Joint-Embedding Predictive Architectures (JEPAs) support planning by comparing predicted latent states with an encoded goal. For this comparison to guide temporal progress, states closer in time to the goal should receive lower costs. However, training representations for prediction and distribution regularization does not directly enforce this ordering. We examine this mismatch in flat LeWorldModel (LeWM) by analyzing how its Euclidean goal cost changes with temporal separation. Our analysis identifies conditions under which states at different long offsets receive similar average costs, weakening their temporal distinction. To learn the missing ordering explicitly, we introduce Time-to-Goal (T2G), a lightweight metric trained on latent triples from offline trajectories. A margin ranking loss encourages smaller distances for temporally nearer states, requiring no rewards or policy labels. The learned metric then replaces the Euclidean planning cost while the JEPA encoder and predictor remain frozen. Diagnostics on AntMaze and FourRoom show that T2G preserves stronger temporal contrast and improves near--far ranking at long offsets. Across four navigation and manipulation benchmarks, T2G improves the average planning success rate from 32.7\% (flat LeWM) to 63.0\% and approaches or even surpasses the performance of the hierarchical H-JEPA baselines. These results show that learning temporal ordering for the goal cost can substantially improve latent planning even with a flat world model.
User preferences shift as needs, context, and tastes evolve. This matters for personalized recommendation, LLM response generation, and RLHF-trained reward models, which can become miscalibrated as preferences drift. Existing non-stationary bandit methods forget uniformly across all dimensions, but real preference shifts are typically partial: some dimensions go stale while others remain valid. Neural contextual bandits accumulate confidence monotonically via the Gram matrix, with no mechanism to direct uncertainty where predictions have gone wrong. We propose PEARL (Prediction Error-Adaptive Regularized Learning), which reverses the Gram update along feature directions where predictions are surprisingly wrong, while leaving confidence intact elsewhere. We prove that (i) any non-adaptive policy suffers linear regret after a preference shift, (ii) no fixed exploration rate achieves low regret in both stationary and non-stationary regimes, and (iii) PEARL's cumulative regret scales with the number of shifted users N_s, not the total population N. On PRISM, a personalized LLM response selection benchmark (1,500 users, 21 LLMs), PEARL beats greedy by +4.0 points and the best neural bandit baseline by +2.5 points (p<0.001), while performing on par with greedy when preferences are stable. It beats sliding-window and discounted approaches by 3 to 10 points, showing that selective forgetting outperforms uniform forgetting. The selection policy is a ~100K-parameter MLP that runs in milliseconds on CPU, leaves LLM weights frozen, and works with any API-based model.
Firms using large language models under fixed budgets must decide which model to call and whether to retry a failed task. Because a call's charge is revealed only after completion, one long response can exhaust the remaining budget and leave later tasks unserved. Our objective is to maximize the number of tasks solved before service stops. We develop a contextual bandit policy, ADP-HT, which learns each model's task-specific success probability and constructs conservative cost estimates from coarsened response-length labels on a quantile grid with $2^K$ intervals. The policy weighs predicted success against these costs, adjusting the cost penalty to realized spending and the budget available per remaining task. Under calibration, local regularity, and grid-coverage conditions, we bound the excess allowance in the policy's conservative cost estimates. At a fixed sample size, increasing $K$ reduces the discretization term but increases the estimation allowance. At the tightest tested budgets, ADP-HT solves more than twice as many MATH500 and GPQA tasks as the best implemented baseline. It achieves the highest mean cumulative score at ten of fourteen RouterBench budgets. On LiveCodeBench, it outperforms a deployed commercial router in both default and cost-saving modes at the three lowest test budgets.
Decision models choose among predefined options in tasks such as routing and action selection. In multi-agent collaboration, a decision determines how members divide work, exchange resources, and act in parallel. We introduce TandemBench, a benchmark of 1,200 questions in multi-agent cooking scenarios where coordination choices affect goal completion. Models receive complete global information and candidate team plans, with reference answers established through execution and exact search. Models select an optimal team plan and, in paired variants that retain or remove it, judge whether better arrangements exist beyond the supplied options. We evaluate 40 native decision models and compare them with 10 general-purpose language models. The best native decision model achieves 62.50% decision accuracy. Native decision models remain close to chance in optimality verification. Paired tests reveal that some report better alternatives regardless of whether an optimal plan is already present. These findings show that team-plan decision accuracy alone can conceal systematic errors in judging whether the supplied options contain an optimal arrangement. The dataset and evaluation code are publicly available at https://github.com/lililibaohang/TandemBench.
Digital human e-commerce video generation requires preserving product appearance, human identity, and overall video style during dynamic demonstrations. Although recent models support multiple reference images, their general conditioning schemes do not explicitly distinguish the asymmetric roles of "what is presented" and "who presents it." Consequently, generated videos may favor a single reference, resulting in product distortion, identity drift, or single-reference collapse. To address this issue, we propose DualCast, a role-addressed dual-image conditioning framework for video generation. By explicitly modeling the distinct roles of product and human conditions, DualCast reduces role ambiguity and feature competition between references. First, a dual-spatiotemporal slot injection mechanism VAE-encodes the product and human images separately and places their latent features at the front and rear boundaries of the DiT sequence, enabling sequence-level condition separation and directed injection. Second, a mask-guided region-weighted loss strengthens supervision over product, face, and product-face overlap regions, improving generation fidelity in critical areas. Third, image condition dropout enables a single model to support dual-image, product-only, and human-only generation. In addition, we construct a curated dataset of 10K e-commerce videos for model training. Experimental results demonstrate the strong performance of DualCast.
Marine surface vehicles (MSVs) have attracted considerable attention for their commercial, scientific, and military applications. Owing to their favorable performance-to-cost ratio, shipboard cameras are widely used to detect and recognize potentially hazardous situations across diverse operational scenarios. However, visual perception is inevitably degraded by restricted conditions, including irregular motion of the imaging platform, adverse weather, and long imaging distances. To improve situational awareness and navigation capabilities, complementary sensors, such as the automatic identification system (AIS), radar, and light detection and ranging (LiDAR), etc., have become essential shipboard equipment. Multi-sensor fusion can provide richer perceptual information and help ensure navigational safety of MSVs in restricted visibility. This article reviews recent progress from intelligent vision to vision-centered multi-sensor fusion for newcomers and researchers in intelligent ship navigation and intelligent waterborne transportation system (IWTS). After introducing the generation of quality-degraded images in restricted visibility, we will review intelligent vision methods for four key issues, i.e., shipboard video stabilization, visual perception enhancement, object detection and tracking, and navigable area segmentation. We then examine vision-centered multi-sensor fusion methods, including infrared-visible image fusion, radar-vision fusion, LiDAR-vision fusion, AIS-vision fusion, and other multi-sensor fusion scenarios. Open-source datasets and safety-critical applications are also summarized and discussed. Finally, we highlight open challenges and future research directions. The collected maritime datasets are available at https://github.com/MAPGroup/Datasets and will be regularly updated.
Large language models increasingly automate complex tasks, but human decision capacity does not scale with their capabilities. In many applications, humans remain essential for providing private context, authority, or judgments unavailable to the agent. We formulate human decision capacity allocation: given multiple consultation opportunities and a limited budget, at which decisions should an LLM agent consult a human? The central challenge is estimating consultation value, which is executor-dependent because the same human input may benefit different downstream agents differently. We introduce Consultation Value Distillation (CVD), which estimates consultation values offline using Monte Carlo executor rollouts and distills these values into lightweight predictors for budgeted allocation, requiring no rollout-based value estimation at deployment. Across five batch and three sequential settings with two frontier executors, CVD improves allocation through joint and continuation-aware value learning, while independent consultation values remain competitive in several settings. CVD also broadly outperforms direct prompting and Value of Information where applicable, remains robust with substantially less rollout supervision, and enables nearly lossless approximate allocation at low search cost.
We study the query complexity of sampling from smooth distributions on $\mathbb R^d$ using first-order oracles. For $d$-dimensional strongly log-concave targets with condition number $\kappa=2$, we prove that any randomized sampler requires $\exp({\Omega(\log^{1/3} d)})$ queries even from a constant warm start. This rules out polylogarithmic dimension dependence and strictly separates strongly log-concave sampling from Gaussian sampling. For targets with $L$-smooth potentials satisfying an $\alpha$-log-Sobolev inequality with $\kappa= L/\alpha$, we prove an $\Omega(\kappa)$ query lower bound for $d\gtrsim\log^2\kappa$. This shows that log-Sobolev sampling is strictly harder than strongly log-concave sampling. Our proofs construct instance-dependent tests that target samples typically pass but outputs of algorithms making few queries typically fail. For strongly log-concave targets, we embed a sequence of hidden Gaussian into high-degree tensor polynomial with smooth gates, forcing any algorithm to uncover the layers sequentially. The log-Sobolev construction hides a constant fraction of the target mass in angular caps while controlling the log-Sobolev constant via delicate estimates.
Recent pansharpening models achieve strong fusion performance on trained sensors, yet often generalize poorly to unseen sensors. Existing cross-sensor adaptation is limited by target-sensor retraining, which requires target-sensor training pairs and a dedicated training stage, and by per-image zero-shot adaptation, which is computationally expensive due to whole-network optimization for each test image. To address these problems, we propose ReTailor, a real-time sequential cross-sensor adaptation framework. Only a lightweight residual Feature Tailor is rapidly optimized under self-supervised, physics-aware constraints to correct cross-sensor shifts without modifying the well-learned fusion prior. For efficient and effective deployment, ReTailor combines content-aware patch selection, which identifies a few informative patches per image for optimization at negligible cost to improve both quality and efficiency, with rolling residual bootstrap, which inherits sensor-related knowledge across the image stream to further improve quality. Extensive experiments on cross-sensor adaptation settings show that ReTailor mitigates cross-sensor degradation both effectively and efficiently. Moreover, we compare ReTailor with Low-Rank Adaptation (LoRA), a widely used method for fine-tuning, to demonstrate the advantages of our approach. We further evaluate the core principle of ReTailor on two additional remote sensing tasks: super-resolution pansharpening and image segmentation, where it consistently improves performance. In general, ReTailor provides a highly effective and efficient strategy for deploying pansharpening models under real-world cross-sensor degradation, while also offering useful insights into managing cross-sensor degradation in other remote sensing tasks. Code will be released at https://github.com/JingZe-Liang/ReTailor .
Expert deactivation at inference time changes both token routing and expert weights, and its effect on performance depends on how these changes are implemented. We compare removal, freezing, remaining-expert renormalization, and unnormalized re-routing on identical disabled sets across five instruction-tuned checkpoints from four model families, with a base OLMoE checkpoint as an additional comparison. We develop a weight-sum model that relates the loss of expert contributions and changes in branch scale to the weight rule used during training. With half of the experts deactivated according to activation-based rankings, remaining-expert renormalization yields the highest perplexity in models trained with raw router probabilities, whereas unnormalized re-routing yields the highest perplexity in models trained with normalized weights. Perplexity ranges from 1.4 to 73 times the intact baseline when the training rule is retained, and from 14 to 28,740 times the baseline under a rule mismatch. Task outcomes vary across evaluation types: on OLMoE, GSM8K strict-match accuracy falls to zero under all four implementations. Extending the model to changes in the number of active experts yields a further prediction, supported by the OLMoE experiments: the perplexity penalty from additional renormalization increases as fewer experts are activated.
How much phonological knowledge do language models (LMs) possess about Chinese characters, and how is this knowledge represented and used? We introduce PinyinBench, a controlled benchmark covering homophones, phonological features (initials, finals, and tones), and polyphonic characters. We investigate 17 text-only and multimodal LMs through three complementary approaches: behavioral evaluation, layer-wise probing, and activation steering. Behaviorally, models demonstrate substantial knowledge of initials and finals, with a frontier model (DS-v4-flash) scoring 90%+ in homophone judgment, when two characters share no phonological features. However, its accuracy drops sharply to 72% when two characters differ only in lexical tone. Probing reveals that tone is highly decodable from embeddings and improves modestly across layers, whereas segmental information starts less decodable and improves substantially with depth. Activation steering shows that segmental representations can systematically influence generation, while tone exhibits much weaker effects. Furthermore, audio-bearing training improves phonological decodability, including tone, without corresponding improvements in steering effectiveness. Together, these findings reveal distinct representational and functional profiles for segmental and tonal information, with tonal information much harder to access and manipulate, demonstrating the necessity for combined evaluation, probing, and causal intervention for understanding linguistic knowledge in LMs.
Recent LLM-centric advances can generate attractive furnished rooms by selecting and arranging assets. Yet evaluation remains limited to specific perspectives or predefined questions, failing to reflect overall scene quality. To address this pressing need, we introduce GREP. Its core is a focus shift from defining specific questions to establishing a three-tier evaluation philosophy: basic physical validity checks whether a scene obeys physical constraints; visual coherence concerns compatibility in object scale, style, and composition; and, at the highest level, human-use logic requires object arrangements to align with everyday human habits. Guided by these principles, an evaluation agent autonomously and adaptively identifies issues from scene context, gathers evidence, and produces scores and reports. This supports scene-specific issue discovery and reliable judgments. Experiments show that (1) GREP achieves 87% agreement with human majority preferences, substantially outperforming baseline evaluators. (2) GREP reports improve scene quality through refinement, whereas score-only and no-feedback baselines show slight declines. (3) GREP suggests that as planning ability improves, recent models such as GPT-5.6 Sol can move from relying on pipelines and harnesses to challenging their guidance and constraints, but still lack the ability to resolve the resulting conflicts. Stronger models are therefore expected not only to plan well, but also to adapt to external guidance and constraints more flexibly. Project page: https://han-808.github.io/GREP/
Holistic perception for autonomous agents requires reliably segmenting and associating scene elements across time and camera views, including objects outside a fixed semantic taxonomy. Existing open-set panoptic benchmarks focus on individual images or views, while panoramic tracking benchmarks assume closed-set taxonomies. Consequently, these benchmarks do not evaluate whether unknown objects can be consistently segmented and tracked across synchronized multi-camera sequences. We introduce WayPOP, a panoramic open-set panoptic tracking benchmark built on real Waymo PVPS sequences augmented with diverse out-of-taxonomy 3D assets from Objaverse. Inserted objects are placed at fixed locations in the 3D scene and rendered using calibrated vehicle-mounted cameras as the ego vehicle and surrounding traffic move, providing temporally and cross-view consistent panoptic annotations and auxiliary LiDAR range observations. WayPOP contains approximately 670 curated assets instantiated as 980 unique unknown-object tracks, yielding 53,452 unknown-object mask annotations across 21,300 camera images. Our evaluation protocol defines a hierarchy of tasks from view-independent open-set panoptic segmentation to full panoramic open-set panoptic tracking, using known/unknown PQ and (w)STQ metrics. We benchmark representative open-set and open-vocabulary segmentation methods with temporal and cross-camera association. Our results reveal substantial limitations of current methods in truly open-set scenarios, highlighting robust unknown-object localization and identity association across time and views as major open challenges.
Modern recommender systems rely on generative retrieval techniques to predict the next item either as discrete codes or as a continuous vector. On the one hand, Semantic IDs (SIDs) give discrete models shared parameters and pretrained semantic structure, but discretizing items into hard codes discards some information from the original content embeddings. On the other hand, continuous models avoid quantization, yet typically use flat item lookup tables with no explicit parameter tying across items. We ask whether a continuous recommender can introduce shared structure without making it a discrete bottleneck. We propose CAP-Mix, a flow recommender that represents each item as a soft mixture of shared prototypes plus an item-specific vector. The assignments, prototypes, and item vectors are trained jointly, and the soft representation is retained at inference. Pretrained information is optional: SID responsibilities can serve as a prior over assignments, while a full content embedding can initialize the item-specific vector without changing the initial flat table. In matched comparisons on three datasets, CAP-Mix improves over a flat table on the two sparse Amazon datasets and yields a small gain on Steam when trained without pretrained information. Given only an offline SID, it outperforms a hard table built from the same tokenizer by 4.45-14.90% in HR@5. Given the full content embedding, it matches or improves a strong flat table while hard assignments regress on the sparse Amazon datasets. Overall, averaged across six benchmarks, CAP-Mix improves HR@5 and NDCG@5 by 6.9% and 13.6% relative to the best evaluated baseline for each dataset and metric, while delivering 1.4-161x the inference throughput of the discrete baselines in our experiments.
Continual model updating has become a common practice in the deployment of machine learning systems. However, the dynamic training behaviors give rise to new risks not sufficiently addressed by existing studies. In this paper, we present the first systematic study of temporal privacy risk in continually updated deep learning models. We formalize the notion of temporal membership in continually updated models. We then define the temporal membership inference attack, which seeks to infer whether and when individual samples were involved in model training, at both timestamp-level and interval-level granularities. To this end, we propose TMIA, a novel black-box attack that leverages bidirectional LSTMs to infer temporal membership from model outputs observed across successive updates. Through extensive experiments on three language models and three image classification models, we show that TMIA is highly effective and significantly outperforms existing baselines. Finally, we evaluate three potential defenses, revealing the trade-off between privacy protection and model utility.
Data-driven methods can recover compact equations, yet the physical dependence of their coefficients across operating conditions often remains unresolved. Dimensionless groups can explain this variation, but selecting relevant groups from the many dimensionally admissible combinations remains challenging. Here, we introduce a knowledge-guided framework for dimensionless learning, called {\pi}-former. It learns patterns of variable association and exponent assignment from a corpus of 1,288 established dimensionless groups. Under exact dimensional constraints, the model proposes interpretable basic groups whose combinations are optimized against observations. Across seven physical problems, the framework identifies predictive dimensionless coordinates within seconds. Integration with equation discovery further expresses condition-dependent coefficients through these coordinates, recovering established physical scalings in multi-condition simulations. Applied to experimental measurements of evaporation-driven wetting, the framework discovers dimensionless coordinates and uses them to construct a unified trajectory equation. The resulting model generalizes to held-out conditions across liquids and initial volumes, outperforming existing empirical models. These results establish dimensionless learning as a transferable bridge between accumulated scientific knowledge and data-driven equation discovery, enabling artificial intelligence to uncover physically meaningful laws from observations.
Algorithmic recourse identifies modifications that can change an unfavorable model prediction into a favorable one. Under predictive multiplicity, similarly performing models can disagree on individual predictions, so recourse valid for one model may fail for another. We formulate robust recourse under predictive multiplicity as a budget-constrained minimization of the worst-case validity loss across a competing set of models, which can include models with different architectures or from different hypothesis classes. We propose an oracle-efficient algorithm called ORPM and prove sufficient conditions for its convergence. We evaluate ORPM on one synthetic and five real datasets, and competing sets consist of linear, neural, mixed, and decision-tree models. Our experiments show decreasing optimization-gap bounds and high validity in many tested settings, with favorable performance against baselines designed for specific model classes or architectures. We also quantify how requiring a common action across competing models changes recourse success at a given budget and examine disparities in this success across demographic groups.
This study investigates the authorship impersonation capacity of six widely used large language models (LLMs): Gemini 3 Pro, Claude Opus, GPT 5.2, GPT 5.2 Pro, DeepSeek 3.2, and Grok 4.1 Fast. The evaluation was conducted using short product review texts selected to ensure high within author consistency in individual writing style. Two types of in context prompt were designed: a simple prompt with minimal instruction and a complex prompt incorporating explicit stylometric guidance for mimicry. Authorship mimicry was evaluated using a cosine distance based distance to training metric, supplemented by visual analyses of embedding distributions. The results indicate that authorship impersonation remained challenging for most LLMs, with Gemini 3 Pro showing the strongest apparent mimicry performance. However, subsequent overlap analysis revealed that Gemini 3 Pro extensively copied and reused sentences and phrases from the training texts, at levels far exceeding those observed among human authors. Follow up factor analyses showed that training set consistency was the most robust predictor of mimicry success across models, whereas author distinctiveness did not generalise as a reliable predictor. Global embedding visualisations further revealed a consistent macro level pattern: for most models, generated texts occupied regions of the embedding space that were largely separated from the corresponding human training clusters. This indicates limited convergence towards target author style and suggests the presence of model specific lexical and phraseological preferences. The findings highlight the importance of distinguishing genuine stylistic imitation from direct textual reuse and have implications for the forensic analysis of textual evidence involving potential LLM enabled impersonation.
Automated segmentation of post-treatment glioma from MRI is essential for accurate diagnosis and treatment planning, yet remains difficult. Surgery and chemoradiotherapy cause structural changes in brain like resection cavities, edema, and fibrosis, that alter imaging appearance and mimic tumor recurrence. Contemporary segmentation architectures attain high accuracy with two limitations. First, the bottleneck originates from the deepest encoder stage, so one representation must serve sub-regions that differ widely in size and appearance. Second, they produce the segmentation in a single forward pass with no mechanism for refinement. We propose ME^2FDiff, a single-model architecture, addressing both. An attention-conditioned spectral diffusion block refines the bottleneck. It uses the image-conditioned latent diffusion process with two processes: a spatial pre-attention gate and a spectral fusion block whose timestep-adaptive bandpass filter selects the informative frequency band at each noise level. A multiscale expert-enhanced feature block fuses the intermediate encoder scales into the bottleneck through expert-selected shared tokens, guaranteeing balanced utilization without an auxiliary loss. On the BraTS 2024 post-treatment glioma dataset, ME^2FDiff achieves the best results on every tumor sub-region among all single-model baselines (91.23% Dice, 84.52% IOU, 2.13 mm HD95 on whole-tumor) and surpasses a three-expert ensemble on both overlap metrics at roughly one-third of its inference cost. Against recent state-of-the-art methods retrained under identical conditions, it maintains the strongest performance with the fewest parameters of any competing model. These findings demonstrate that a single, compact network can absorb the specialization, usually sought through ensembling or larger architectures.
Classifier-Free Guidance is a widely used inference-time guidance rule for conditional image generation with diffusion models, which exposes a guidance scale that adjusts conditioning strength after training. This flexibility requires conditional and unconditional model evaluations at every sampling step, so an N-step trajectory takes 2N forward passes. Single-pass alternatives reduce such cost, yet most collapse CFG's two components into one opaque guided prediction, losing the separable base flow and guidance direction that support per-step control and diagnostics, even when the scale remains adjustable. This work introduces CtrlFlow, a single-pass guidance method that preserves CFG's separable base-flow and guidance-direction interface. To preserve both components at one-pass cost, CtrlFlow attaches two lightweight LoRA adapters to a frozen backbone, each adding 2.5% parameters, and predicts the base flow and guidance direction from one pass of the shared frozen backbone. Because the guidance scale multiplies the guidance direction only after the forward pass, one evaluation yields the guided velocity at any scale, so a single trained checkpoint remains adjustable at inference without retraining. Preserving two outputs introduces a training mismatch: inference amplifies guidance-direction errors by the chosen scale, while naive component-wise losses weight both outputs equally. To align training with this composed inference-time error, CtrlFlow uses a unified multi-scale distillation loss. Residual guidance errors can still persist at extreme scales, where even small guidance-direction errors are amplified by the guidance scale. To reduce this inference-time error, CtrlFlow applies scale-adaptive modulation to damp velocity-field errors and time-grid warping to concentrate solver evaluations where the trajectory changes most rapidly.