As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak attacks, with effectiveness varying across language contexts. This paper investigates the role of classical Chinese in jailbreak attacks. Owing to its conciseness and obscurity, classical Chinese can partially bypass existing safety constraints, exposing notable vulnerabilities in LLMs. Based on this observation, this paper proposes a framework, CC-BOS, for the automatic generation of classical Chinese adversarial prompts based on multi-dimensional fruit fly optimization, facilitating efficient and automated jailbreak attacks in black-box settings. Prompts are encoded into eight policy dimensions-covering role, behavior, mechanism, metaphor, expression, knowledge, trigger pattern and context; and iteratively refined via smell search, visual search, and cauchy mutation. This design enables efficient exploration of the search space, thereby enhancing the effectiveness of black-box jailbreak attacks. To enhance readability and evaluation accuracy, we further design a classical Chinese to English translation module. Extensive experiments demonstrate that effectiveness of the proposed CC-BOS, consistently outperforming state-of-the-art jailbreak attack methods.

Multimodal learning that integrates genomics and histopathology has shown strong potential in cancer diagnosis, yet its clinical translation is hindered by the limited availability of paired histology-genomics data. Knowledge distillation (KD) offers a practical solution by transferring genomic supervision into histopathology models, enabling accurate inference using histology alone. However, existing KD methods rely on batch-local alignment, which introduces instability due to limited within-batch comparisons and ultimately degrades performance. To address these limitations, we propose Momentum Memory Knowledge Distillation (MoMKD), a cross-modal distillation framework driven by a momentum-updated memory. This memory aggregates genomic and histopathology information across batches, effectively enlarging the supervisory context available to each mini-batch. Furthermore, we decouple the gradients of the genomics and histology branches, preventing genomic signals from dominating histology feature learning during training and eliminating the modality-gap issue at inference time. Extensive experiments on the TCGA-BRCA benchmark (HER2, PR, and ODX classification tasks) and an independent in-house testing dataset demonstrate that MoMKD consistently outperforms state-of-the-art MIL and multimodal KD baselines, delivering strong performance and generalization under histology-only inference. Overall, MoMKD establishes a robust and generalizable knowledge distillation paradigm for computational pathology.

Diffusion models are a strong backbone for visual generation, but their inherently sequential denoising process leads to slow inference. Previous methods accelerate sampling by caching and reusing intermediate outputs based on feature distances between adjacent timesteps. However, existing caching strategies typically rely on raw feature differences that entangle content and noise. This design overlooks spectral evolution, where low-frequency structure appears early and high-frequency detail is refined later. We introduce Spectral-Evolution-Aware Cache (SeaCache), a training-free cache schedule that bases reuse decisions on a spectrally aligned representation. Through theoretical and empirical analysis, we derive a Spectral-Evolution-Aware (SEA) filter that preserves content-relevant components while suppressing noise. Employing SEA-filtered input features to estimate redundancy leads to dynamic schedules that adapt to content while respecting the spectral priors underlying the diffusion model. Extensive experiments on diverse visual generative models and the baselines show that SeaCache achieves state-of-the-art latency-quality trade-offs.

Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional fields, yet they face a critical fidelity-speed dilemma: deep MLPs suffer from high inference cost, while efficient embedding-based models lack sufficient expressiveness. To resolve this, we propose the Decoupled Representation Refinement (DRR) architectural paradigm. DRR leverages a deep refiner network, alongside non-parametric transformations, in a one-time offline process to encode rich representations into a compact and efficient embedding structure. This approach decouples slow neural networks with high representational capacity from the fast inference path. We introduce DRR-Net, a simple network that validates this paradigm, and a novel data augmentation strategy, Variational Pairs (VP) for improving INRs under complex tasks like high-dimensional surrogate modeling. Experiments on several ensemble simulation datasets demonstrate that our approach achieves state-of-the-art fidelity, while being up to 27$\times$ faster at inference than high-fidelity baselines and remaining competitive with the fastest models. The DRR paradigm offers an effective strategy for building powerful and practical neural field surrogates and INRs in broader applications, with a minimal compromise between speed and quality.

When audio and text conflict, speech-enabled language models follow text far more often than they do when arbitrating between two conflicting text sources, even under explicit instructions to trust the audio. We introduce ALME (Audio-LLM Modality Evaluation), a dataset of 57,602 controlled audio-text conflict stimuli across eight languages, together with Text Dominance Ratio (TDR), which measures how often a model follows conflicting text when instructed to follow audio. Gemini 2.0 Flash and GPT-4o show TDR 10--26$\times$ higher than a baseline that replaces audio with its transcript under otherwise identical conditions (Gemini 2.0 Flash: 16.6% vs. 1.6%; GPT-4o: 23.2% vs. 0.9%). These results suggest that text dominance reflects not only information content, but also an asymmetry in arbitration accessibility, i.e., how easily the model can use competing representations at decision time. Framing the transcript as deliberately corrupted reduces TDR by 80%, whereas forcing explicit transcription increases it by 14%. A fine-tuning ablation further suggests that arbitration behavior depends more on LLM reasoning than on the audio input path alone. Across four audio-LLMs, we observe the same qualitative pattern with substantial cross-model and cross-linguistic variation.

Robust navigation in changing marine environments requires autonomous systems capable of perceiving, reasoning, and acting under uncertainty. This study introduces a hybrid risk-aware navigation architecture that integrates probabilistic modeling of obstacles along the vehicle path with smooth trajectory optimization for autonomous surface vessels. The system constructs probabilistic risk maps that capture both obstacle proximity and the behavior of dynamic objects. A risk-biased Rapidly Exploring Random Tree (RRT) planner leverages these maps to generate collision-free paths, which are subsequently refined using B-spline algorithms to ensure trajectory continuity. Three distinct RRT* rewiring modes are implemented based on the cost function: minimizing the path length, minimizing risk, and optimizing a combination of the path length and total risk. The framework is evaluated in experimental scenarios containing both static and dynamic obstacles. The results demonstrate the system's ability to navigate safely, maintain smooth trajectories, and dynamically adapt to changing environmental risks. Compared with conventional LIDAR or vision-only navigation approaches, the proposed method shows improvements in operational safety and autonomy, establishing it as a promising solution for risk-aware autonomous vehicle missions in uncertain and dynamic environments.

Active learning (AL) is a machine learning (ML) approach that strategically selects the most informative samples for annotation during training, aiming to minimize annotation costs. This strategy not only reduces labeling expenses but also results in energy savings during neural network training, thereby enhancing both data and energy efficiency. In this paper, we implement and evaluate various state-of-the-art acquisition functions, analyzing their accuracy and computational costs, while discussing the advantages and disadvantages of each method. Our findings reveal that representativity-based acquisition functions effectively explore the dataset but do not prioritize boundary decisions, whereas uncertainty-based acquisition functions focus on refining boundary decisions already identified by the neural network. This trade-off is known as the exploration-exploitation dilemma. To address this dilemma, we introduce six aggregation structures: series, parallel, hybrid, adaptive feedback, random exploration, and annealing exploration. Our aggregated acquisition functions alleviate common AL pathologies such as batch mode inefficiency and the cold start problem. Additionally, we focus on balancing accuracy and energy consumption, contributing to the development of more sustainable, energy-aware artificial intelligence (AI). We evaluate our proposed structures on various models and datasets. Our results demonstrate the potential of these structures to reduce computational costs while maintaining or even improving accuracy. Innovative aggregation approaches, such as alternating between acquisition functions such as BALD and BADGE, have shown robust results. Sequentially running functions like $K$-Centers followed by BALD has achieved the same performance goals with up to 12\% fewer samples, while reducing the acquisition cost by almost half.

Humans acquire semantic object representations from egocentric visual streams with minimal supervision, but the underlying mechanisms remain unclear. Importantly, the visual system only processes the center of its field of view with high resolution and it learns similar representations for visual inputs occurring close in time. This emphasizes slowly changing information around gaze locations. This study investigates the role of central vision and slowness learning in the formation of semantic object representations from human-like visual experience. We simulate five months of human-like visual experience using the Ego4D dataset and a state-of-the-art gaze prediction model. We extract image crops around predicted gaze locations to train a time-contrastive Self-Supervised Learning model. Our results show that exploiting temporal slowness when learning from central visual field experience improves the encoding of different facets of object semantics. Specifically, focusing on central vision strengthens the extraction of foreground object features, while considering temporal slowness, especially in conjunction with eye movements, allows the model to encode broader semantic information about objects. These findings provide new insights into the mechanisms by which humans may develop semantic object representations from natural visual experience. Our code will be made public upon acceptance. Code is available at https://github.com/t9s9/central-vision-ssl.

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing latency and degrading inference performance, making managing tool-use behavior challenging. In this work, we conduct entropy-based pilot experiments and observe a strong positive correlation between entropy reduction and high-quality tool calls. Building on this finding, we propose using entropy reduction as a supervisory signal and design two reward strategies to address the differing needs of optimizing tool-use behavior. Sparse outcome rewards provide coarse, trajectory-level guidance to improve efficiency, while dense process rewards offer fine-grained supervision to enhance performance. Experiments across diverse domains show that both reward designs improve tool-use behavior: the former reduces tool calls by 72.07% compared to the average of baselines, while the latter improves performance by 22.27%. These results position entropy reduction as a key mechanism for enhancing tool-use behavior, enabling agents to be more adaptive in real-world applications.

General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in continual parameter-efficient tuning (PET) of pretrained models show promise, they typically rely on multiple training epochs and explicit task cues, limiting their effectiveness in GCL scenarios. Moreover, existing methods often lack targeted design and fail to address two fundamental challenges in continual PET: how to allocate expert parameters to evolving data distributions, and how to improve their representational capacity under limited supervision. Inspired by the fruit fly's hierarchical memory system characterized by sparse expansion and modular ensembles, we propose FlyPrompt, a brain-inspired framework that decomposes GCL into two subproblems: expert routing and expert competence improvement. FlyPrompt introduces a randomly expanded analytic router for instance-level expert activation and a temporal ensemble of output heads to dynamically adapt decision boundaries over time. Extensive theoretical and empirical evaluations demonstrate FlyPrompt's superior performance, achieving up to 11.23%, 12.43%, and 7.62% gains over state-of-the-art baselines on CIFAR-100, ImageNet-R, and CUB-200, respectively. Our source code is available at https://github.com/AnAppleCore/FlyGCL.

Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and often produce hallucinations. Hallucinations denote generated content that is grammatically and syntactically coherent, yet bears no match or direct relevance to visual input. To address this problem, we propose Residual Decoding (ResDec). It is a novel training-free method that uses historical information to aid decoding. The method relies on the internal implicit reasoning mechanism and token logits evolution mechanism of LVLMs to correct biases. Extensive experiments demonstrate that ResDec effectively suppresses hallucinations induced by language priors, significantly improves visual grounding, and reduces object hallucinations. In addition to mitigating hallucinations, ResDec also performs exceptionally well on comprehensive LVLM benchmarks, highlighting its broad applicability.

For applications of machine learning in critical decisions, explainability is a primary concern, and often a regulatory requirement. Local linear methods for generating explanations, such as LIME and SHAP, have been criticized for being unstable near decision boundaries. In this paper, we explain that such concerns reflect a misunderstanding of the problem. The forecast uncertainty is high at decision boundaries, so consequently, the explanatory instability is high. The correct approach is to change the sequence of events and questions being asked. Nonlinear models can be highly predictive in some regions while having little or no predictability in others. Therefore, the first question is whether a usable forecast exists. When there is a forecast with low enough uncertainty to be useful, an explanation can be sought via a local linear approximation. In such cases, the explanatory instability is correspondingly low. When no usable forecast exists, the decision must fall to a simpler overall model such as traditional logistic regression. Additionally, these results show that some methods that purport to be explainable everywhere, such as ReLU networks or any piecewise linear model, have only an illusory explainability, because the forecast uncertainty at the segment boundaries is too high to be useful. Explaining an unusable forecast is pointless.

Despite rapid advances in autonomous AI scientists powered by language models, generating publication-ready illustrations remains a labor-intensive bottleneck in the research workflow. To lift this burden, we introduce PaperBanana, an agentic framework for automated generation of publication-ready academic illustrations. Powered by state-of-the-art VLMs and image generation models, PaperBanana orchestrates specialized agents to retrieve references, plan content and style, render images, and iteratively refine via self-critique. To rigorously evaluate our framework, we introduce PaperBananaBench, comprising 292 test cases for methodology diagrams curated from NeurIPS 2025 publications, covering diverse research domains and illustration styles. Comprehensive experiments demonstrate that PaperBanana consistently outperforms leading baselines in faithfulness, conciseness, readability, and aesthetics. We further show that our method effectively extends to the generation of high-quality statistical plots. Collectively, PaperBanana paves the way for the automated generation of publication-ready illustrations.

Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by ``reasoning-then-tool-call'' for visual and textual search engines to obtain substantial gains on tasks requiring extensive factual information. However, these approaches typically define multimodal search in a naive setting, assuming that a single full-level or entity-level image query and few text query suffices to retrieve the key evidence needed to answer the question, which is unrealistic in real-world scenarios with substantial visual noise. Moreover, they are often limited in the reasoning depth and search breadth, making it difficult to solve complex questions that require aggregating evidence from diverse visual and textual sources. Building on this, we propose Vision-DeepResearch, which proposes one new multimodal deep-research paradigm, i.e., performs multi-turn, multi-entity and multi-scale visual and textual search to robustly hit real-world search engines under heavy noise. Our Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions, while internalizing deep-research capabilities into the MLLM via cold-start supervision and RL training, resulting in a strong end-to-end multimodal deep-research MLLM. It substantially outperforming existing multimodal deep-research MLLMs, and workflows built on strong closed-source foundation model such as GPT-5, Gemini-2.5-pro and Claude-4-Sonnet. The code will be released in https://github.com/Osilly/Vision-DeepResearch.

An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance factors. As a result, different frames contribute unequally to the final utterance-level speaker representation for Automatic Speaker Verification systems. To address this issue, we propose to estimate the inherent uncertainty of each frame and assign adaptive weights accordingly, where frames with higher uncertainty receive lower attention. Based on this idea, we present U3-xi, a comprehensive framework designed to produce more reliable and interpretable uncertainty estimates for speaker embeddings. Specifically, we introduce several strategies for uncertainty supervision. First, we propose speaker-level uncertainty supervision via a Stochastic Variance Loss, where the distance between an utterance embedding and its corresponding speaker centroid serves as a pseudo ground truth for uncertainty learning. Second, we incorporate global-level uncertainty supervision by injecting the predicted uncertainty into the sof tmax scale during training. This adaptive scaling mechanism adjusts the sharpness of the decision boundary according to sample difficulty, providing global guidance. Third, we redesign the uncertainty estimation module by integrating a Transformer encoder with multi-view self-attention, enabling the model to capture rich local and long-range temporal dependencies. Comprehensive experiments demonstrate that U3-xi is model-agnostic and can be seamlessly applied to various speaker encoders. In particular, when applied to ECAPA-TDNN, it achieves 21.1% and 15.57% relative improvements on the VoxCeleb1 test sets in terms of EER and minDCF, respectively.

We present the Input-Connected Multilayer Perceptron (IC-MLP), a feedforward neural network architecture in which each hidden neuron receives, in addition to the outputs of the preceding layer, a direct affine connection from the raw input. We first study this architecture in the univariate setting and give an explicit and systematic description of IC-MLPs with an arbitrary finite number of hidden layers, including iterated formulas for the network functions. In this setting, we prove a universal approximation theorem showing that deep IC-MLPs can approximate any continuous function on a closed interval of the real line if and only if the activation function is nonlinear. We then extend the analysis to vector-valued inputs and establish a corresponding universal approximation theorem for continuous functions on compact subsets of $\mathbb{R}^n$.

Long video understanding presents significant challenges for vision-language models due to extremely long context windows. Existing solutions relying on naive chunking strategies with retrieval-augmented generation, typically suffer from information fragmentation and a loss of global coherence. We present HAVEN, a unified framework for long-video understanding that enables coherent and comprehensive reasoning by integrating audiovisual entity cohesion and hierarchical video indexing with agentic search. First, we preserve semantic consistency by integrating entity-level representations across visual and auditory streams, while organizing content into a structured hierarchy spanning global summary, scene, segment, and entity levels. Then we employ an agentic search mechanism to enable dynamic retrieval and reasoning across these layers, facilitating coherent narrative reconstruction and fine-grained entity tracking. Extensive experiments demonstrate that our method achieves good temporal coherence, entity consistency, and retrieval efficiency, establishing a new state-of-the-art with an overall accuracy of 84.1% on LVBench. Notably, it achieves outstanding performance in the challenging reasoning category, reaching 80.1%. These results highlight the effectiveness of structured, multimodal reasoning for comprehensive and context-consistent understanding of long-form videos.

Fairness and privacy are two vital pillars of trustworthy machine learning. Despite extensive research on these individual topics, their relationship has received significantly less attention. In this paper, we utilize an information-theoretic measure Chernoff Information to characterize the fundamental trade-off between fairness, privacy, and accuracy, as induced by the input data distribution. We first propose Chernoff Difference, a notion of data fairness, along with its noisy variant, Noisy Chernoff Difference, which allows us to analyze both fairness and privacy simultaneously. Through simple Gaussian examples, we show that Noisy Chernoff Difference exhibits three qualitatively distinct behaviors depending on the underlying data distribution. To extend this analysis beyond synthetic settings, we develop the Chernoff Information Neural Estimator (CINE), the first neural network-based estimator of Chernoff Information for unknown distributions. We apply CINE to analyze the Noisy Chernoff Difference on real-world datasets. Together, this work fills a critical gap in the literature by providing a principled, data-dependent characterization of the fairness-privacy interaction.

Large Language Models (LLMs) are increasingly integrated into vehicle-based digital assistants, where unsafe, ambiguous, or legally incorrect responses can lead to serious safety, ethical, and regulatory consequences. Despite growing interest in LLM safety, existing taxonomies and evaluation frameworks remain largely general-purpose and fail to capture the domain-specific risks inherent to real-world driving scenarios. In this paper, we introduce DriveSafe, a hierarchical, four-level risk taxonomy designed to systematically characterize safety-critical failure modes of LLM-based driving assistants. The taxonomy comprises 129 fine-grained atomic risk categories spanning technical, legal, societal, and ethical dimensions, grounded in real-world driving regulations and safety principles and reviewed by domain experts. To validate the safety relevance and realism of the constructed prompts, we evaluate their refusal behavior across six widely deployed LLMs. Our analysis shows that the evaluated models often fail to appropriately refuse unsafe or non-compliant driving-related queries, underscoring the limitations of general-purpose safety alignment in driving contexts.

Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for privacy preservation degrades gradient quality. Although second-order optimization can accelerate training, existing approaches for DP-FL face significant scalability limitations: Newton-type methods require clients to compute Hessians, while feature covariance methods scale poorly with model dimension. We propose DP-FedSOFIM, a simple and scalable second-order optimization method for DP-FL. The method constructs an online regularized proxy for the Fisher information matrix at the server using only privatized aggregated gradients, capturing useful curvature information without requiring Hessian computations or feature covariance estimation. Efficient rank-one updates based on the Sherman-Morrison formula enable communication costs proportional to the model size and require only O(d) client-side memory. Because all curvature and preconditioning operations are performed at the server on already privatized gradients, DP-FedSOFIM introduces no additional privacy cost beyond the underlying privatized gradient release mechanism. Experiments on CIFAR-10 and PathMNIST show that DP-FedSOFIM converges faster and consistently achieves higher accuracy than DP-FedGD, DP-SCAFFOLD, and DP-FedFC across a range of privacy budgets, with particularly pronounced gains under stringent privacy constraints.

Achieving agile and generalized legged locomotion across terrains requires tight integration of perception and control, especially under occlusions and sparse footholds. Existing methods have demonstrated agility on parkour courses but often rely on end-to-end sensorimotor models with limited generalization and interpretability. By contrast, methods targeting generalized locomotion typically exhibit limited agility and struggle with visual occlusions. We introduce AME-2, a unified reinforcement learning (RL) framework for agile and generalized locomotion that incorporates a novel attention-based map encoder in the control policy. This encoder extracts local and global mapping features and uses attention mechanisms to focus on salient regions, producing an interpretable and generalized embedding for RL-based control. We further propose a learning-based mapping pipeline that provides fast, uncertainty-aware terrain representations robust to noise and occlusions, serving as policy inputs. It uses neural networks to convert depth observations into local elevations with uncertainties, and fuses them with odometry. The pipeline also integrates with parallel simulation so that we can train controllers with online mapping, aiding sim-to-real transfer. We validate AME-2 with the proposed mapping pipeline on a quadruped and a biped robot, and the resulting controllers demonstrate strong agility and generalization to unseen terrains in simulation and in real-world experiments.

Audio-driven visual dubbing aims to synchronize a video's lip movements with new speech but is fundamentally challenged by the lack of ideal training data: paired videos differing only in lip motion. Existing methods circumvent this via mask-based inpainting. However, masking inevitably destroys spatiotemporal context, leading to identity drift and poor robustness (e.g., to occlusions), while also inducing lip-shape leakage that degrades lip sync. To bridge this gap, we propose X-Dub, a novel two-stage generative bootstrapping framework leveraging powerful Diffusion Transformers to unlock mask-free dubbing. Our core insight is to repurpose a mask-based inpainting model exclusively as a dedicated data generator to synthesize scalable, high-fidelity pseudo-paired data, which is subsequently utilized to train and bootstrap a robust, mask-free editing model as the final video dubber. The final dubber is liberated from masking artifacts and leverages the complete video input for high-fidelity inference. We further introduce timestep-adaptive multi-phase learning to disentangle conflicting objectives (structure, lip motion, and texture) across diffusion phases, facilitating stable convergence and advanced editing quality. Additionally, we present X-DubBench, a benchmark for diverse scenarios. Extensive experiments demonstrate that our method achieves state-of-the-art performance with superior lip sync, visual quality, and robustness.

Vision-Language-Action (VLA) models align vision and language with embodied control, but their object referring ability remains limited when relying solely on text prompt, especially in cluttered or out-of-distribution (OOD) scenes. In this study, we introduce the Point-VLA, a plug-and-play policy that augments language instructions with explicit visual cues (e.g., bounding boxes) to resolve referential ambiguity and enable precise object-level grounding. To efficiently scale visually grounded datasets, we further develop an automatic data annotation pipeline requiring minimal human effort. We evaluate Point-VLA on diverse real-world referring tasks and observe consistently stronger performance than text-only instruction VLAs, particularly in cluttered or unseen-object scenarios, with robust generalization. These results demonstrate that Point-VLA effectively resolves object referring ambiguity through pixel-level visual grounding, achieving more generalizable embodied control.

Robots must balance compliance with safety and social expectations as blind obedience can cause harm, while over-refusal erodes trust. Existing safe reinforcement learning (RL) benchmarks emphasize physical hazards, while human-robot interaction trust studies are small-scale and hard to reproduce. We present the Empathic Ethical Disobedience (EED) Gym, a standardized testbed that jointly evaluates refusal safety and social acceptability. Agents weigh risk, affect, and trust when choosing to comply, refuse (with or without explanation), clarify, or propose safer alternatives. EED Gym provides different scenarios, multiple persona profiles, and metrics for safety, calibration, and refusals, with trust and blame models grounded in a vignette study. Using EED Gym, we find that action masking eliminates unsafe compliance, while explanatory refusals help sustain trust. Constructive styles are rated most trustworthy, empathic styles -- most empathic, and safe RL methods improve robustness but also make agents more prone to overly cautious behavior. We release code, configurations, and reference policies to enable reproducible evaluation and systematic human-robot interaction research on refusal and trust. At submission time, we include an anonymized reproducibility package with code and configs, and we commit to open-sourcing the full repository after the paper is accepted.

Training data detection is critical for enforcing copyright and data licensing, as Large Language Models (LLM) are trained on massive text corpora scraped from the internet. We present SPECTRA, a watermarking approach that makes training data reliably detectable even when it comprises less than 0.001% of the training corpus. SPECTRA works by paraphrasing text using an LLM and assigning a score based on how likely each paraphrase is, according to a separate scoring model. A paraphrase is chosen so that its score closely matches that of the original text, to avoid introducing any distribution shifts. To test whether a suspect model has been trained on the watermarked data, we compare its token probabilities against those of the scoring model. We demonstrate that SPECTRA achieves a consistent p-value gap of over nine orders of magnitude when detecting data used for training versus data not used for training, which is greater than all baselines tested. SPECTRA equips data owners with a scalable, deploy-before-release watermark that survives even large-scale LLM training.

Intraoperative hypotension (IOH) poses significant surgical risks, but accurate prediction remains challenging due to patient-specific variability. While test-time adaptation (TTA) offers a promising approach for personalized prediction, the rarity of IOH events often leads to unreliable test-time training. To address this, we propose CSA-TTA, a novel Cross-Sample Augmented Test-Time Adaptation framework that enhances training by incorporating hypotension events from other individuals. Specifically, we first construct a cross-sample bank by segmenting historical data into hypotensive and non-hypotensive samples. Then, we introduce a coarse-to-fine retrieval strategy for building test-time training data: we initially apply K-Shape clustering to identify representative cluster centers and subsequently retrieve the top-K semantically similar samples based on the current patient signal. Additionally, we integrate both self-supervised masked reconstruction and retrospective sequence forecasting signals during training to enhance model adaptability to rapid and subtle intraoperative dynamics. We evaluate the proposed CSA-TTA on both the VitalDB dataset and a real-world in-hospital dataset by integrating it with state-of-the-art time series forecasting models, including TimesFM and UniTS. CSA-TTA consistently enhances performance across settings-for instance, on VitalDB, it improves Recall and F1 scores by +1.33% and +1.13%, respectively, under fine-tuning, and by +7.46% and +5.07% in zero-shot scenarios-demonstrating strong robustness and generalization.

While Temporal Logic provides a rigorous verification framework for robotics, it typically operates on trajectory-level signals and does not natively represent the object-centric geometric relations that are central to manipulation. Spatio-Temporal Logic (SpaTiaL) overcomes this by explicitly capturing geometric spatial requirements, making it a natural formalism for manipulation-task verification. Consequently, translating natural language (NL) into verifiable SpaTiaL specifications is a critical objective. Yet, existing NL-to-Logic methods treat specifications as flat sequences, entangling nested temporal scopes with spatial relations and causing performance to degrade sharply under deep nesting. We propose NL2SpaTiaL, a framework modeling specifications as Hierarchical Logical Trees (HLT). By generating formulas as structured HLTs in a single shot, our approach decouples semantic parsing from syntactic rendering, aligning with human compositional spatial reasoning. To support this, we construct, to the best of our knowledge, the first NL-to-SpaTiaL dataset with explicit hierarchical supervision via a logic-first synthesis pipeline. Experiments with open-weight LLMs demonstrate that our HLT formulation significantly outperforms flat-generation baselines across various logical depths. These results show that explicit HLT structure is critical for scalable NL-to-SpaTiaL translation, ultimately enabling a rigorous ``generate-and-test'' paradigm for verifying candidate trajectories in language-conditioned robotics. Project website: https://sites.google.com/view/nl2spatial

With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding tasks, failing to achieve a comprehensive and multi-grained video perception. To bridge this gap, we introduce UFVideo, the first Video LLM with unified multi-grained cooperative understanding capabilities. Specifically, we design unified visual-language guided alignment to flexibly handle video understanding across global, pixel and temporal scales within a single model. UFVideo dynamically encodes the visual and text inputs of different tasks and generates the textual response, temporal localization, or grounded mask. Additionally, to evaluate challenging multi-grained video understanding tasks, we construct the UFVideo-Bench consisting of three distinct collaborative tasks within the scales, which demonstrates UFVideo's flexibility and advantages over GPT-4o. Furthermore, we validate the effectiveness of our model across 9 public benchmarks covering various common video understanding tasks, providing valuable insights for future Video LLMs.

Video Motion Magnification (VMM) amplifies subtle macroscopic motions to a perceptible level. Recently, existing mainstream Eulerian approaches address amplification-induced noise via decoupling representation learning such as texture, shape and frequency schemes, but they still struggle to mitigate the interference of photon noise on true micro-motion when motion displacements are very small. We propose GeoDiffMM, a novel diffusion-based Lagrangian VMM framework conditioned on optical flow as a geometric cue, enabling structurally consistent motion magnification. Specifically, we design a Noise-Free Optical Flow Augmentation strategy that synthesizes diverse nonrigid motion fields without photon noise as supervision, helping the model learn more accurate geometry-aware optical flow and generalize better. Next, we develop a Diffusion Motion Magnifier that conditions the denoising process on (i) optical flow as a geometry prior and (ii) a learnable magnification factor controlling magnitude, thereby selectively amplifying motion components consistent with scene semantics and structure. Finally, we perform Flow-based Video Synthesis to map the amplified motion back to the image domain with high fidelity. Extensive experiments on real and synthetic datasets show that GeoDiffMM outperforms state-of-the-art methods and significantly improves motion magnification.

Rigorous evaluation of large language models (LLMs) relies on comparing models by the prevalence of desirable or undesirable behaviors, such as task pass rates or policy violations. These prevalence estimates are produced by a classifier, either an LLM-as-a-judge or human annotators, making the choice of classifier central to trustworthy evaluation. Common metrics used for this choice, such as Accuracy, Precision, and F1, are sensitive to class imbalance and to arbitrary choices of positive class, and can favor judges that distort prevalence estimates. We show that Youden's $J$ statistic is theoretically aligned with choosing the best judge to compare models, and that Balanced Accuracy is an equivalent linear transformation of $J$. Through both analytical arguments and empirical examples and simulations, we demonstrate how selecting judges using Balanced Accuracy leads to better, more robust classifier selection.