Accurate prediction of future risk and disease progression in sepsis is clinically important for early warning and timely intervention in intensive care. However, short-window sepsis prediction remains challenging, because shorter observation windows provide limited historical evidence, whereas longer prediction horizons reduce the number of patient trajectories with valid future supervision. To address this problem, we propose CSRA, a Controlled Spectral Residual Augmentation framework for short-window multi-system ICU time series. CSRA first groups variables by clinical systems and extracts system-level and global representations. It then performs input-adaptive residual perturbation in the spectral domain to generate structured and clinically plausible trajectory variations. To improve augmentation stability and controllability, CSRA is trained end-to-end with the downstream predictor under a unified objective, together with anchor consistency loss and controller regularization. Experiments on a MIMIC-IV sepsis cohort across multiple downstream models show that CSRA is consistently competitive and often superior, reducing regression error by 10.2\% in MSE and 3.7\% in MAE over the non-augmentation baseline, while also yielding consistent gains on classification. CSRA further maintains more favorable performance under shorter observation windows, longer prediction horizons, and smaller training data scales, while also remaining effective on an external clinical dataset~(ZiGongICUinfection), indicating stronger robustness and generalizability in clinically constrained settings.

Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production logs. These pairs constitute a free, growing training set: a lightweight surrogate trained on them can absorb a significant portion of future traffic at near-zero marginal inference cost. The open questions are when the surrogate is reliable enough to deploy, what it handles versus defers, and how that boundary evolves as data accumulates. We introduce TRACER (Trace-based Adaptive Cost-Efficient Routing), an open-source system that trains ML surrogates on an LLM's own production traces and governs deployment through a parity gate: the surrogate is activated only when its agreement with the LLM exceeds a user-specified threshold α. To make the routing boundary transparent, TRACER generates interpretability artifacts describing which input regions the surrogate handles, where it plateaus, and why it defers. On a 77-class intent benchmark with a Sonnet 4.6 teacher, TRACER achieves 83-100% surrogate coverage depending on the quality target α; on a 150-class benchmark, the surrogate fully replaces the teacher. On a natural language inference task, the parity gate correctly refuses deployment because the embedding representation cannot support reliable separation. The system is available as open-source software.

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors are not uniformly distributed but often originate from a small number of early transition points, after which reasoning remains locally coherent but globally incorrect. These transitions coincide with localized spikes in token-level entropy, and alternative continuations from the same intermediate state can still lead to correct solutions. Based on these observations, we introduce GUARD, a targeted inference-time framework that probes and redirects critical transitions using uncertainty signals. Empirical evaluations across multiple benchmarks confirm that interventions guided by these failure dynamics lead to more reliable reasoning outcomes. Our findings highlight the importance of understanding when and how reasoning first deviates, complementing existing approaches that focus on scaling inference-time computation.

A low cost fluorescence-based optical system is developed for detecting the presence of certain microorganisms and molecules within a diluted sample. A specifically designed device setup compatible with conventional 96 well plates is chosen to create an ideal environment in which a smart phone camera can be used as the optical detector. In comparison with conventional microplate reading machines such as Perkin Elmer Victor Machine, the device presented in this paper is not equipped with expensive elements such as exciter filer, barrier filter and photomultiplier; instead, a phone camera is all needed to detect fluorescence within the sample. The strategy being involved is to determine the relationship between the image color of the sample in RGB color space and the molar concentration of the fluorescence specimen in that sample. This manuscript is a preprint version of work related to a publication in IEEE. The final version may differ from this manuscript.

Existing single-modal RGB trackers often face performance bottlenecks in complex dynamic scenes, while the introduction of event sensors offers new potential for enhancing tracking capabilities. However, most current RGB-event fusion methods, primarily designed in the spatial domain using convolutional, Transformer, or Mamba architectures, fail to fully exploit the unique temporal response and high-frequency characteristics of event data. To address this, we1 propose FreqTrack, a frequency-aware RGBE tracking framework that establishes complementary inter-modal correlations through frequency-domain transformations for more robust feature fusion. We design a Spectral Enhancement Transformer (SET) layer that incorporates multi-head dynamic Fourier filtering to adaptively enhance and select frequency-domain features. Additionally, we develop a Wavelet Edge Refinement (WER) module, which leverages learnable wavelet transforms to explicitly extract multi-scale edge structures from event data, effectively improving modeling capability in high-speed and low-light scenarios. Extensive experiments on the COESOT and FE108 datasets demonstrate that FreqTrack achieves highly competitive performance, particularly attaining leading precision of 76.6\% on the COESOT benchmark, validating the effectiveness of frequency-domain modeling for RGBE tracking.

Large language models frequently produce mutually inconsistent answers when reasoning over multiple related queries. We study case-file logical consistency: maintaining a globally satisfiable belief state across interdependent queries. We introduce a benchmark of 390 multi-query reasoning instances with entailment/contradiction/unknown labels and propose set-level metrics including Case Satisfiability Rate, Contradiction Density and Revision Cost. Our solver-augmented approach extracts commitments, verifies global satisfiability and performs counterexample-guided repair. Across four reasoning domains, our method substantially reduces cross-query contradictions (SetCons: 0.56 to 0.94) while preserving per-query accuracy, demonstrating that global coherence is critical for robust multi-query reasoning.

Omni-modal Large Language Models (Omni-MLLMs) promise a unified integration of diverse sensory streams. However, recent evaluations reveal a critical performance paradox: unimodal baselines frequently outperform joint multimodal inference. We trace this perceptual fragility to the static fusion topologies universally employed by current models, identifying two structural pathologies: positional bias in sequential inputs and alignment traps in interleaved formats, which systematically distort attention regardless of task semantics. To resolve this functional rigidity, we propose Chain of Modality (CoM), an agentic framework that transitions multimodal fusion from passive concatenation to dynamic orchestration. CoM adaptively orchestrates input topologies, switching among parallel, sequential, and interleaved pathways to neutralize structural biases. Furthermore, CoM bifurcates cognitive execution into two task-aligned pathways: a streamlined ``Direct-Decide'' path for direct perception and a structured ``Reason-Decide'' path for analytical auditing. Operating in either a training-free or a data-efficient SFT setting, CoM achieves robust and consistent generalization across diverse benchmarks.

Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especially pronounced in class incremental learning (CIL), which is the most challenging setting in continual learning. Existing methods to address catastrophic forgetting often sacrifice either model interpretability or accuracy. To address this challenge, we introduce ClassIncremental Concept Bottleneck Model (CI-CBM), which leverage effective techniques, including concept regularization and pseudo-concept generation to maintain interpretable decision processes throughout incremental learning phases. Through extensive evaluation on seven datasets, CI-CBM achieves comparable performance to black-box models and outperforms previous interpretable approaches in CIL, with an average 36% accuracy gain. CICBM provides interpretable decisions on individual inputs and understandable global decision rules, as shown in our experiments, thereby demonstrating that human understandable concepts can be maintained during incremental learning without compromising model performance. Our approach is effective in both pretrained and non-pretrained scenarios; in the latter, the backbone is trained from scratch during the first learning phase. Code is publicly available at github.com/importAmir/CI-CBM.

Large Language Models (LLMs) are increasingly used in scientific peer review, assisting with drafting, rewriting, expansion, and refinement. However, existing peer-review LLM detection methods largely treat authorship as a binary problem-human vs. AI-without accounting for the hybrid nature of modern review workflows. In practice, evaluative ideas and surface realization may originate from different sources, creating a spectrum of human-AI collaboration. In this work, we introduce PeerPrism, a large-scale benchmark of 20,690 peer reviews explicitly designed to disentangle idea provenance from text provenance. We construct controlled generation regimes spanning fully human, fully synthetic, and multiple hybrid transformations. This design enables systematic evaluation of whether detectors identify the origin of the surface text or the origin of the evaluative reasoning. We benchmark state-of-the-art LLM text detection methods on PeerPrism. While several methods achieve high accuracy on the standard binary task (human vs. fully synthetic), their predictions diverge sharply under hybrid regimes. In particular, when ideas originate from humans but the surface text is AI-generated, detectors frequently disagree and produce contradictory classifications. Accompanied by stylometric and semantic analyses, our results show that current detection methods conflate surface realization with intellectual contribution. Overall, we demonstrate that LLM detection in peer review cannot be reduced to a binary attribution problem. Instead, authorship must be modeled as a multidimensional construct spanning semantic reasoning and stylistic realization. PeerPrism is the first benchmark evaluating human-AI collaboration in these settings. We release all code, data, prompts, and evaluation scripts to facilitate reproducible research at https://github.com/Reviewerly-Inc/PeerPrism.

As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a frequently-faced issue. To solve it, the few-shot anomaly detection (FSAD) scheme is attracting increasing attention. In recent years, beyond traditional visual paradigm, Vision-Language Model (VLM) has been extensively explored to boost this field. However, in currently-existing VLM-based FSAD schemes, almost all perform anomaly inference only by pairwise feature matching, ignoring structural dependencies and global consistency. To further redound to FSAD via VLM, we propose a Heterogeneous Hypergraph Vision-Language Reasoning (H2VLR) framework. It reformulates the FSAD as a high-order inference problem of visual-semantic relations, by jointly modeling visual regions and semantic concepts in a unified hypergraph. Experimental comparisons verify the effectiveness and advantages of H2VLR. It could often achieve state-of-the-art (SOTA) performance on representative industrial and medical benchmarks. Our code will be released upon acceptance.

Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images due to the contextual similarity of neighboring patches, leading to information leakage and SSL simplification. Hierarchical shifted window (Swin) transformer, a highly effective approach for medical images cannot use advanced masking methods as it lacks a global [CLS] token. Hence, we introduced an attention guided masking mechanism for Swin within a co-distillation learning framework to selectively mask semantically co-occurring and discriminative patches, to reduce information leakage and increase the difficulty of SSL pretraining. However, attention guided masking inevitably reduces the diversity of attention heads, which negatively impacts downstream task performance. To address this, we for the first time, integrate a noisy teacher into the co-distillation framework (termed DAGMaN) that performs attentive masking while preserving high attention head diversity. We demonstrate the capability of DAGMaN on multiple tasks including full- and few-shot lung nodule classification, immunotherapy outcome prediction, tumor segmentation, and unsupervised organs clustering.

We study the expressive power and limitations of multi-layer state-space models (SSMs). First, we show that multi-layer SSMs face fundamental limitations in compositional tasks, revealing an inherent gap between SSMs and streaming models. Then, we examine the role of chain-of-thought (CoT), showing that offline CoT does not fundamentally increase the expressiveness, while online CoT can substantially increase its power. Indeed, with online CoT, multi-layer SSMs become equivalent in power to streaming algorithms. Finally, we investigate the tradeoff between width and precision, showing that these resources are not interchangeable in the base model, but admit a clean equivalence once online CoT is allowed. Overall, our results offer a unified perspective on how depth, finite precision, and CoT shape the power and limits of SSMs.

Expert specialization is fundamental to Mixture-of-Experts (MoE) model success, yet existing metrics (cosine similarity, routing entropy) lack theoretical grounding and yield inconsistent conclusions under reparameterization. We present an information-geometric framework providing the first rigorous characterization of MoE specialization dynamics. Our key insight is that expert routing distributions evolve on the probability simplex equipped with the Fisher information metric, enabling formal analysis via Riemannian geometry. We prove that standard heuristic metrics violate parameterization invariance (Theorem 1), establish that specialization corresponds to geodesic flow with quantified approximation bounds (Theorem 2), and derive a failure predictor with theoretical threshold justification (Theorem 3). The framework introduces two principled metrics: Fisher Specialization Index (FSI) achieving r=0.91+/-0.02 correlation with downstream performance, and Fisher Heterogeneity Score (FHS) predicting training failure at 10% completion with AUC=0.89+/-0.03 -- outperforming validation-loss-based early stopping by 23% while requiring 40x fewer compute cycles. We validate intervention protocols achieving 87% recovery rate when FHS>1 is detected. Comprehensive experiments across language modeling (WikiText-103, C4), vision MoE (ImageNet), and scaling studies (8-64 experts, 125M-2.7B parameters) validate our theoretical predictions.

Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its statistical role remains poorly understood. We formalize synthetic augmentation as a modification of the effective training distribution and show that it induces a structural bias--variance trade-off: while additional samples may reduce estimation error, they may also shift the population objective whenever the synthetic distribution deviates from regions relevant under evaluation. To isolate informational gains from mechanical sample-size effects, we introduce a size-matched null augmentation and a finite-sample, non-parametric block permutation test that remains valid under weak temporal dependence. We evaluate this framework in both controlled Markov-switching environments and real financial datasets, including high-frequency option trade data and a daily equity panel. Across generators spanning bootstrap, copula-based models, variational autoencoders, diffusion models, and TimeGAN, we vary augmentation ratio, model capacity, task type, regime rarity, and signal-to-noise. We show that synthetic augmentation is beneficial only in variance-dominant regimes, such as persistent volatility forecasting-while it deteriorates performance in bias-dominant settings, including near-efficient directional prediction. Rare-regime targeting can improve domain-specific metrics but may conflict with unconditional permutation inference. Our results provide a structural perspective on when synthetic data improves financial learning performance and when it induces persistent distributional distortion.

Quantization is a natural complement to the sparse, event-driven computation of Spiking Neural Networks, reducing memory bandwidth and arithmetic cost for deployment on resource-constrained hardware. However, existing SNN quantization evaluation focuses almost exclusively on accuracy, overlooking whether a quantized network preserves the firing behavior of its full-precision counterpart. We demonstrate that quantization method, clipping range, and bit-width can produce substantially different firing distributions at equivalent accuracy, differences invisible to standard metrics but relevant to deployment, where firing activity governs effective sparsity, state storage, and event-processing load. To capture this gap, we propose Earth Mover's Distance as a diagnostic metric for firing distribution divergence, and apply it systematically across weight and membrane quantization on SEW-ResNet architectures trained on CIFAR-10 and CIFAR-100. We find that uniform quantization induces distributional drift even when accuracy is preserved, while LQ-Net style learned quantization maintains firing behavior close to the full-precision baseline. Our results suggest that behavior preservation should be treated as an evaluation criterion alongside accuracy, and that EMD provides a principled tool for assessing it.

Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanistic interpretability has recently focused on studying task-specific computational graphs, defined by connections (edges) between model components. Such edge-based circuits have been defined in the context of large language models, yet vision-based approaches so far only consider neuron-based circuits. These tell which information is encoded, but not how it is routed through the complex wiring of a neural network. In this work, we investigate whether useful mechanistic circuits can be identified through computational graphs in vision transformers. We propose an effective method for Automatic Visual Circuit Discovery (Vi-CD) that recovers class-specific circuits for classification, identifies circuits underlying typographic attacks in CLIP, and discovers circuits that lend themselves for steering to correct harmful model behavior. Overall, we find that insightful and actionable edge-based circuits can be recovered from vision transformers, adding transparency to the internal computations of these models.

Tool-augmented large language model (LLM) agents can orchestrate specialist classifiers, segmentation models, and visual question-answering modules to interpret chest X-rays. However, these agents still solve each case in isolation: they fail to accumulate experience across cases, correct recurrent reasoning mistakes, or adapt their tool-use behavior without expensive reinforcement learning. While a radiologist naturally improves with every case, current agents remain static. In this work, we propose Evo-MedAgent, a self-evolving memory module that equips a medical agent with the capacity for inter-case learning at test time. Our memory comprises three complementary stores: (1)~\emph{Retrospective Clinical Episodes} that retrieve problem-solving experiences from similar past cases, (2)~an \emph{Adaptive Procedural Heuristics} bank curating priority-tagged diagnostic rules that evolves via reflection, much like a physician refining their internal criteria, and (3)~a \emph{Tool Reliability Controller} that tracks per-tool trustworthiness. On ChestAgentBench, Evo-MedAgent raises multiple-choice question (MCQ) accuracy from 0.68 to 0.79 on GPT-5-mini, and from 0.76 to 0.87 on Gemini-3 Flash. With a strong base model, evolving memory improves performance more effectively than orchestrating external tools on qualitative diagnostic tasks. Because Evo-MedAgent requires no training, its per-case overhead is bounded by one additional retrieval pass and a single reflection call, making it deployable on top of any frozen model.

Traditional esports scouting workflows rely heavily on manual video review and aggregate performance metrics, which often fail to capture the nuanced decision-making patterns necessary to determine if a prospect fits a specific tactical archetype. To address this, we reframe style-based player evaluation in esports as an Inverse Reinforcement Learning (IRL) problem. In this paper, we introduce a novel player selection framework that learns professional-specific reward functions from logged gameplay demonstrations, allowing organizations to rank candidates by their stylistic alignment with a target star player. Our proposed architecture utilizes a multimodal, two-branch intake: one branch encodes structured state-action trajectories derived from high-resolution in-game telemetry, while the second encodes temporally aligned tactical pseudo-commentary generated by Vision-Language Models (VLMs) from broadcast footage. These representations are fused and evaluated via a Generative Adversarial Imitation Learning (GAIL) objective, where a discriminator learns to capture the unique mechanical and tactical signatures of elite professionals. By transitioning from generic skill estimation to scouting "by reward," this framework provides a scalable, workflow-aware digital twin system that enables data-driven roster construction and targeted talent discovery across massive candidate pools.

A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model's generation. Existing methods select these subsets primarily using similarity between user memory items and input queries, ignoring how features actually affect the model's response distribution. We propose Response-Utility optimization for Memory Selection (RUMS), a novel method that selects user memory items by measuring the mutual information between a subset of memory and the model's outputs, identifying items that reduce response uncertainty and sharpen predictions beyond semantic similarity. We demonstrate that this information-theoretic foundation enables more principled user memory selection that aligns more closely with human selection compared to state-of-the-art methods, and models $400\times$ larger. Additionally, we show that memory items selected using RUMS result in better response quality compared to existing approaches, while having up to $95\%$ reduction in computational cost.

Physics-informed neural networks (PINNs) are often selected by a single scalar loss even when the quantity of interest is more specific. We study a hybrid design in which the governing PDE residual remains automatic-differentiation (AD) based, while finite differences (FD) appear only in a weak auxiliary term that penalizes gradients of the sampled residual field. The FD term regularizes the residual field without replacing the PDE residual itself. We examine this idea in two stages. Stage 1 is a controlled Poisson benchmark comparing a baseline PINN, the FD residual-gradient regularizer, and a matched AD residual-gradient baseline. Stage 2 transfers the same logic to a three-dimensional annular heat-conduction benchmark (PINN3D), where baseline errors concentrate near a wavy outer wall and the auxiliary grid is implemented as a body-fitted shell adjacent to the wall. In Stage 1, the FD regularizer reproduces the main effect of residual-gradient control while exposing a trade-off between field accuracy and residual cleanliness. In Stage 2, the shell regularizer improves the application-facing quantities, namely outer-wall flux and boundary-condition behavior. Across seeds 0-5 and 100k epochs, the most reliable tested configuration is a fixed shell weight of 5e-4 under the Kourkoutas-beta optimizer regime: relative to a matched run without the shell term, it reduces the mean outer-wall BC RMSE from 1.22e-2 to 9.29e-4 and the mean wall-flux RMSE from 9.21e-3 to 9.63e-4. Adam with beta2=0.999 becomes usable when the initial learning rate is reduced to 1e-3, although its shell benefit is less robust than under Kourkoutas-beta. Overall, the results support a targeted view of hybrid PINNs: an auxiliary-only FD regularizer is most valuable when it is aligned with the physical quantity of interest, here the outer-wall flux.

AI systems are increasingly used to assist humans in sequential decision-making tasks, yet determining when and how an AI assistant should intervene remains a fundamental challenge. A potential baseline is to recommend the optimal action according to a strong model. However, such actions assume optimal follow-up actions, which human decision makers may fail to execute, potentially reducing overall performance. In this work, we propose and study value-aware interventions, motivated by a basic principle in reinforcement learning: under the Bellman equation, the optimal policy selects actions that maximize the immediate reward plus the value function. When a decision maker follows a suboptimal policy, this policy-value consistency no longer holds, creating discrepancies between the actions taken by the policy and those that maximize the immediate reward plus the value of the next state. We show that these policy-value inconsistencies naturally identify opportunities for intervention. We formalize this problem in a Markov decision process where an AI assistant may override human actions under an intervention budget. In the single-intervention regime, we show that the optimal strategy is to recommend the action that maximizes the human value function. For settings with multiple interventions, we propose a tractable approximation that prioritizes interventions based on the magnitude of the policy-value discrepancy. We evaluate these ideas in the domain of chess by learning models of humans from large-scale gameplay data. In simulation, our approach consistently outperforms interventions based on the strongest chess engine (Stockfish) in a wide range of settings. A within-subject human study with 20 players and 600 games further shows that our interventions significantly improve performance for low- and mid-skill players while matching expert-engine interventions for high-skill players.

Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-stream injections, which rely on injection-strength sweeps to approximate optimal intervention settings. However, existing methods restrict the search space and sweep in uncalibrated activation-space units, potentially missing optimal intervention conditions. Thus, we introduce a psychological steering framework that performs unbounded, fluency-constrained sweeps in semantically calibrated units. Our method derives and calibrates residual-stream injections using psychological artifacts, and we use the IPIP-NEO-120, which measures the OCEAN personality model, to compare six injection methods. We find that mean-difference (MD) injections outperform Personality Prompting (P$^2$), an established baseline for OCEAN steering, in open-ended generation in 11 of 14 LLMs, with gains of 3.6\% to 16.4\%, overturning prior reports favoring prompting and positioning representation engineering as a new frontier in open-ended psychological steering. Further, we find that a hybrid of P$^2$ and MD injections outperforms both methods in 13 of 14 LLMs, with gains over P$^2$ ranging from 5.6\% to 21.9\% and from 3.3\% to 26.7\% over MD injections. Finally, we show that MD injections align with the Linear Representation Hypothesis and provide reliable, approximately linear control knobs for psychological steering. Nevertheless, they also induce OCEAN trait covariance patterns that depart from the Big Two model, suggesting a gap between learned representations and human psychology.

For humans, filler-gap dependencies require a shared representation across different syntactic constructions. Although causal analyses suggest this may also be true for LLMs (Boguraev et al., 2025), it is still unclear if such a representation also exists for language models trained on developmentally feasible quantities of data. We applied Distributed Alignment Search (DAS, Geiger et al. (2024)) to LMs trained on varying amounts of data from the BabyLM challenge (Warstadt et al., 2023), to evaluate whether representations of filler-gap dependencies transfer between wh-questions and topicalization, which greatly vary in terms of their input frequency. Our results suggest shared, yet item-sensitive mechanisms may develop with limited training data. More importantly, LMs still require far more data than humans to learn comparable generalizations, highlighting the need for language-specific biases in models of language acquisition.

AI models underpin modern intelligent systems, driving advances across science, medicine, finance, and technology. Yet developing high-performing AI models remains a labor-intensive process that requires expert practitioners to iteratively design architectures, engineer representations, implement training pipelines and refine approaches through empirical evaluation. Existing AutoML methods partially alleviate this burden but remain limited to narrow aspects such as hyperparameter optimization and model selection within predefined search spaces, leaving the full development lifecycle largely dependent on human expertise. To address this gap, we introduce AIBuildAI, an AI agent that automatically builds AI models from a task description and training data. AIBuildAI adopts a hierarchical agent architecture in which a manager agent coordinates three specialized sub-agents: a designer for modeling strategy, a coder for implementation and debugging, and a tuner for training and performance optimization. Each sub-agent is itself a large language model (LLM) based agent capable of multi-step reasoning and tool use, enabling end-to-end automation of the AI model development process that goes beyond the scope of existing AutoML approaches. We evaluate AIBuildAI on MLE-Bench, a benchmark of realistic Kaggle-style AI development tasks spanning visual, textual, time-series and tabular modalities. AIBuildAI ranks first on MLE-Bench with a medal rate of 63.1%, outperforming all existing baseline methods and matching the capability of highly experienced AI engineers. These results demonstrate that hierarchical agent systems can automate the full AI model development process from task specification to deployable model, suggesting a pathway toward broadly accessible AI development with minimal human intervention.

Autonomous vehicles equipped with robust onboard perception, localization, and planning still face limitations in occlusion and non-line-of-sight (NLOS) scenarios, where delayed reactions can increase collision risk. We propose CooperDrive, a cooperative perception framework that augments situational awareness and enables earlier, safer driving decisions. CooperDrive offers two key advantages: (i) each vehicle retains its native perception, localization, and planning stack, and (ii) a lightweight object-level sharing and fusion strategy bridges perception and planning. Specifically, CooperDrive reuses detector Bird's-Eye View (BEV) features to estimate accurate vehicle poses without additional heavy encoders, thereby reconstructing BEV representations and feeding the planner with low latency. On the planning side, CooperDrive leverages the expanded object set to anticipate potential conflicts earlier and adjust speed and trajectory proactively, thereby transforming reactive behaviors into predictive and safer driving decisions. Real-world closed-loop tests at occlusion-heavy NLOS intersections demonstrate that CooperDrive increases reaction lead time, minimum time-to-collision (TTC), and stopping margin, while requiring only 90 kbps bandwidth and maintaining an average end-to-end latency of 89 ms.

Quick and accurate emergency handling in Disaster Decision Support Systems (DDSS) is often hampered by network latency and suboptimal application accuracy. While Federated Learning (FL) addresses some of these issues, it is constrained by high communication costs and rigid synchronization requirements across heterogeneous convolutional neural network (CNN) architectures. To overcome these challenges, this paper proposes a decentralized ensembling framework based on asynchronous probability aggregation and feedback distillation. By shifting the exchange unit from model weights to class-probability vectors, our method maintains data privacy, reduces communication requirements by orders of magnitude, and improves overall accuracy. This approach enables diverse CNN designs to collaborate asynchronously, enhancing disaster image identification performance even in resource-constrained settings. Experimental tests demonstrate that the proposed method outperforms traditional individual backbones and standard federated approaches, establishing a scalable and resource-aware solution for real-time disaster response.

Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between visual data and linguistic descriptions. This bias adversely affects performance in computer vision tasks. This paper proposes an image annotation methodology that integrates knowledge representation, natural language processing, and computer vision techniques, aiming to reduce annotator subjectivity by applying visual property constraints. We introduce an interactive crowdsourcing framework that dynamically asks questions based on a predefined object category hierarchy and annotator feedback, guiding image annotation by visual properties. Experiments demonstrate the effectiveness of this methodology, and annotator feedback is discussed to optimize the crowdsourcing setup.

Large language models (LLMs) are increasingly used as sources of information, yet their reliability depends on the ability to search the web, select relevant evidence, and synthesize complete answers. While recent benchmarks evaluate web-browsing and agentic tool use, multilingual settings, and Portuguese in particular, remain underexplored. We present \textsc{MARCA}, a bilingual (English and Portuguese) benchmark for evaluating LLMs on web-based information seeking. \textsc{MARCA} consists of 52 manually authored multi-entity questions, paired with manually validated checklist-style rubrics that explicitly measure answer completeness and correctness. We evaluate 14 models under two interaction settings: a Basic framework with direct web search and scraping, and an Orchestrator framework that enables task decomposition via delegated subagents. To capture stochasticity, each question is executed multiple times and performance is reported with run-level uncertainty. Across models, we observe large performance differences, find that orchestration often improves coverage, and identify substantial variability in how models transfer from English to Portuguese. The benchmark is available at https://github.com/maritaca-ai/MARCA

We present an empirical study of whether hierarchically structured, shared-weight recurrence can match the representational quality of independent-layer stacking in a Transformer-based language model. HRM-LM replaces L independent Transformer layers with a two-speed recurrent pair: a Fast module operating at every step for local refinement, and a Slow module operating every T steps for global compression. This recurrent hierarchy is unrolled for M = N x T steps with shared parameters. The central and most robust finding, supported by a parameter-matched Universal Transformer ablation (UniTF, 1.2B) across five independent runs, is a sharp empirical gap between the two approaches.

We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks. The approach extends the concept of Reward Machines (RM) with Signal Temporal Logic (STL) formulas that can be used for event generation. The use of STL allows not only a more efficient representation of rewards for complex tasks but also guiding the training process to converge towards behaviors satisfying specified requirements. We also propose an implementation of the framework that leverages the STL online monitoring algorithms. We illustrate the framework with three case studies (minigrid, cart-pole and high-way environments) with non-trivial tasks.