让下一篇重要论文，不再错过。

Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffer or how much is at risk, and the records that could tell span many sources. We present WxCrop, the first agent that judges agricultural hazards from physically interpretable weather indices examined by causal analysis, and the first that combines weather and agricultural information to predict crop loss reliably for past and forecast dates. We demonstrate it in Florida on hurricanes, freezes and dry heat, with a loss model calibrated on insurance records for each, and the same procedure extends to other hazards and areas. Three checks show reliability: the hurricane index detects recorded cyclone days with an AUC of 0.98, recorded losses in held-out years are reproduced to within 2%, and independent production records confirm the county rankings (rank correlation 0.63). Users ask the agent for each crop group's loss as a fraction of expected season value, every number sourced, so that governments, growers and scientists respond to agricultural disasters quickly.

Recent progress in visual scene generation has extended beyond static 3D scenes toward the more challenging problem of generating dynamic 4D scenes from minimal input. However, sound, despite being intrinsically coupled with dynamic objects and events, remains largely unmodeled in prior work. We introduce Video-to-4DAVScene, a new task that turns a video into an explorable, time-varying 4D audio-visual scene, and present the SonoWorld4D framework for this task. Given a monocular video, our method generates a 360 static background, reconstructs explicit motion trajectories of dynamic, sound-emitting foreground objects, and synthesizes a physically-grounded sound field consistent across multiple sources through dual-space audio diffusion synchronization. The resulting 4D scene supports real-time novel-view visual and spatial audio rendering. Evaluation on real-world dynamic scenes and a user study demonstrates SonoWorld4D generates 4D audio-visual scenes with perceptually realistic, physically grounded spatial audio consistent with scene geometry and visual content.

World models can achieve strong control performance without faithfully capturing the dynamics of their environment, limiting their potential for mechanistic interpretability and scientific discovery. Here, we introduce world2vec to learn mechanistic world models without reward information directly from observations and actions. World2vec learns latent dynamics that faithfully reproduce the true system over long prediction horizons, with at least one order of magnitude fewer parameters than DreamerV3, TD-MPC2 and LeWM. This enables state of the art performance in controlling continuous environments from pixels and accurate system identification across a benchmark of 71 attractors, demonstrating how world models are amenable to scientific discovery.

The classic duck-rabbit illusion reveals a fundamental property of perception: when visual evidence is ambiguous, a visual system must resolve competing interpretations. But do humans and machine classifiers resolve the same ambiguity in the same way? To explore this, we use semantically ambiguous images as probes of human-machine perceptual alignment. Our psychophysically-informed framework interpolates between concepts in vision-language embedding space to generate continuous spectra of ambiguous images, enabling direct comparison of human and machine perceptual decision boundaries and sensitivities. We find systematic differences in these boundaries: machine classifiers are shifted relative to both human observers and the midpoint of the synthesis continuum. Guidance scale affects both bias and sensitivity in humans and the machine classifiers tested. Controlled semantic ambiguity in generated images, combined with a psychophysical framework, can thus enable quantitative evaluation of human-machine perceptual alignment.

An observer sees only part of the surrounding world, yet must keep track of what lies beyond the current view. Spatial perception therefore involves more than recognizing individual images: it calls for a persistent spatial state that is updated under self-motion and used to guide action. Do visual foundation models provide representations that support such a state? We study this question through four levels of spatial capability---spatial structure, object persistence, predictive spatial update, and actionability---using frozen-feature probes on ten representations under streaming egocentric observations of static indoor environments. The resulting capability profiles vary across tasks, network layers, and prefix lengths: strong readout of the visible scene does not ensure accurate object persistence or future-feature retrieval. Matched controls separate readout accuracy from reliance on visual history and motion. Native future prediction retains recoverable spatial structure, but a spatial reader trained on real features does not transfer to predicted features unchanged. Finally, goal-dependent candidate selection does not establish reliable continuous action utility: predicted actions respond to goal changes, yet supplying the correct goal does not reliably improve progress. Across the four levels, object persistence and actionability build on camera-pose readout, whereas feature prediction builds on visible-scene readout. Together, these findings motivate evaluating spatial representations not only by what can be decoded from them, but by whether that information is maintained beyond observation, updated predictively, and used for goal-directed action.

As robots and intelligent systems increasingly interact with humans, they must anticipate long sequences of future actions from only brief observations. While purely neural models typically require extensive observations to predict future actions and remain difficult to interpret and adjust, symbolic priors offer a structured alternative. To this end, we introduce SymAnt, a novel neuro-symbolic approach that unifies the expressiveness of neural networks with the structured reasoning of scene and knowledge graphs. Given a short video, SymAnt performs a joint-search over both graphs to construct a symbolic context, enabling unified reasoning over spatial relationships, object attributes, affordances, and associated actions. This symbolic context serves as a prior for an iterative refinement process that progressively generates and improves the sequence of future actions. By grounding predictions in symbolic context, SymAnt anticipates long-horizon actions from short observation windows in a parameter-efficient manner, while enabling users to directly edit the underlying knowledge to adjust predictions without further training. Through our experiments, we demonstrate the effectiveness of SymAnt, particularly when only short observation contexts are available, across five diverse datasets: Breakfast, 50 Salads, EPIC-KITCHENS, EGTEA Gaze+, and Assembly101.

Safety alignment has enabled large language models to reliably refuse harmful requests directly, yet the same request distributed across a multi-turn conversation still succeeds far too often. This brittleness has a mechanistic root: Alignment is shallow, with safety behavior concentrated in a model's first few output tokens, and existing defenses inherit the weakness, supervising the surface form of the response without ever giving the model an explicit safety decision to learn. We take the opposite view of shallowness: if a short span determines the trajectory of an entire response, that span is the highest-leverage place to intervene, and the defender can occupy it first. We propose Assess $\to$ Decide $\to$ Respond, a framework in which the defender assesses the user's intent, commits to an explicit, parseable safety decision, and only then generates a reply conditioned on it, with the commitment trained by reinforcement learning at the payload turn. Because the decision is a token span, the reward can be a rule: a self-verified reward checks the committed label against the conversation's known nature, requiring no judge and no annotation, while the same format also supports an LLM-as-judge reward over a graded decision space with safe redirection. Across two model families and fourteen benchmarks spanning safety, utility, and helpfulness, our defenders achieve the strongest multi-turn safety in a controlled comparison, maintaining their lead in safety while preserving utility at a modest cost to helpfulness. A per-token KL analysis and interventional probes confirm why this works: training concentrates its effect on the brief deliberation that sets a response's trajectory, and the decision committed there is a causal control point. The very shallowness attackers exploit becomes the mechanism of defense.

Adapting Large Language Models (LLMs) to specific tasks usually involves fine-tuning: Low-Rank Adaptation (LoRA) edits the weights, while soft prompting prepends trainable virtual tokens. Both change how an already-optimized model is served, so serving many task-specific adapters at high throughput requires adapter-aware infrastructure. We propose Art-Based Reinforcement Training (ART), which optimizes a single auxiliary input image to specialize a frozen Multimodal Large Language Model (MLLM) for a specific task. At inference time, ART simply includes this image in each standard multimodal prompt, requiring no changes to the serving engine. We compare ART with LoRA and soft prompting across five reasoning benchmarks for four small MLLMs from three architectures. While different methods perform best for different tasks, ART ranks first or second in 10 of 20 benchmark-MLLM pairs, with its best results on the two math word problem benchmarks (GSM8k and SVAMP). It is significantly ahead of the next best adapter in 2 cases, within the noise of the next best adapter in 6, and significantly above the text-only baseline in 18. ART therefore reaches accuracy close to LoRA and soft prompts while serving faster than LoRA. In the vLLM serving stack, ART reduces throughput by 6% to 14% relative to text-only requests, compared to LoRA's 13% to 93% slowdown. Beyond efficient serving, ART artifacts are plain images, making them easy to store, distribute, and share. This approach keep task-specific adaptation outside the model weights, so the same frozen model can support different tasks without separate model variants.

Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be uneven: gains in some categories coincide with regressions in others, while aggregate resolution obscures these changes. Motivated by this category see-saw, we develop a category-aware expert-training and policy-integration framework. Executable task construction and SWE Labeler, an evidence-grounded multi-axis labeling system, organize the training pools. Initial category-specific RL improves average training success while leaving uneven instance-level progress, motivating explicit consolidation of successful behavior and policy-adaptive task selection. Same-origin category experts alternate long-horizon Agentic-miniRL with Refresh-Repair-Expand (RRE): the updated policy refreshes instance mastery, reuses its own verified successful trajectories for Repair SFT, and reselects tasks for further RL. Label-routed multi-teacher on-policy distillation (MOPD) consolidates the experts into one deployable student, with ReLU-gated reward extrapolation keeping only each teacher's improving direction over the reference. Expert training and policy integration require no external model to provide solution trajectories or action targets. On a fixed, audit-filtered Pro-618 subset, we connect Pooled RL and Balanced RL, expert development, and single-model integration through overall and per-category resolution and expert-gain recovery. In final-model evaluations, MOPD achieves mean resolution of 86.19% on SWE-bench Pro V2 and 71.78% on SWE-bench Multilingual, exceeding the base model by 4.57 and 3.89 percentage points, respectively. The same three 27B experts also improve a Qwen3.6-35B-A3B student across the evaluated task sets.

Differential privacy is the leading mathematical framework for privacy protection, providing a probabilistic guarantee that safeguards individuals' private information when publishing statistics from a dataset. This guarantee is achieved by applying a randomized algorithm to the original data, which introduces unique challenges in data analysis by distorting inherent patterns. In particular, causal inference using observational data while preserving privacy is challenging because it requires a good covariate balance between treatment groups, but checking the covariate balance is challenging when privacy is a primary concern because releasing any statistic (e.g., t-statistic) for the balance check compromises privacy. Additionally, the performance of the privatized estimator critically depends on the choice of differential privacy mechanisms, and it remains unexplored how privacy-protecting causal inference could be conducted with observational data. In this article, we present a differentially private two-stage covariate balancing weighting estimator to infer causal effects from observational data. Our algorithm produces both point and interval estimators with statistical guarantees, such as covariate balance, rate optimality, and oracle budget allocation, under a given privacy budget.

Ask a language model whether sales tend to dip after a product recall, or whether one side effect tends to follow another after a vaccine, and it answers in a fluent sentence that reads like a finding, with no test behind it. Assertions about how events unfold across many cases fill the Web, and each is a temporal hypothesis that only a significance test over the right records can settle. The verifier must specify the null, select the test and decide which records bear on the hypothesis, and any of these choices can go wrong while the conclusion still comes out right. Yet benchmarks for language-model data analysis grade only the conclusion, with the relevant data handed over. We study the problem in health, where a wrong verdict is costly, and present STRATA, a benchmark that grades every decision on the way to a verdict: 8,735 hypotheses over the clinical timelines of vaccine adverse-event reports, with gold plans, evidence sets, p-values and verdicts derived under a released codebook and reproduced by a deterministic oracle. We also propose ART (articulate, retrieve, test), a staged paradigm that exposes each decision as an inspectable output. Extensive experiments with five model configurations show that systems fail mostly at choosing which records count, a verdict-evidence gap that accuracy alone conceals. ART closes most of this gap and brings a 31B open model to within 0.01 of the frontier models under the same paradigm; the frontier models succeed once given the codebook.

The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated sampling and consistency distillation. In this paper we address the question whether an analogous formulation exists for discrete diffusion models and answer it affirmatively by introducing exponential residual flows (ERFs). Our framework augments the discrete state with a continuous residual variable for each token and position. These residuals evolve deterministically according to piecewise-defined ODEs whose vector fields depend on the current discrete state and the forward and backward rate matrices of the prescribed diffusion model. The discrete state changes whenever a residual reaches zero. We prove that this construction preserves the marginals of the original diffusion. We derive a practical discretization of our sampler and specialize it to masked and uniform diffusion. The deterministic trajectories of ERFs support consistency distillation and yield empirical improvements over previous approaches across a variety of benchmarks including code and text generation tasks.

Election integrity is a shared commitment in American politics, but Democrats and Republicans in Congress increasingly mean different things by it. Analyzing 10,420 congressional e-newsletters sent from 2010 to 2025, we examine how the two parties invoke election terms such as ``integrity,'' ``security,'' and ``fraud.'' Using diachronic word embeddings, which track semantic change through how words are used in context, we measure how differently each party uses each term, how much each party shifts, and whether they share nearest semantic neighbors. We show that members of Congress do not need different words to tell different stories about elections. They need only place those same words in different company. Across nearly every term and year, the two parties surround election-integrity vocabulary with entirely different words. That divergence is easy to miss, because most election vocabulary is no more divergent than other words used at roughly the same frequency, and neither party's usage shifted more than the other's. Only a subset of terms grew more divergent, most notably ``certification,'' while ``rigged'' and ``stolen'' entered election discourse after 2020 and polarized there. By 2024, Democrats surround ``voter,'' ``election,'' and ``integrity'' with the language of access and administration. Republicans surround the same terms with ``citizenship verification,'' ``noncitizen voting,'' and ``border security.'' For one party, integrity means protecting eligible voters' ability to cast a ballot. For the other, it means protecting the electoral process from illegitimate ballots. Election officials, who must administer a single system under both definitions, inherit this tension.

Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a given image was in a model's training set. The standard approach scores an image by its reconstruction loss and flags low-loss images as members. This often fails because some images are simply easier to reconstruct than others, so a simple unseen image can score a lower loss than a complex training image. Difficulty calibration separates memorization from how difficult an image is to begin with. We show how to calibrate along two axes of time: training time and diffusion time. First, across training time, we introduce Reference-Model Calibration (RMC), which compares a fine-tuned model's loss against an earlier checkpoint. This cleanly isolates newly memorized data and gives near-perfect auditing, even without text captions. Since earlier checkpoints are not always available, we next present Temporal Self-Calibration (TSC), which calibrates across diffusion time using only a single model. Our key observation is that an image's difficulty persists across noise levels, whereas memorization is localized in time. By comparing the loss at a target timestep against neighboring timesteps from the same model, TSC attenuates image difficulty using the model's own trajectory. Empirically, our methods beat the state of the art by a wide margin, and unlike most existing attacks, generalize across different model parameterizations such as $x$-, $v$-, and $ε$-prediction models. Code is available at https://github.com/MichaelJoseph777/TSC.

Interactive world models generate visual content conditioned on user actions, yet maintaining spatial consistency over long-horizon exploration in real time remains challenging. Existing approaches rely on either temporal context or explicit 3D memory, both of which scale poorly because memory grows with the length of the generated stream. Moreover, explicit 3D memories condition latent video generators by re-encoding RGB renderings, which precludes real-time generation. In this paper, we introduce a Latent 3D Gaussian Memory (L3G) that combines the efficiency of feed-forward reconstruction with a compact, rapidly renderable scene representation. Building on this memory, we propose L3G-World, in which a memory updater and a video diffusion transformer (DiT) alternate autoregressively to generate spatially consistent worlds. The memory updater spawns Gaussians in newly observed regions and refines existing ones, so that the memory grows with scene extent rather than stream length. Each Gaussian further stores a VAE latent feature, allowing the memory to be rendered directly into the DiT's latent space without VAE re-encoding. Experiments show that L3G-World achieves state-of-the-art generation quality and long-horizon spatial consistency, with up to $38.6\times$ fewer 3D primitives, $3.2\times$ faster memory updates, and $359\times$ faster memory rendering relative to the most efficient prior 3D-memory baseline for each metric, enabling real-time world generation at 9 FPS.

We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same keys, and the acceptance rate is unchanged. It also preserves output diversity and adds no measurable inference latency. Its predecessor, TextSeal, restores diversity in the Gumbel-max scheme by routing each token to one of two keys via a coin flip. This is suboptimal because the detector averages the scores from both keys without knowing which key was used. TextSeal2 instead merges two or more keys into a single virtual key and couples it to fresh noise through AutoMark's Gaussian copula. Any number of keys, including publicly shared keys, can be merged this way without diluting detection. Under speculative decoding, TextSeal2 verifies keyed drafts with one more exponential race, run on the leftovers of the draft races. By memorylessness, this race reproduces block verification, so the output follows the target model exactly. We evaluate TextSeal2 on three LLMs. At equal output token diversity, TextSeal2 detects 8 to 22 percentage points more 100-token answers than TextSeal at a false-positive rate of $10^{-3}$, and is comparable to textGrain while requiring no post-logits optimization. Under speculative decoding, it detects 18 and 22 percentage points more 200-token answers than TextSeal and textGrain, respectively, at the same acceptance rate.

Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and a larger generator; we evaluate both together on 28,058 decision points. Stage-wise generation scores are oracle-gate ceilings: behind a real gate, end-to-end exact match is 0.2619 against a ceiling of 0.2971, and end-to-end precision is 0.2387, leaving substantial headroom. A gate pays off through precision and compute, whose saving falls from 4.39x with an 8B generator to 1.38x with a 1B one. The memory profile drives hint quality: removing it costs 24.7 exact-match points (rescaled BERTScore 0.57 to 0.35), while retrieval and a larger generator add nothing on exact match. One 1B decoder can do both, gating from an intermediate layer and generating in the same pass. At its final checkpoint it matches or exceeds the two-model pipelines on automatic end-to-end measures with 1.31-1.76x less wall-clock time than the matched 1B pipeline; across three seeds, its deeper exit ties the separate gate. A human evaluation (1,144 ratings over 32 dialogues) supports the memory effect and rates the single model level with the matched 1B pipeline and below the 8B one. Graded metrics and LlamaPIE's native judge track human ratings more closely than exact match, which we report as a strict lower bound.

A playable, programmable game world must maintain persistent state, enforce executable rules, and support extensible gameplay mechanics. Existing video world models can generate plausible combat, yet struggle to keep hit reactions and health updates consistent with game rules. We introduce Fight World Model (FWM), which separates rule-governed combat execution from video rendering. An executable engine maintains state and resolves interactions. A deterministic compiler encodes these outcomes and attempted actions in a spatially and temporally aligned interaction proxy. The proxy aligns action and skill windows, brief hit reactions, and persistent health by fighter identity and timing. These cues can be controlled separately to render interactions under modified rules. Identity-bound references preserve character appearance across side switches. We train FWM on FightWorld Corpus, spanning 52 skill effects, 187 character-appearance variants, and 15 arenas. Without retraining the renderer, FWM supports damage scaling, limited-hit immunity, lifesteal, and multi-stage skill mechanisms beyond the native game. It also allows character and arena customization. Experiments demonstrate the effectiveness of FWM, which outperforms existing game world models in action fidelity, hit reactions, health-state consistency, and character appearance preservation. Our project is available at https://fight-world-model.github.io.

This work proposes a novel conveyor belt mechanism enabling continuous, active repositioning of functional elements along the body of a tendon-driven continuum robot. Up to three conveyor belt mechanisms are integrated within a 9 mm diameter continuum robot. We demonstrate equivalent or reduced conveyor belt actuation forces compared to robot tendon actuation forces. As a case study, we mount permanent magnets along two conveyor belts, and demonstrate actively reconfigurable inter-robot coupling. Coupling point location and quantity can be adjusted during robot operation to actively tune the effective stiffness of the coupled multi-robot system. We show that effective stiffness follows a predictable inverse-cubic relationship with coupling location, and increases with the number of coupling points. These findings demonstrate that the conveyor belt mechanism enables active functional element repositioning for changing tasks requirements, with magnetic inter-robot coupling as one proof-of-concept.

The hair of stylized characters in games and avatars is built from hair cards: artist-placed ribbons whose geometry is the visible hair, animated by spring bones. Existing image-based methods produce realistic hair or a single fused mesh, while CHARM, the only generator of stylized hair cards, decodes a hairstyle autoregressively as a long sequence of control points. Observing that a card hairstyle is an unordered set of artist-defined primitives, we propose HairDeck, which generates it as one: each card is a single token, and a set diffusion transformer denoises all cards together. From a single image, HairDeck generates the cards and the spring-bone chains that drive them, yielding an animatable asset that exports to ready-to-use downstream formats. On CHARM's own test set, it lowers Chamfer distance by 44% and card-orientation error by more than half while running 33 times faster, and from single images it outperforms CHARM, image-to-3D pipelines and strand-based methods. Project page: https://hyzcluster.github.io/HairDeck

An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards this goal. Recent AI systems take on several research roles, but may draw conclusions that the evidence does not support. Here, we present an autonomous research laboratory in which agents based on large language models assess one another's work and can stop or redirect investigations. They can generate and reject research questions, require separate theoretical checks and conduct experiments designed to challenge their claims. We demonstrate these capabilities by investigating ensembles of quantum spins in diamond. The agents derived the minimum number of calibration settings needed to predict responses to a defined family of microwave pulse sequences. They checked the result computationally and designed experiments to distinguish competing predictions. An initial experiment agreed with the theoretical predictions, but repeated reference measurements showed that the signal was drifting during data collection. The agents therefore treated the result as inconclusive and revised the measurement protocol without relaxing the acceptance criteria. The revised experiment met those criteria and supported the theoretical predictions. This study demonstrates that collaborating AI agents can select research questions, derive theoretical results and test their predictions experimentally.

When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an agent has already written. Can an overseer tell beforehand that an agent is about to give in? We show that a linear probe on the agent's activations can, in a controlled multi-agent setting. Across six scenarios, a peer presses a target for up to 20 rounds to reveal a secret, such as a deploy token; the target often refuses, then gives in. Read at each model call before its output is written, the probe picks out the one that leaks. On held-out Qwen3-32B episodes, at a threshold set to flag 5% of benign calls, it catches 82% of leaking calls. At a similar flag rate, a zero-shot decision-model monitor catches 26%. On gpt-oss-20b, a probe on its reasoning reaches AUROC 0.91. A bag-of-words classifier trained on the same calls comes close, so most of the gain comes from training on labels, not activations. The probe also flags permitted disclosures: it reads the coming disclosure more than the violation. The warning is short-range, and halting on any alarm would stop most benign episodes, which a second text check does not fix. A warning raised before generation could let an overseer stop an agent that is about to give in, ahead of others acting on its messages or recruitment spreading through a swarm.

In real-world clinical settings, dental X-ray segmentation using deep learning methods suffers from reliability issues. Even when the segmentation quality is bad, deep learning models show high confidence in their predictions (calibrational blindness). Moreover, in real use, doctors do not have ground-truth masks to check their accuracy. To address this problem, we introduce a simple quality-checking engine called HUS-QA with three stages. We train it on the PRAD (Periapical Dental X-ray) dataset to build our SimCLR self-supervised ResNet-18 U-Net model, which generates the segmentation mask and then evaluates its quality. Our HUS-QA checks the segmentation mask quality without a ground-truth mask. Prediction confidence, edge sharpness, shape connectivity, and area-size penalty are the simple indicators considered in this research. Results show that standard confidence methods fail (r = -0.1394, p = 1.7864e-3, ROC AUC = 0.4275). By contrast, our HUS-QA shows a positive correlation with actual Dice scores (r = 0.4647, p = 3.7510e-28) and achieves a strong ROC-AUC of 0.8405. Therefore, HUS-QA serves as a practical tool for clinical quality control.

Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spectrum resources. While multistatic ISAC can increase sensing coverage with spatially distributed receivers, dense and dynamic clutter can significantly degrade bistatic range and Doppler estimation, leading to errors in target localization and velocity estimation. This paper presents a multistatic ISAC framework with clutter suppression for high-fidelity estimation of target position and velocity. Distributed clutter is modeled with randomly located scatterers with varying Doppler spreads and radar cross sections to capture dense and dynamic clutter effects. A broad range of conventional signal processing baselines are evaluated for clutter suppression, showing limited robustness under strong clutter conditions. To address this limitation, deep learning-based clutter suppression methods are introduced to improve robustness against dense and dynamic clutter by employing residual and attention-enhanced deep neural network architectures that directly enhance target responses from clutter-contaminated observations. These methods substantially outperform conventional approaches in target position and velocity estimation across diverse clutter conditions in multistatic ISAC.

Current zero-shot anomaly detection methods often rely on complex prompt-learning techniques or computationally expensive sliding-window strategies to achieve fine-grained visual alignment to detect small-scale anomalies. This reliance stems from the fundamental limitation of standard CLIP architectures, where [CLS] token attention and spatial patch pooling struggle to capture subtle, localized anomaly features. While prompt-learning approaches aim to bridge this gap, they typically require a large number of ground-truth segmentation masks from auxiliary datasets, which are often unavailable in specialized domains. In this work, we show an emerging property of multi-head attention pooling in vision-language models: remarkable zero-shot anomaly localization and detection right out of the box. We translate this property into a single-pass anomaly detection technique, RADIOlogy, that does not require dense, windowed execution and significantly outperforms other training-free baselines. Instead, the method relies on a simple contrastive scoring approach that compares the average similarity between vision features and a suite of normal and abnormal prompts. Furthermore, we leverage the agglomerative features of RADIO models to enhance pixel-level anomaly segmentation using a dense anomaly refinement pipeline. Finally, we show how the vision-language family of training-free zero-shot anomaly detection techniques can be applied successfully to the medical domain with minimal modifications. Code is available at https://github.com/jacomof/RADIOlogy.

Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation, and reinforcement learning. Typical automated approaches prompt vision-language models (VLMs) to judge trajectories or generate programs to inspect application state. However, both rely on partial views of complex digital environments. VLM judges are restricted to supplied observations, while generated programs depend on accessible state. These views can omit decisive evidence or leave completion judgments unsupported. Tailoring separate verifiers to different platforms and access settings adds further engineering cost. We present VeriCUA, a platform-agnostic framework for verification through agentic exploration. It treats verification as dynamic evidence gathering and assessment within a shared procedure for online and offline settings across platforms and observation modalities. After inspecting the available context to construct a task rubric, the verifier selects GUI or code checks for unresolved requirements and combines their findings under explicit evidence rules. Experiments show improved agreement with reference labels over the compared baselines across these settings, with the largest offline gains on hard cases and stronger rejection of false completion claims online. Further analyses connect these gains to complementary evidence and test-time exploration.

Reinforcement learning from verifiable rewards (RLVR) is limited by sparse outcome-level feedback on hard reasoning tasks: when all rollouts in a group fail, rewards provide no learning signal. Stronger teachers can provide additional guidance, but this raises a central question: how can such signals be incorporated into RLVR to support successful rollouts while remaining learnable for the student? We distinguish two complementary mechanisms: trajectory-level intervention, which improves access to reward-bearing trajectories, and token-level supervision, which provides dense targets to guide student learning. Our controlled experiments show that either mechanism alone can remain insufficient, motivating their combination. We therefore introduce PIVOT, which inserts teacher-generated corrections into student rollouts and applies token-level KL supervision to these segments alongside the RLVR objective. Beyond their combination, we systematically analyze where to intervene and how to supervise, yielding a recipe for effective guidance. Across hard logic games and mathematical reasoning benchmarks, PIVOT consistently outperforms existing methods, nearly doubling mean avg@8 on logic games from 19.5% for the best-performing baseline to 35.6%.

Uniform Discrete Diffusion Models have emerged as a powerful paradigm for generative modeling on sequence data; however, the information-theoretic principles governing their reverse processes remain underexplored. In this work, we bridge this gap by analyzing the reverse process dynamics through the lens of thermodynamic entropy production and dynamical activity. We use a variational expression of the discrete Wasserstein distance to characterize the dynamics of the generation process. Leveraging these insights, we first introduce the Entropic Discrete Schedule (EDS), which aligns with entropy production, and later construct the Wasserstein Discrete Schedule (WDS), which combines entropy production and dynamical activity to act as a geometric cost. Our experimental results on language modeling show that WDS provide the same results as uniform while using up to half of the computations on the MBPP benchmark. The code is available at https://github.com/AlbertoForesti/impscheds.

On-policy Self-distillation (OPSD) has proven effective for post-training large language models by constructing a teacher conditioned on privileged references. However, existing approaches keep the teacher fixed either throughout training by consistently exposing it to the full reference, or within each response by adaptively varying partial reference exposure only across responses. In this paper, we argue that neither of them is sufficient. Instead, every token needs its own teacher, as the teacher preference can vary token by token within the same response. Through a teacher-intervention pilot study, we validate that the teacher preference differs across tokens, and reveal that a preferred teacher can be identified for each token through majority voting and KL-based selection. Motivated by these findings, we propose Multi-teacher Adaptive On-policy Self-Distillation (MTA-OPSD), the first token-level adaptive OPSD method. Our method constructs a multi-teacher pool consisting of candidate teachers, and enables every token to adaptively select its preferred teacher during training. Experiments with Qwen3 models on mathematical reasoning tasks show that MTA-OPSD consistently outperforms existing OPSD approaches with an average gain of up to $+5.9$ over the base model, highlighting the importance of adapting teacher supervision at the token level. The code is available at https://github.com/xingzhejun/MTA-OPSD.

Given a labeled dataset $\{(x_i, y_i)\}_{i = 1}^n$, consider drawing a parameter vector $\hatθ$ uniformly at random from those that interpolate the data within a width-$W$ depth-$D$ ReLU architecture with continuous weights bounded within $[-M, M]$. We study the generalization properties of $\hatθ$ in the case where the dataset can, in fact, be explained by a smaller $w$-by-$d$ ReLU network. Despite the obliviousness of the selection rule for $\hatθ$, it adaptively generalizes at the rate $\tilde O\left(\frac{wdWD}{n}\right)$, rather than being governed by the VC dimension of the full $W$-by-$D$ hypothesis class. The reason is due to a particular inductive bias in ReLU networks: the $w$-by-$d$ parameter *witnesses* an exponential volume of $W$-by-$D$ interpolating parameters, which dwarfs the volume of poorly generalizing parameters (conditioned on interpolation). We explicitly construct this set of near-equivalent $W$-by-$D$ parameters by a proof technique called *deep lifting*, and then tie the achievable volume to stability properties of the $w$-by-$d$ witness. Examples show that these techniques allow us to convert approximation-theoretic results into generalization guarantees for nonparametric classes. We further show that generalization of uniform-random interpolators can survive label corruptions.