Weekly Recap

Edge service orchestration can achieve up to 64.5% lower decision latency than LLMs by using Jev decision models, even at high loads where LLMs fail.

The results showed that higher runx2 b promoter methylation patterns significantly inhibited eGFP mRNA expression levels in the recombinant plasmid, and this approach provides a theoretical foundation and technical support for improving fish economic traits.

A hierarchical control architecture for human–SL augmentation that draws on predictive coding to couple intent inference, safety, action planning, and interaction and provides design principles for safe, versatile, and intuitive SL control in industrial, assistive, and surgical settings is proposed.

A query optimization framework that integrates a Graph Transformer with the model-based reinforcement learning (RL) algorithm MuZero, which converts SQL queries into heterogeneous graphs containing tables, predicates, and join operators and demonstrates its practical effectiveness and scientific value for building high-performance, adaptive intelligent database systems.

A hierarchical control architecture for human–SL augmentation that draws on predictive coding to couple intent inference, safety, action planning, and interaction and provides design principles for safe, versatile, and intuitive SL control in industrial, assistive, and surgical settings is proposed.

A query optimization framework that integrates a Graph Transformer with the model-based reinforcement learning (RL) algorithm MuZero, which converts SQL queries into heterogeneous graphs containing tables, predicates, and join operators and demonstrates its practical effectiveness and scientific value for building high-performance, adaptive intelligent database systems.

This paper presents UltraTex, an efficient end-to-end framework for high-resolution multi-view diffusion-based 3D texturing and introduces Background Token Dropping, which removes background tokens before the DiT backbone, and Block-Sparse Attention, which reduces attention computation over the retained foreground sequence.

It is highlighted that Anxiety and Depression and Social Dysfunction are more directly linked to academic outcomes than Loss of Confidence.

RoboDawn is investigated, a human-intuitive interface that exposes robotic control to an agentic VLM through a compact set of discrete translation, rotation, and gripper commands, and an in-context learning (ICL) scheme is introduced that ground the VLM in both interface usage and task-solving strategies.

The value of curated, capability-balanced supervision for adapting general language models to educational tasks spanning problem solving, curriculum understanding, and instructional support is demonstrated.

Edge service orchestration can achieve up to 64.5% lower decision latency than LLMs by using Jev decision models, even at high loads where LLMs fail.

Probe of Internal Recognition (PIR) separates a model that will not answer from one that cannot, which supports sandbagging audits and unlearning verification, and extends from multiple-choice questions to free-form generation.

It is suggested that AI can play a pivotal role in facilitating interdisciplinary teaching by enabling personalized learning, supporting teacher development, and promoting an inclusive, technology-driven educational environment.

The integration of AI into clinical practice is a key element in the evolution of "precision nephrology," supporting the detection of subtle disease patterns and the standardization of management.

The results showed that higher runx2 b promoter methylation patterns significantly inhibited eGFP mRNA expression levels in the recombinant plasmid, and this approach provides a theoretical foundation and technical support for improving fish economic traits.

The results show that combining spatial graph modeling with temporal deep learning provides a robust computational approach for manufacturing industrial land change prediction and supports data-driven industrial land planning decisions.

The analysis suggests that technologies such as NLP and large language models may both reproduce and challenge existing linguistic hierarchies, raising important questions about representation, diversity, and equity in digital environments.

In tumor cells with heterogeneous CAR antigen expression, CAR T cell recognition of antigen-positive cells induced HLA-A*02 upregulation across the tumor population, enabling subsequent NY-ESO-1 TCR T cell recognition of cells not directly recognized by CAR T cells.

MILER, an end-to-end policy framework with zero-shot sim-to-real transfer of both perception and control, is presented and extensively evaluated on a diverse test track comprising numerous challenges.

This standard approach to process mining, built on the stochastic language of an event log, reports only the assumptions of its discovery algorithm, because every such log is explained equally well by a model with no concurrency at all.

Diagnostics limit explanations based solely on terminal optimization accuracy and distinguish numerical cost from quality, rank coverage and freshness; they establish neither practical-tracker convergence nor predictive or deployment benefits from basis availability.

Comprehensive experiments demonstrate CellRFT's applicability across different pretrained models and effectiveness in improving perturbation prediction, reveal that optimizing one biological criterion can help or hinder others, and show that complementary rewards can improve criteria beyond those directly optimized.

This study establishes an exploratory screening workflow for hypothesis generation and prioritization based on observational associations and introduces a Task-Adaptive Representation Approach to alleviate the over-encoding of historical prescription information within diagnostic vectors, enabling the robust prioritization of generated hypotheses.

TriDim, a reusable block that preserves the representation shape and keeps three EEG axes explicit: channel, sample position within each patch, and patch position across the recording, is proposed, a reusable block that preserves the representation shape and keeps three EEG axes explicit.

This method introduces Instance-level Difficulty-Aware Control (IDAC), a reward-shaping mechanism that leverages pre-computed reference statistics (accuracy and token usage) to regulate reasoning depth and enables stable critic-free optimization without learned reward models or online reference-model queries.

The IRJS model enables robust spatiotemporal assessment of immune evasion, offering multidisciplinary teams a potential framework to explore non-invasive biopsy decisions, prognostic stratification, and provide exploratory insights into potential immunotherapy resistance.

WeVisDoc is presented, a two-stage data-centric framework for robust end-to-end document parsing that broadens semantic, structural, and appearance coverage through heterogeneous data and structure-preserving degradation synthesis and guides targeted data construction and reallocation of the target-token budget.

BA-TRACE is presented, a boundary-aware trace reconstruction framework for scenario-based evaluation of mixed AUTOSAR AP and ROS 2 vehicular embedded systems that reconstructs the expected cross-platform path and exposes boundary-specific latency such as point-cloud transfer overhead.

This work implements two representative architectures --- the Simplified Graph Convolution (SGC) and Linear Graph Convolution (LGC) models and evaluates them on open benchmark graph datasets and semi-supervised learning tasks using quantum simulation and presents a cost gradient analysis that identifies the tasks for which the models are trainable.

ALIBI is presented, a semantic cover story attack against frontier LLM-based malware analyzers that adds a small, non-executed read-only section to a compiled binary, containing a coherent but false security product narrative, without altering imports or executable behavior.

This study introduces TrustReviewer, an open-source LLM-based system for generating peer reviews of AI and machine learning papers and describes a concrete risk of recursive reviewer training and provides practical interventions for preserving judgment diversity and improving recommendation alignment in AI-assisted scientific evaluation.

This work introduces ActObs, which also supervises the observation tokens already present in each trajectory, and traces this difference to SFT: action and observation gradients rapidly become orthogonal, while action-only training leaves a large residual observation gradient and degrades environment prediction below the base model.

This work introduces a novel surface-based diffusion bridge framework DB-SUiT for MRI-to-PET translation that operates natively on the cortical manifold and demonstrates high-fidelity synthesis that substantially outperforms other baselines.

Qualitative analysis shows that S4L captures implicit causal relations, deontic modality, and exception structure more reliably than the baselines, demonstrating that structured reasoning prompts can substantially improve the reliability of natural-language-to-logic translation for legal and safety-critical applications.

The refined proposal enables a sparse encoding that magnifies evidence and excludes background tokens, and is called Vision-RL2, which improves accuracy over the base model at every token budget and surpasses its largest-budget accuracy with about 4 times fewer visual tokens.

This work proposes a pure single-loop damped extragradient method with fixed parameters and two new full-gradient evaluations per iteration after one initialization query that attains the optimal condition-number order up to logarithmic factors through fixed explicit updates.

This work proposes OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes) which provides supervision to the pre-trained student during closed-loop post-training.

A recursive learning algorithm is proposed that orders SCCs topologically and, for each component, isolates its marginal dynamics and solves a linear system derived from the steady-state moment equations, leveraging parameters recovered for upstream components.

Empirically, EPIG reduces gradient MSE in cloned-state control, winning in all nine dense continuous-control environments of a 13-environment sweep and recovering the reference gradient direction near-perfectly, and it improves frozen-LLM gradient calibration relative to entropy branching.

REARL, a closed-loop simulation enhancement framework that integrates real traffic data with large language model (LLM) and modulates the simulated vehicle with reference to that real action, is proposed.

An architecture extending unanticipated-fault recovery from detection to mitigation and an ensemble methodology for evaluating LLM-assisted mission management on low-power AUVs are made.

A 202-scenario benchmark with Reference Decisions under a seven-class taxonomy is introduced and Decision Alignment and safety-specific error metrics are evaluated, finding structured LLM decisions are insufficient as a standalone safety mechanism and deployment requires an independent enforcement layer.

This paper identifies a gap in both speech initiation and response content that requires genuine content understanding and intervention decisions grounded in it and constructs context-matched English monologues in which only the trigger utterance varies within a topic.

This work formalises a unified view of block redundancy that decouples the geometry from specific surrogate interventions and introduces Transformer-Within-Transformer (TWT), a post-hoc method that fuses contiguous groups of redundant layers into a single learned surrogate layer.

This paper presents PART, a unified transformer-based framework for 3D part retrieval and assembly: given a target shape and a part library, PART automatically selects the appropriate parts and predicts their 6-DoF poses to reconstruct the target.

Imagine-TAMP is introduced, an interleaved planning and execution framework that uses semantic and geometric imagination to compare alternative task-level strategies under partial observability before committing to expensive motion planning and experiments show that imagination-guided evaluation improves observation-versus-manipulation decisions.

AdvScene, a conditional latent diffusion model that is trained in two stages that Conditioning on ego driving displacement prevents the ego from remaining static, and RL finetuning induces criticality directly with non-differentiable safety-critical metrics is proposed.

VAST is presented, a V2X/Dynamic Map-aware validation toolchain that connects Scenic, Scenario Simulator v2, AWSIM, Autoware, and SIM-LDM and addresses interoperability challenges, including Lanelet2-to-Scenic mapping, ROS 2-based co-simulation through SS2, Dynamic Map object injection into Autoware, and collection of TTC, PET, collision, timeout, and performance measurements.

Comparisons support complementary benefits of feature-wise gated tactile fusion and training-only predictive supervision of TacSushi, a tactile-grounded, Cosmos3-based world-action policy that learns from recorded future consequences while acting on current observations.

This work introduces LIFD (Look, Imagine, Focus, and Do), a framework for persistent, 3D-aware scene memory that learns a scene-token representation from multi-view agreement and completes it from a single RGB view and recurrent memory.

A new SF-GVF with prescribed physical speed (PPS) that converge exponentially to the desired path from any initial condition in the higher-dimensional space (including virtual dimension); more importantly, the robot's physical speed converges to the PPS, while the path-error dynamics remain invariant under regular reparameterizations of the desired path.

This work puts the opportunities the compute continuum offers to the test through a real-world multi-view detection model (MvDet) implemented with the FastFL C/C++ high-performance edge inference framework, and obtains up to 1.92x speedup in inference time over a centralised solution using the same devices.

Initial evidence is provided that greCAPTCHA can assess manuscript-specific understanding under proctored conditions and the appropriate construct validity for author understanding is remarked on, while also suggesting important changes to be made before deployment.

This work finds that the wording of the question affects VLMs in two opposite ways: verbose paraphrasing reduces drift variance by 70--81% on the 8B models and the practical recipe---pad the prompt---further yields measurable gains in accuracy, even under image corruption.

MERIT-Rank is proposed, a framework that models complementary reasoning trajectories to improve reranking robustness and develops Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes reasoning trajectories while continually improving ranking quality through staged optimization objectives.

This work proposes Set of Centre Active Receptive Fields (SCARF), a real-time velocity-invariant representation that preserves raw events while consistently handling fast motion, stationary scenes, and independently moving objects and achieves state-of-the-art performance in both computational efficiency and representation quality.

FAMOS, a feed-forward model that predicts movable-part segmentation and joint parameters from a sparse, unordered set of partial point clouds, is presented and a procedural data generator that synthesizes self-annotated assets during training is introduced to overcome the limited scale and diversity of existing datasets.

AMPLE-Math, a reusable suite of 5,319 mathematical problems with six reasoning views that share the same answer, is constructed and AMPLE-Math, a reusable suite of 5,319 mathematical problems with six reasoning views that share the same answer, is compared, suggesting that OPSD can improve access to existing reasoning capabilities through parameters shared by direct-response and thinking-enabled inference.

This work instantiates VDN on MiniMax H3, which combines local Softmax attention with bidirectional linear memory for long-range video context and introduces Video Delta Attention (VDA), which updates memory once per frame by jointly incorporating its spatial tokens.

VA-Bench is introduced to evaluate the complete observe-reason-act-revise loop and tests whether general-purpose MLLMs can turn visual demonstrations and actively acquired evidence into successful embodied action.

This work takes an RSI-inspired approach at the harness layer, scaling auto-research loops across increasingly numerous and diverse environments for harness rollouts, and yields reusable improvements that transfer beyond their development setting.

This work studies a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management, and finds that context management becomes increasingly valuable as the context-window budget tightens.

CURB (Collusion Unwinding via Reward shaping and Belief injection), a reward-shaping framework that penalizes this Total Variation (TV) distance signal during Q-learning and is guaranteed to convert any SPC fixed point of the dynamics into a trivial one, thus precluding collusive equilibria sustained by punishment threats.

Relational BabyLM is a system submission to the BabyLM 2026 challenge that combines two cognitively motivated inductive biases in a single decoder-only Transformer, and introduces a novel symbol-retrieval mechanism that matches learned symbol libraries while adding no parameters.

Using realistic communication models reversed simulated traffic speed trends and more than doubled predicted hard-braking events, so researchers and transportation agencies can maintain existing simulation pipelines while accurately accounting for dense-traffic packet loss and denial-of-service impacts.

Sampling-Guided Policy Search (SGPS), which couples recurring action-target refinement by sampling-based model-predictive control with first-order policy optimization with first-order policy optimization, and shows that refinement improves policy learning beyond initialization and tracking alone.

It is shown that the instability of RL under TIM is primarily caused by drift: a persistent bias between training and inference engines that accumulates with every training step, and an additive score centering term is derived that stabilizes RL under TIM by canceling drift.

TetrisCNN is introduced, a convolutional architecture with parallel branches of differently shaped filters, reminiscent of Tetris blocks, that learns sparse, interpretable latent representations directly in terms of spin correlators, and opens the way to integrating interpretable neural networks with quantum simulators to uncover and understand new phases of matter.

The propensity of frontier agents to overclaim, a misrepresentation that can mislead the user, is quantified and results show that agents'final responses are not reliable accounts of their actions.

This paper introduces multi-horizon multimodal prediction in ABBR, an agile tactile World Action Model for contact-rich robot control, which provides supervision for visual latent at a larger temporal offset while predicting the tactile latent in the next frame to capture fine-grained contact dynamics.

The results support the conclusion: foundation-model supervision can amplify a fixed manual annotation budget into a substantially larger training set and yield a compact, deployable edge model.

A physics-enhanced machine learning approach for the system identification of Linear Time-Varying systems under time-varying operating conditions in terms of fast-varying natural frequencies and damping ratios by combining a long short-term memory network with an Extended Kalman Filter is proposed.

This paper proposes a conceptual Agentic AI architecture for AI systems that can plan, access data sources, execute tools, and act autonomously and audibly, aimed at supporting decision-making across the three Brazilian Armed Forces.

This work proposes an observer-based dynamic cooperative learning framework incorporating online distributed Gaussian Process (GP) regression, which enables accurate estimation despite incomplete in measurements and deficient GP models, and derives an error upper bound encompassing state estimation and model estimation.