Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments is challenging because memory turns the agent's past actions into part of its future environment. Once different rollouts write, update, or delete different memories, they no longer share the same intermediate memory state, making trajectory-level comparisons fundamentally unfair. This violates a key assumption behind group-relative methods such as GRPO, where rollouts are compared as if they were sampled from the same effective environment. Consequently, trajectory-level rewards provide noisy or biased credit signals for long-horizon memory operations. To address this challenge, we introduce Memory-R2, a training framework for long-horizon memory-augmented LLM agents. Its core algorithm, LoGo-GRPO, combines local and global group-relative optimization. The global objective preserves end-to-end learning from long-horizon trajectory-level rewards, while local rerollouts compare different memory-operation outcomes from the same intermediate memory state, yielding fairer group comparisons and more precise supervision for memory construction. Beyond credit assignment, Memory-R2 jointly optimizes memory formation and memory evolution with a shared-parameter co-learning design, where a fact extractor and a memory manager are instantiated from the same LLM backbone through role-specific prompts. To stabilize multi-step RL over long memory horizons, we adopt a progressive curriculum that increases the training horizon from 8 to 16 to 32 sessions. Together, these components provide an effective training paradigm for memory-augmented LLM agents in long-horizon multi-session settings.

Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. Our model is trained on a hybrid dataset of pixel-aligned video relighting pairs, covering a diverse combination of lighting conditions, performances and viewpoints. To acquire such dataset, we combine traditional static One-Light-at-a-Time (OLAT) capture and a novel dynamic performance capture in which two smoothly varying lighting sequences are rapidly interleaved. Because the lighting operates above the human flicker-fusion threshold, the interleaving does not appear to strobe. We train our video relighting model from a pretrained text-to-video model to fully leverage the generative priors for producing high quality videos. To achieve accurate lighting control, we introduce a new lighting conditioning method that represents each light source as a token. We further condition on sequences of lighting using masked attention to support dynamic lighting control. Together with a carefully designed data augmentation pipeline, we achieve photorealistic, robust, and temporally consistent video relighting of subject-specific human performances.

The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that SAI has achieved computational parity with optimization-based methods and is at the verge of superseding such methods for effective and efficient inference in BNNs. This development should be in the interest of the whole community, promoting BNNs as a principled paradigm with its long-standing yet unfulfilled promise of providing principled uncertainty quantification for neural networks. SAI can even do more -- yielding superior prediction performance through model averaging, serving as the foundation for a plethora of possible downstream tasks, and providing crucial insights into the landscape of BNNs. In order to make such a change happen and unfold the potential of sampling, overcoming current misconceptions is a necessary first step. The next step is to realign research efforts toward addressing remaining challenges in SAI. In particular, the community must focus on two core problems: sufficient exploration of the posterior landscape and high-fidelity distillation of posterior samples for efficient downstream inference. By addressing conceptual and practical obstacles, we can unlock the full potential of SAI and establish it as a central tool in Bayesian deep learning.

We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a family or risk measures called the optimized certainty equivalent (OCE), which includes important risk measures such as entropic risk, CVaR, and mean-variance. Our focus is on the sample complexities of learning the optimal state-action value function (value learning) and an optimal policy (policy learning) under recursive OCE. We provide an exact characterization of utility functions $u$ for which the corresponding OCE defines an objective that is PAC-learnable. We analyze a simple model-based approach and derive PAC sample complexity bounds. We establish that whenever $u$ does not have full domain $\text{dom}(u)\neq \mathbb{R}$, the corresponding problem is not PAC-learnable. Finally, we establish corresponding lower bounds for both value and policy learning, demonstrating tightness in the size $SA$ of state-action space, and for a more restricted class of utilities, we derive lower bounds that makes the dependence on the effective horizon $\frac{1}{1-γ}$ explicit. Specifically, for $\text{CVaR}_τ$ we show that the correct dependence on $τ$ is $\frac{1}{τ^2}$, thus improving by a factor of $\frac{1}τ$ over state-of-the-art although our bound has a suboptimal dependence on $\frac{1}{1-γ}$.

Non-contrast computed tomography calcium scoring (CTCS) is a cost-effective imaging modality widely used to detect coronary artery calcifications. This study aimed to develop an advanced machine learning framework that utilizes quantitative analyses of coronary calcium and epicardial fat from CTCS images to predict obstructive coronary artery disease (CAD). The study population consisted of 1,324 patients from the SCOT-HEART clinical trial who underwent both CTCS and coronary CT angiography. We extracted and analyzed a broad range of features, including 24 clinical variables, 189 calcium-omics, and 211 epicardial fat-omics features from the CTCS images. Feature selection was conducted using the CatBoost algorithm combined with SHapley Additive exPlanation (SHAP) values. Predictive modeling utilized the CatBoost gradient boosting method, focusing on the most informative features. From an initial set of 424 candidate features, 14 were identified as most predictive through the CatBoost-SHAP method. The top two predictive features originated from fat-omics, with the remaining 12 features derived from calcium-omics. The optimized model achieved robust predictive capabilities, demonstrating a sensitivity of 83.1+/-4.6%, specificity of 93.8+/-1.7%, accuracy of 85.3+/-2.0%, and an F1 score of 73.9+/-3.3%. Inclusion of calcium-omics and fat-omics data significantly improved predictive performance. Notably, the model also showed reliable predictive accuracy in patients with diverse coronary calcium scores, including cases with obstructive CAD despite a zero-calcium score. This innovative approach holds promise for improving clinical decision-making and potentially reducing dependence on contrast-enhanced or invasive diagnostic procedures, particularly within low-to intermediate-risk patient groups.

Explainable AI (XAI) methods identify which features are relevant to a model's predictions but often fail to clarify why certain decisions are made. In this work, we present a novel method that integrates causality with argument-based reasoning to explain why models may be making predictions. Our approach first identifies causal relationships among variables using causal discovery methods and then translates these into a Bipolar Argumentation Framework (BAF) to represent supportive and opposing interactions among features. By using semi-stable semantics, we find extensions of features that explain why certain outcomes may have been chosen. We demonstrate our method on two benchmark datasets and compare its results against standard post-hoc explainability approaches.

Recommender systems trained on user interaction data are susceptible to behavioral intensity imbalance--a systematic distortion arising from heterogeneous engagement patterns across users. This imbalance skews feedback signals such that observed interactions no longer faithfully reflect true preferences, causing models to disproportionately amplify signals from highly active users while underrepresenting others, which ultimately degrades recommendation quality and robustness at scale. To address this issue, we propose a nonparametric contrastive percentile approximation framework, PEARL, that models relative preference signals instead of absolute engagement magnitudes. Building upon relative advantage debiasing, PEARL leverages real contrastive interaction samples to approximate percentile relationships directly, without relying on auxiliary distribution estimation models. We provide theoretical justification demonstrating that such pairwise comparisons yield unbiased estimates of percentile-based preference signals. For broader applicability, we introduce a prediction-based bootstrapping mechanism for percentile smoothing to handle sparse and discrete feedback, alongside a generalized value-weighted formulation and a co-training strategy to enhance both modeling flexibility and representation learning. Extensive offline experiments demonstrate that PEARL effectively mitigates behavioral bias and consistently improves recommendation performance across multiple ranking targets. Deployed in a production livestream platform with a combined user base of billions, online A/B testing confirms substantial real-world gains: +2.10% Watch Duration, +0.80% Consumption Amount, +1.49% Interaction Rate, and -6.91% Report Rate.

Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter in the concrete problem data. We study this via Text2Opt-Bench, a scalable benchmark of solver-verified optimization problems spanning 12 categories, from textbook linear programs to stochastic and multi-objective formulations with up to thousands of variables. Across 10+ models, we find that accuracy collapses as instance data grows, even when the formulation itself is simple. We call this the effective binding limit. We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data programmatically rather than transcribing from the prompt. BIND improves GPT-5-Nano from 59.1% to 82.4% accuracy, matching pass@5 (82.0%) at lower token cost than pass@1, and GPT-5 from 86.2% to 95.8%. Furthermore, we validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories, with a 1.5B binding specialist alone matching a 7B end-to-end baseline.

As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes. For simpler systems, human evaluation may be practical, but in complicated systems like conversational chatbots, the amount of generated text can overwhelm human annotation resources. Model developers have begun to rely heavily on auto-evaluation, where LLMs are also used to judge generation quality. However, existing LLM-as-a-judge benchmarks largely focus on simple Q\&A tasks that do not match the complexity of multi-turn conversations. We introduce RankJudge, a benchmark generator for evaluating LLM-as-a-judge on multi-turn conversations grounded in reference documents. RankJudge creates pairs of conversations where one conversation has a single flaw injected into one turn. This construction allows paired conversations to be labeled unambiguously as better or worse, and precisely isolates failure categories to individual turns, enabling a strict joint correctness criterion for judging. We implement RankJudge across the domains of machine learning, biomedicine, and finance, evaluate 21 frontier LLM judges, and rank those judges via the Bradley-Terry model. Our formulation also allows ranking each conversation pair with difficulty ratings, which we use to dynamically curate the evaluation slice to reduce label noise, as confirmed via human annotation. We find that judge rankings are stable under partial observability, coarser correctness criteria, and an alternative random-walk rating algorithm.

We present an approach to improve 3D vehicle labeling in self-driving applications through zero-shot inference of vehicle information, leveraging Vehicle Make and Model Recognition (VMMR) methods. The proposed approach utilizes a Vision Language Model (VLM) to both infer a vehicle's make, model, and generation from image crops, and output accurate 3D bounding box dimensions to seed manual labeling. We evaluate the impact of iterative prompt engineering and the choice of different VLMs on both vehicle bounding box inference and make/model/generation recognition. When compared to strong baselines, the proposed approach not only shows high accuracy, but also excels in mitigating specific failure modes where VLMs provide better dimensions than initial lidar-aided human annotated labels (e.g., in cases of significant vehicle occlusion). Experiments on both public and proprietary data strongly suggest that our conclusions are generalizable across different labelers and datasets. The results demonstrate that integrating VLMs into the labeling process can reduce manual labeling time while increasing label quality.

Non-contrast computed tomography calcium scoring (CTCS) is widely recognized as an effective tool for cardiovascular risk stratification. This study aimed to develop a novel machine learning framework for predicting myocardial ischemia from routine non-contrast CTCS scans using quantitative coronary calcium assessment. This study analyzed 1,375 patients who underwent both non-contrast CTCS and regadenoson stress cardiac positron emission tomography myocardial perfusion imaging within one year at University Hospitals Cleveland Medical Center. A total of 74 variables, including clinical variables, Agatston score, and calcium-omics features, were evaluated. Relevant features were identified using XGBoost with Shapley Additive exPlanations (SHAP). Predictive models were trained and evaluated using 5-fold cross-validation. Among 987 patients, 89 (9%) were positive for myocardial ischemia. The final model incorporated the Agatston score, eight calcium-omics features, and age. The proposed model achieved a precision of 98.9+/-3.0%, sensitivity of 79.2+/-8.4, and F1 score of 87.7+/-5.3%. The addition of calcium-omics features significantly improved predictive performance compared with models using clinical variables alone or clinical variables with the Agatston score (p<0.05). Interestingly, the number of calcified arteries, despite being the lowest-ranked feature based on SHAP analysis, showed the strongest association with myocardial ischemia in logistic regression analysis (odds ratio: 3.63, 95% confidence interval: 2.80-4.77, p<0.00001). We developed a machine learning approach for predicting myocardial ischemia using routinely acquired non-contrast CTCS scans. Calcium-omics features provided incremental predictive value beyond conventional risk factors and Agatston scoring and may support more accessible cardiovascular risk stratification.

Prior-data fitted networks (PFNs) have achieved exceptional performance on tabular classification tasks. However, like other classifiers, their performance can suffer under the effect of class imbalance, resulting in poor performance for rare classes. Several techniques exist which attempt to mitigate the deleterious effect of class imbalance on classification performance, but the in-context learning (ICL) dynamic of PFNs means that loss-based strategies are impossible, and other techniques are unproven. We have adapted several classical techniques addressing class imbalance and analyzed their performance on PFN classification. We observe that thresholding performs exceptionally well because of the calibration characteristics of PFNs, and downsampling performs comparably because of PFNs exceptional limited-data performance, with the additional benefit of reduced computation cost for inference.

Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve extensive computational costs associated with the use of Large Language Models (LLMs) as judges, or instead suffer from the limitations of standard CLIP-based encoders, such as strict token limits, lack of fine-grained sensitivity, or lack of compositional generalization by treating captions as ``bags-of-words.'' We propose a new learned metric that tackles the aforementioned challenges, based on a lightweight cross-encoder that is initialized from a visual question-answering model checkpoint, balancing a strong weight initialization with computational efficiency. Our training scheme uses a carefully assembled data mixture for supervised learning, featuring adversarial LLM-based data augmentations to enhance model sensitivity to fine-grained visual-linguistic errors. We also introduce a new benchmark designed to assess detailed captioning evaluation across diverse scenarios. Experimental results demonstrate that the proposed metric achieves state-of-the-art performance while maintaining the efficiency required for large-scale benchmarking, quality-aware decoding, or reward guidance.

The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These probabilities encode the distributional structure that the model learns in training and exploits in inference. In this work, we use these probabilities to situate LLMs within the mathematical theory of stochastic processes. We use this framework to design a model-agnostic probabilistic token attribution measure, using Bayes rule to invert the next-token log-probabilities so as to capture the models internal representation of the distribution over token sequences. The representation is independent of the models computational structure. This representation yields the conditional probability of the response given the prompt, and of the response given the prompt with a token marginalized away. Our attribution score is the log of the ratio of these probabilities. We further compute the entropies of a single prompts token distributions, conditioned on the remaining context. The interplay between entropy and attribution score sheds light on LLM behavior. We evaluate 8 models across 7 prompts and investigate anomalies, token sensitivity, response stability, model stability, and training convergence, thereby improving interpretability and guiding users to focus on uncertain or unstable parts of the generation.

Hyper-Connections (HC) improve residual networks by introducing learnable mixing across multiple residual streams, but unconstrained mixing leads to training instability. Manifold-Constrained Hyper-Connections (mHC) address this by enforcing approximate double stochasticity via Sinkhorn normalization, while mHC-lite ensures exact constraints through convex combinations of permutation matrices at the cost of factorial complexity. KromHC reduces this cost using Kronecker-product parameterizations, but restricts the mixing matrices to a structured submanifold of the Birkhoff polytope . We propose Transportation Birkhoff Polytope (TBP) parameterizations and their Recursive variants (RTBP), which construct exactly doubly stochastic mixing matrices with $(n-1)^2$ degrees of freedom. Our approach avoids iterative normalization and combinatorial explosion while preserving full expressivity of the Birkhoff polytope. Empirical results on language model pre-training' demonstrate competitive performance with improved stability and scalability.

This paper studies heterogeneous multi-team collaboration through dynamic robot allocation, where robots are treated as transferable resources. Leveraging Hamilton's rule from ecology as an altruistic decision-making mechanism, we propose a multi-team collaborative resource allocation framework with heterogeneous capabilities, transfer costs, and capability-dependent contributions. The resulting allocation problem is combinatorial and is shown to be NP-hard. To address scalability, we develop a graph neural network policy under centralized training and decentralized execution that approximates the altruistic allocations based on Hamilton's rule. The model operates over the team interaction graph and predicts robot-level transfer decisions and next robot-to-team assignments. The proposed approach is validated in a firefighting scenario through simulations and experiments, demonstrating that the learned policy achieves near-optimal performance while scaling to larger systems.

In this work, we address the problem of multi-robot adaptive coverage, where teams of robots perform dynamic sampling by continuously adjusting their positions to collect data in an environment. This task can be challenging, particularly when robots must be efficiently allocated to new sampling locations over time. Ergodic search methods optimize robot trajectories by ensuring that the robots' time-averaged spatial distribution aligns with the spatial distribution of environmental information. While these methods promote effective exploration provided a target distribution, they often fail to account for unknown prior distributions of the environment. To overcome this limitation, we propose an adaptive coverage strategy that utilizes real-time feedback from an environmental model to adjust robot sampling behavior in response to unknown conditions. Our approach enhances traditional ergodic trajectory optimization by constructing a target spatial information distribution based on parametric models of the environment, which are updated online. This strategy assumes that the environment is either static or changes slowly compared to the robot's motion. Our framework allows robots to dynamically prioritize regions of high interest, improving coverage efficiency, synthesizing effective control policies for individual agents, and optimizing resource use in settings with unknown prior distributions. We validate our approach through simulations, demonstrating its effectiveness in enhancing coverage and resource allocation.

We present AVI-HT, an adaptive visual-IMU fusion approach for tracking 3D hand poses by jointly modeling the egocentric image with on-glove 6-DoF IMU signals. AVI-HT achieves significantly improved accuracy and availability, particularly in hand-object interaction (HOI) scenarios involving heavy visual occlusion. Two complementary ingredients underpin its success: (1) synchronized multi-modal training data pairing on-body vision-IMU sensor streams with ground-truth 3D hand poses from a motion-capture system, and (2) a cross-sensor deep attention mechanism that adaptively modulates the trust assigned to the vision and individual IMU sensors. To evaluate AVI-HT in real-world settings, we conduct extensive experiments on our DexGloveHOI dataset that consists of 100K+ pairwise vision-IMU samples with synchronized 3D annotated poses, in which users manipulate a variety of objects during daily tasks. We compare against multiple single- and multi-modal tracking approaches under two hand models (UmeTrack, MANO). The results show that AVI-HT reduces mean keypoint error by 16.1% and its wrist-aligned variant by 24.2% over the baselines. Ablation studies further reveal the per-finger contribution of IMU sensors across activity types, and the model's sensitivity to IMU noise and temporal misalignment in vision-IMU fusion.

How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not be attributed solely from the textual features of a review, but also from the ideas, judgments, and claims it expresses. To this end, we propose Sem-Detect, an authorship detection method for peer reviews that operationalizes this principle by combining textual features with claim-level semantic analysis. Sem-Detect compares a target review against multiple AI-generated reviews of the same paper, leveraging the observation that different AI models tend to converge on similar points, while human reviewers introduce more unique and diverse ones. As a result, Sem-Detect is able to distinguish fully AI reviews from authentic human-written ones, including those that have been refined using an LLM but still reflect human judgment. Across a dataset of over 20,000 peer reviews from ICLR and NeurIPS conferences, Sem-Detect improves over the strongest baseline by 25.5% in TPR@0.1% FPR in the binary setting. Moreover, in the three-class scenario, we empirically show that LLM refinement preserves the semantic signals of human reviews, which remain distinct from the patterns exhibited by fully AI-generated text; as a result, fewer than 3.5% of LLM-refined human reviews are misclassified as AI-generated.

Transportation safety analysis requires integrating crash records, roadway attributes, and geospatial data through GIS-based workflows, but access remains uneven across agencies and community stakeholders. Technical prerequisites create a gap between analytical tools central to safety planning and the practitioners able to use them. Local agencies, school committees, and residents may have safety concerns but limited capacity to retrieve, filter, map, and analyze relevant data. Generative AI offers a way to narrow this divide, but its public-sector use raises questions about reliability, reproducibility, and governance. This paper presents a schema-grounded natural language interface for transportation safety analysis, using a large language model (LLM) to interpret user intent while preserving deterministic, reviewable execution against an authoritative database. User queries are translated into structured semantic frames, validated by a rule-based layer, compiled into a typed directed acyclic graph of spatial operations, and executed against a PostGIS database. This bounded design separates language interpretation from deterministic execution, keeping results reproducible and schema-grounded while removing access barriers. The framework is evaluated using a statewide Massachusetts transportation safety database integrating crash records, roadway attributes, and geospatial layers including schools, bus stops, crosswalks, and municipal boundaries. All queries executed successfully; the validation layer corrects errors in 29% of evaluation queries, reflecting the gap between flexible natural language and strict schema-grounded requirements. The results suggest that combining natural language accessibility with deterministic execution is a practical direction for broadening access to transportation safety data, with implications for trustworthy AI in public-sector planning.

Behavior cloning for contact-rich bimanual manipulation remains challenging because diverse demonstrations are expensive to collect, and even small disturbances can push the system into off-manifold states where no recovery supervision is available. We propose PGDG, a data generation framework with zero-shot curation that expands a single demonstration into a compact dataset of physically plausible, successful, and diverse recovery behaviors without additional human labeling. PGDG iterates between a physics-grounded sampler and a dataset curator, where the curator selects informative, non-redundant, and recoverable behaviors to update the sampling distribution toward under-covered recovery modes, and the sampler draws physically plausible rollout candidates from this updated distribution and retains successful trajectories. To further improve data quality, PGDG applies short-horizon sampling-based control to relabel selected risky states with corrective actions. Across four bimanual manipulation tasks, PGDG consistently outperforms spatial-only augmentation in both simulation and zero-shot real-world transfer. On RotateBox-Pitch, success improves from 38% to 93% in simulation and from 35% to 82% in the real world. PGDG also enables effective foundation models fine-tuning such as GR00T, increasing success from 46% to 77%. Additional results are available in our website: https://cunxid.github.io/PGDG/.

Locomotion in microgravity often relies on sparsely and irregularly arranged anchors, motivating grasp-based mobility with multiple limbs. In this setting, dynamic locomotion is feasible only through deliberate regulation of both anchored interactions and whole-body coordination under coupled dynamic and kinematic constraints. This paper presents design insights for grasp-based dynamic locomotion with multi-limbed robotic systems in microgravity, targeting scenarios that require 6D limb manipulation to establish contacts with candidate anchors. The investigated design parameters include gait pattern, stride length, locomotion speed, and nominal posture. A parameterizable locomotion planning framework is proposed to support variations of these parameters and to evaluate the resulting locomotion performance in terms of stability and actuation demand. Two representative quadruped morphologies are adopted for evaluation in physics-based simulation. The results demonstrate that enlarging the feasible contact wrench space and attenuating impulsive whole-body dynamics improve locomotion performance. These findings inform strategies for contact configuration selection and whole-body coordination in microgravity locomotion with multi-limbed systems.

Cross-tokenizer knowledge distillation allows a student model to learn from teachers with incompatible vocabularies. Prior work operates on hidden states or logits; the latter is preferred as a drop-in replacement requiring no auxiliary components. Logit-based methods either use only the correct-token probability, missing the full 'dark knowledge' in the teacher's distribution, or operate on the full output distribution, relying on strict token partitioning and/or unprincipled heuristic ranking. We identify two key shortcomings of full-distribution, logit-based methods: (i) an uncommon-token failure, where critical tokens fall into the unmatched subset (e.g., Llama's 1100 multi-digit numerals under digit-splitting Qwen supervision) and are suppressed during training, reducing GSM8k from 12.89 to 2.56 compared to same-tokenizer KD from a weaker teacher; and (ii) over-conservative matching, where strict 1-to-1 matching excludes near-equivalent tokens across surface forms. These failures require distinct remedies: eliminating the partition when critical tokens are misaligned, and refining it when alignment is reliable. We propose X-Token, an approach with two complementary loss formulations targeting these issues. P-KL removes partitioning and aligns the student's distribution with the teacher's via a sparse projection matrix W (initialized from tokenizer-level string rules) to address the uncommon-token failure. H-KL retains the hybrid form while relaxing matching to align each student token with its top-ranked teacher mapping under W. Both objectives share W and extend naturally to multiple teachers. Empirically, on Llama-3.2-1B, X-Token outperforms the current state of the art GOLD by +3.82 average points with a Qwen3-4B teacher and by +0.5 with a Phi-4-Mini teacher. Further, a two-teacher setup (Phi-4-mini + Llama-3B) improves over single-teacher distillation by +1.3 points.

Artificial intelligence (AI) is being increasingly integrated into human problem-solving, yet its effects on individual skill development remain unclear. We examine how both AI usage and informativeness can shape learning in the context of a controlled logical reasoning task with on-demand access to AI assistance. We find that greater AI usage is associated with weaker skill development: heavy AI users underperform relative to comparable peers, whereas light AI users perform similarly to matched users who do not use AI. We also find in our study that these patterns are mediated by AI informativeness. Low-information AI neither improves immediate performance nor preserves performance after AI assistance is removed, and is linked to weaker learning overall. On the other hand, high-information AI was found to improve short-run performance without reducing post-AI outcomes on average in our experiments, but with heterogeneous effects. Our findings in general suggest that AI can, depending on context, either complement human skill development by amplifying independent reasoning or can act as a substitute that undermines such reasoning, with the implication that regulating AI access and usage will be important for promoting skill development in the presence of AI assistance.

Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem in machine learning, which relies heavily on heuristics and practitioners' intuition to make key design choices. In order to mitigate this issue, we introduce the Representation Gap, a metric closely related to the generalization error, but admitting better-behaved asymptotic dynamics. Focusing on equivariant diffusion models and leveraging results from optimal quantization and point-process theory, we derive a precise asymptotic equivalent of the Representation Gap and show that it is governed by a single parameter, the \textit{intrinsic dimension} of the task, which is easy to interpret, efficient to estimate, and can be linked to the equivariances of common neural network architectures. We show that this asymptotic dynamic also extends to a broader range of tasks and training algorithms. Finally, we demonstrate empirically that our asymptotic law and intrinsic dimension estimation are accurate on a wide range of synthetic datasets, where these quantities are known, as well as on more realistic datasets, where we obtain results consistent with the related literature.

Autonomous contact-based micromanipulation is challenging because surface and interfacial interactions at the microscale are difficult to model accurately, limiting the use of conventional model-based control and sim-to-real learning. We present a closed-loop sim-to-real reinforcement learning (RL) approach for microfiber shape control on a surface. The central idea is to train geometric shape regulation in a simplified frictionless simulator and rely on real-time visual feedback during deployment to iteratively correct the observed effects of unmodeled surface interactions. An RL policy trained entirely in simulation is transferred directly to a physical dual-gripper micromanipulation system operating at 40 Hz, without retraining or domain adaptation. Using silk microfibers as a testbed, the policy achieves a mean point-wise shape error of 270 $\pm$ 80 $μ$m across twenty-four diverse initial configurations. Across nine specimens covering all combinations of three fiber diameters (50, 80, and 120 $μ$m) and three manipulated lengths (10 mm, 15mm, and 20 mm), the same policy achieves sub-millimeter final shape error without any retraining or retuning. These results show that a policy learned in a simplified simulator can achieve repeatable real-world microfiber shape regulation under surface contact, provided that the task-relevant effects of the sim-to-real mismatch remain observable and correctable within the closed feedback loop.

Autonomous drone swarms deployed for surveillance, environmental monitoring, and infrastructure inspection must maintain reliable coverage of critical assets despite robot failures. This requires multicoverage: each asset must be observed by multiple robots for redundancy, with coverage requirements varying by asset importance. While recent work has solved the centralized problem optimally using integer programming, practical deployments face constraints that demand distributed solutions: robots operate with limited communication ranges, onboard computation restricts global planning, and partial system failures must not cause mission abort. We present a distributed multicoverage algorithm for robot swarms operating with local sensing, local communication, and no global coordination.

Developing AI systems with a human-like understanding of everyday concepts is a key step towards developing safe, reliable systems whose behavior makes sense to humans. When probing concept understanding, asking questions about plausible category members (e.g., "Is a car a vehicle?") is likely to recall patterns in the model's vast training data. We pursue an alternative strategy, characterizing the boundaries of conceptual categories by asking about implausible category members (e.g., "Is an olive a vehicle?") to probe the kind of concept-level knowledge we take for granted in fellow humans. We characterize concept boundaries for a set of fundamental concepts by studying AI systems' assignments of objects to superordinate categories from a classic psychological study by Rosch and Mervis, as well as their assignments of the same objects to mismatched superordinate categories. We compare these assignments to those made by human participants on the full range of within-category and cross-category assignment tasks. Our results reveal a range of concepts for which which models differ in meaningful and surprising ways from humans, including treating "words" as belonging to categories like "vehicles" and "clothing," identifying several "vegetable" category members as "fruit," and assigning exemplars from non-weapon categories to the "weapons" category. We also demonstrate how these instances of concept misalignment translate into problematic downstream behavior with implications for AI safety.

While autonomous multi-robots can achieve safe and coordinated navigation, they often struggle to adapt to unforeseen conditions and to capture operator-driven objectives in unstructured environments. We present a Virtual Reality (VR)-based shared control framework for teams of drones operating in constrained and unknown environments, enabling real-time, user-guided exploration. At the core of our approach is a novel, user-guided motion-primitive-based planner that computes continuous, collision-free trajectories while continuously integrating operator input. This planner is coupled with an admittance controller, allowing the operator to flexibly influence team behavior and guide drones toward regions of interest that autonomous planners may overlook. The system supports mixed-reality operations with both physical and simulated drones, and implements a bilateral VR-based interface, allowing the operator to guide the robot team via migration points while receiving immediate visual feedback of the team state. Experimental results show that shared control improves obstacle avoidance, maintains inter-agent spacing, and reduces operator effort, demonstrating the feasibility and advantages of immersive, human-in-the-loop multi-robot navigation.

Hippocampal subfield segmentation requires high-resolution T2w turbo spin echo (TSE) MRI, yet this sequence is susceptible to motion artifacts, leading to substantial data loss. We developed a conditional generative model (MRecover) that synthesizes routinely acquired T1w images to create TSE images with autoregressive slice conditioning for volumetric consistency. Trained on 7T MRI data (n=577), the model achieved high in-domain fidelity (n=148, SSIM=0.84, FSIM=0.94) and generalized well to out-of-domain 3T data: subfield volumes from synthesized and the as-acquired images closely matched: (n=416, r=0.87-0.97) and yielded 31.8% more analyzable subjects in the motion-affected ADNI3 dataset after quality control (593 vs 450). The synthesized images also achieved larger effect sizes due to increasing the sample size for diagnostic group differences in hippocampal subfield atrophy (whole hippocampus $ε^2$= 0.121-0.100 vs. 0.086-0.062, left-right hemispheres). Project page: https://jinghangli98.github.io/MRecover/