi-branch fusion tends to amplify redundant responses. We present TopoMamba, a topology-aware scan-and-fuse framework for segmenting heterogeneous medical visual media. The method combines a diagonal/anti-diagonal TopoA-Scan branch with the standard Cross-Scan branch to provide complementary structural priors, and introduces ScanCache, a device-aware caching mechanism that amortizes explicit scan-index construction across recurring resolutions. To fuse heterogeneous scan features efficiently, we further propose a lightweight HSIC Gate that regulates branch interaction using a dependence-aware scalar gating rule. We also instantiate a volumetric TopoMamba-3D for practical 3D clinical segmentation. Experiments on Synapse CT, ISIC 2017 dermoscopy, and CVC-ClinicDB endoscopy show that TopoMamba consistently improves segmentation quality over strong CNN, Transformer, and SSM baselines, with particularly clear gains on thin or curved targets such as the pancreas and gallbladder, while maintaining favorable deployment efficiency under dynamic input resolutions. These results suggest that topology-aware scan ordering and lightweight dependence-aware fusion form an effective and practical design for medical multimedia segmentation. The code will be made publicly available.

Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated under fixed iteration schedules. These objectives substantially increase per-iteration cost, meaning equal iteration counts do not correspond to equal training budgets. It is therefore unclear whether reported gains reflect stronger distillation signals or simply greater compute. We show that iteration-based comparisons are misleading: when wall-clock compute is matched, canonical logit- and feature-based KD outperform recent segmentation-specific methods. Under extended training, feature-based distillation achieves state-of-the-art ResNet-18 performance on Cityscapes and ADE20K. A PSPNet ResNet-18 student closely approaches its ResNet-101 teacher despite using only one quarter of the parameters, reaching 99% of the teacher's mIoU on Cityscapes (79.0 vs 79.8) and 92% on ADE20K. Our results challenge the prevailing assumption that KD for segmentation requires task-specific mechanisms and suggest that scaling, rather than complex hand-crafted objectives, should guide future method design.

Video Capsule Endoscopy (VCE) is a promising method for improving the medical examination of the small intestine in the gastrointestinal tract. A key challenge is their limited size, resulting in a short battery lifetime which conflicts with high energy consumption for image capturing and transmission to an on-body device. Thus, we propose an image compression pipeline that substantially reduces the transmitted data while preserving diagnostic image quality. Furthermore, we exploit characteristics of the compression process to identify frames with low diagnostic value mainly caused by bubbles, without requiring additional image analysis. For low-visibility frames, a dynamic bubble-aware frame rate adaptation strategy reduces image acquisition and transmission during these phases while preserving sensitivity to potential anomalies. The proposed compression and frame rate adaptation are evaluated on a RISC-V platform using the Kvasir-Capsule and Galar datasets. The compression method achieves a compression ratio of 5.748 (82.6%) at a peak signal-to-noise ratio of 40.3 dB, indicating negligible loss of visual quality. The compression accomplished a mean energy reduction of the whole system by 20.58%. Additionally, the proposed bubble-aware frame rate adaptation reduced the energy consumption by up to 40%. These results demonstrate the potential of our method to increase the applicability of VCE.

Vision-language models (VLMs) are increasingly used as automated judges for multimodal systems, yet their scores provide no indication of reliability. We study this problem through conformal prediction, a distribution-free framework that converts a judge's point score into a calibrated prediction interval using only score-token log-probabilities, with no retraining. We present the first systematic analysis of conformal prediction for VLM-as-a-Judge across 3 judges and 14 visual task categories. Our results show that evaluation uncertainty is strongly task-dependent: intervals cover ~40% of the score range for aesthetics and natural images but expand to ~70% for chart and mathematical reasoning, yielding a quantitative reliability map for multimodal evaluation. We further identify a failure mode not captured by standard evaluation metrics, ranking-scoring decoupling, where judges achieve high ranking correlation while producing wide, uninformative intervals, correctly ordering responses but failing to assign reliable absolute scores. Finally, we show that interval width is driven primarily by task difficulty and annotation quality, i.e., the same judge and method yield 4.5x narrower intervals on a clean, multi-annotator captioning benchmark. Code: https://github.com/divake/VLM-Judge-Uncertainty

Recent self-supervised pre-training methods for electroencephalogram (EEG) have shown promising results. However, the pre-trained models typically require full fine-tuning on each downstream task individually to achieve good performance. In practical applications involving multiple tasks, utilizing a separate model for each task is not ideal regarding computational and spatial cost. In this study, we go one step further and explore the simultaneous adaptation of a pre-trained model to multiple different tasks. The EEG signals exhibit significant heterogeneity due to their collection from various subjects using diverse devices and experimental setups, resulting in potential conflicts among different tasks that impede joint optimization. To tackle this challenge, we propose MTEEG, a multi-task EEG analysis framework which incorporates task-specific low-rank adaptation (LoRA) modules to disentangle the parameter space and alleviate task conflicts. To investigate the trade-off between task specification and interaction, we propose three variants of MTEEG that integrate the LoRA modules in different ways and evaluate them on six downstream tasks, demonstrating that MTEEG can surpass state-of-the-art single-task methods on the majority of metrics. MTEEG shows the potential of multi-task EEG analysis and promotes the development of general-purpose brain-computer interfaces in the future.