Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity but a consequence of architectural necessity: transformers communicate information through linear interfaces (attention OV circuits, unembedding matrices), and any semantic feature decoded through such an interface must occupy a context-invariant linear subspace. We formalize this as the \emph{Invariant Subspace Necessity} theorem and derive the \emph{Self-Reference Property}: tokens directly provide the geometric direction for their associated features, enabling zero-shot identification of semantic structure without labeled data or learned probes. Empirical validation in eight classification tasks and four model families confirms the alignment between class tokens and semantically related instances. Our framework provides \textbf{a principled architectural explanation} for why linear interpretability methods work, unifying linear probes and sparse autoencoders.

Recent studies show that text-to-image models often fail to generate geographically representative images, raising concerns about the representativeness of their training data and motivating the question: which parts of the world do these training examples come from? We geographically profile large-scale multimodal datasets by mapping image-caption pairs to countries based on location information extracted from captions using LLMs. Studying English captions from three widely used datasets (Re-LAION, DataComp1B, and Conceptual Captions) across $20$ common entities (e.g., house, flag), we find that the United States, the United Kingdom, and Canada account for $48.0\%$ of samples, while South American and African countries are severely under-represented with only $1.8\%$ and $3.8\%$ of images, respectively. We observe a strong correlation between a country's GDP and its representation in the data ($ρ= 0.82$). Examining non-English subsets for $4$ languages from the Re-LAION dataset, we find that representation skews heavily toward countries where these languages are predominantly spoken. Additionally, we find that higher representation does not necessarily translate to greater visual or semantic diversity. Finally, analyzing country-specific images generated by Stable Diffusion v1.3 trained on Re-LAION, we show that while generations appear realistic, they are severely limited in their coverage compared to real-world images.

The possibility to create reactive robot programs faster without the need for extensively trained programmers is becoming increasingly important. So far, it has not been explored how various techniques for creating Behavior Tree (BT) program representations could be combined with complete graphical user interfaces (GUIs) to allow a human user to validate and edit trees suggested by automated methods. In this paper, we introduce BEhavior TRee GUI (BETR-GUI) for creating BTs with the help of an AI assistant that combines methods using large language models, planning, genetic programming, and Bayesian optimization with a drag-and-drop editor. A user study with 60 participants shows that by combining different assistive methods, BETR-GUI enables users to perform better at solving the robot programming tasks. The results also show that humans using the full variant of BETR-GUI perform better than the AI assistant running on its own.

Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these burdens by learning a diverse repertoire of useful skills driven by intrinsic motivation. However, existing methods exhibit two key limitations: they typically rely on a single policy to master a versatile repertoire of behaviors without modeling the shared structure or distinctions among them, which results in low learning efficiency; moreover, they are susceptible to reward hacking, where the reward signal increases and converges rapidly while the learned skills display insufficient actual diversity. In this work, we introduce an Orthogonal Mixture-of-Experts (OMoE) architecture that prevents diverse behaviors from collapsing into overlapping representations, enabling a single policy to master a wide spectrum of locomotion skills. In addition, we design a multi-discriminator framework in which different discriminators operate on distinct observation spaces, effectively mitigating reward hacking. We evaluated our method on the 12-DOF Unitree A1 quadruped robot, demonstrating a diverse set of locomotion skills. Our experiments demonstrate that the proposed framework boosts training efficiency and yields an 18.3\% expansion in state-space coverage compared to the baseline.

Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to capture temporal dynamics and physical laws. We propose NavDreamer, a video-based framework for 3D navigation that leverages generative video models as a universal interface between language instructions and navigation trajectories. Our main hypothesis is that video's ability to encode spatiotemporal information and physical dynamics, combined with internet-scale availability, enables strong zero-shot generalization in navigation. To mitigate the stochasticity of generative predictions, we introduce a sampling-based optimization method that utilizes a VLM for trajectory scoring and selection. An inverse dynamics model is employed to decode executable waypoints from generated video plans for navigation. To systematically evaluate this paradigm in several video model backbones, we introduce a comprehensive benchmark covering object navigation, precise navigation, spatial grounding, language control, and scene reasoning. Extensive experiments demonstrate robust generalization across novel objects and unseen environments, with ablation studies revealing that navigation's high-level decision-making nature makes it particularly suited for video-based planning.

In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments. Previous multi-task work has mostly relied on knowledge of the mapping between raw observations and symbols appearing in the formulae. We drop this unrealistic assumption by jointly training a multi-task policy and a symbol grounder with the same experience. The symbol grounder is trained only from raw observations and sparse rewards via Neural Reward Machines in a semi-supervised fashion. Experiments on vision-based environments show that our method achieves performance comparable to using the true symbol grounding and significantly outperforms state-of-the-art methods for sub-symbolic environments.

Lexical Semantic Change (LSC) is the phenomenon in which the meaning of a word change over time. Most studies on LSC focus on improving the performance of estimating the degree of LSC, however, it is often difficult to interpret how the meaning of a word change. Enhancing the interpretability of LSC is a significant challenge as it could lead to novel insights in this field. To tackle this challenge, we propose a method to map the semantic space of contextualized embeddings of words obtained by a pre-trained language model to a neurobiological feature space. In the neurobiological feature space, each dimension corresponds to a primitive feature of words, and its value represents the intensity of that feature. This enables humans to interpret LSC systematically. When employed for the estimation of the degree of LSC, our method demonstrates superior performance in comparison to the majority of the previous methods. In addition, given the high interpretability of the proposed method, several analyses on LSC are carried out. The results demonstrate that our method not only discovers interesting types of LSC that have been overlooked in previous studies but also effectively searches for words with specific types of LSC.

Understanding the reliability of natural language generation is critical for deploying foundation models in security-sensitive domains. While certified poisoning defenses provide provable robustness bounds for classification tasks, they are fundamentally ill-equipped for autoregressive generation: they cannot handle sequential predictions or the exponentially large output space of language models. To establish a framework for certified natural language generation, we formalize two security properties: stability (robustness to any change in generation) and validity (robustness to targeted, harmful changes in generation). We introduce Targeted Partition Aggregation (TPA), the first algorithm to certify validity/targeted attacks by computing the minimum poisoning budget needed to induce a specific harmful class, token, or phrase. Further, we extend TPA to provide tighter guarantees for multi-turn generations using mixed integer linear programming (MILP). Empirically, we demonstrate TPA's effectiveness across diverse settings including: certifying validity of agent tool-calling when adversaries modify up to 0.5% of the dataset and certifying 8-token stability horizons in preference-based alignment. Though inference-time latency remains an open challenge, our contributions enable certified deployment of language models in security-critical applications.

Audio-driven talking head generation is a core component of digital avatars, and 3D Gaussian Splatting has shown strong performance in real-time rendering of high-fidelity talking heads. However, achieving precise control over fine-grained facial movements remains a significant challenge, particularly due to lip-synchronization inaccuracies and facial jitter, both of which can contribute to the uncanny valley effect. To address these challenges, we propose Fine-Grained 3D Gaussian Splatting (FG-3DGS), a novel framework that enables temporally consistent and high-fidelity talking head generation. Our method introduces a frequency-aware disentanglement strategy to explicitly model facial regions based on their motion characteristics. Low-frequency regions, such as the cheeks, nose, and forehead, are jointly modeled using a standard MLP, while high-frequency regions, including the eyes and mouth, are captured separately using a dedicated network guided by facial area masks. The predicted motion dynamics, represented as Gaussian deltas, are applied to the static Gaussians to generate the final head frames, which are rendered via a rasterizer using frame-specific camera parameters. Additionally, a high-frequency-refined post-rendering alignment mechanism, learned from large-scale audio-video pairs by a pretrained model, is incorporated to enhance per-frame generation and achieve more accurate lip synchronization. Extensive experiments on widely used datasets for talking head generation demonstrate that our method outperforms recent state-of-the-art approaches in producing high-fidelity, lip-synced talking head videos.

Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement learning models remains challenging. As one of the most successful deep reinforcement-learning algorithm, the Proximal Policy Optimization algorithm (PPO) clips the policy gradient within a conservative on-policy updates, which ensures reliable and stable policy improvement. However, this training pattern may sacrifice sample efficiency. On the other hand, off-policy methods make more adequate use of data through sample reuse, though at the cost of increased the estimation variance and bias. To leverage the advantages of both, in this paper, we propose a new PPO variant based on the stability guarantee from conservative on-policy iteration with a more efficient off-policy data utilization. Specifically, we first derive an extended off-policy improvement from an expectation form of generalized policy improvement lower bound. Then, we extend the clipping mechanism with segmented exponential functions for a suitable surrogate objective function. Third, the trajectories generated by the past $M$ policies are organized in the replay buffer for off-policy training. We refer to this method as Extended Off-policy Proximal Policy Optimization (ExO-PPO). Compared with PPO and some other state-of-the-art variants, we demonstrate an improved performance of ExO-PPO with balanced sample efficiency and stability on varied tasks in the empirical experiments.

While Vision-Language-Action (VLA) models show strong promise for generalist robot control, it remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics, where training data is inherently heterogeneous across embodiments, sensors, and action spaces. We present a systematic, controlled study of VLA scaling that revisits core training choices for pretraining across diverse robots. Using a representative VLA framework that combines a vision-language backbone with flow-matching, we ablate key design decisions under matched conditions and evaluate in extensive simulation and real-robot experiments. To improve the reliability of real-world results, we introduce a Grouped Blind Ensemble protocol that blinds operators to model identity and separates policy execution from outcome judgment, reducing experimenter bias. Our analysis targets three dimensions of VLA scaling. (1) Physical alignment: we show that a unified end-effector (EEF)-relative action representation is critical for robust cross-embodiment transfer. (2) Embodiment mixture: we find that naively pooling heterogeneous robot datasets often induces negative transfer rather than gains, underscoring the fragility of indiscriminate data scaling. (3) Training regularization: we observe that intuitive strategies, such as sensory dropout and multi-stage fine-tuning, do not consistently improve performance at scale. Together, this study challenge some common assumptions about embodied scaling and provide practical guidance for training large-scale VLA policies from diverse robotic data. Project website: https://research.beingbeyond.com/rethink_vla

Test-time adaptation (TTA) for large language models (LLMs) updates model parameters at inference time using signals available at deployment. This paper focuses on a common yet under-explored regime: unsupervised, sample-specific TTA, where the model adapts independently for each prompt using only the prompt itself, without gold answers or external supervision. Although appealing, naive unsupervised TTA with a fixed, handcrafted learning rate can be unstable: updates may overfit to prompt-specific statistics, drift from the desired answer distribution, and ultimately degrade generation quality. This failure mode is not surprising, as in this case TTA must adapt to a single prompt within only a few gradient steps, unlike standard training that averages updates over large datasets and long optimization horizons. Therefore, we propose layer-wise dynamic test-time adaptation, a framework which explicitly modulates TTA strength as a function of prompt representation, LLM structure and adaptation step. In our setting, TTA updates only LoRA parameters, and a lightweight hypernetwork predicts per-layer, per-step learning-rate multipliers, enabling fine-grained control. Experiments across various datasets and LLMs consistently show that our method substantially strengthens TTA by learning effective scaling patterns over adaptation steps and transformer layer projections, improving stability while delivering better performance.

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the design and evaluation of lightweight CNN-to-SNN pipelines underexplored. In this paper, we present the first systematic benchmark of lightweight SNNs obtained by converting compact CNN architectures into spiking networks, where activations are modeled with Leaky-Integrate-and-Fire (LIF) neurons and trained using surrogate gradient descent under a unified setup. We construct spiking variants of ShuffleNet, SqueezeNet, MnasNet, and MixNet, and evaluate them on CIFAR-10, CIFAR-100, and TinyImageNet, measuring accuracy, F1-score, parameter count, computational complexity, and energy consumption. Our results show that SNNs can achieve up to 15.7x higher energy efficiency than their CNN counterparts while retaining competitive accuracy. Among these, the SNN variant of SqueezeNet consistently outperforms other lightweight SNNs. To further optimize this model, we apply a structured pruning strategy that removes entire redundant modules, yielding a pruned architecture, SNN-SqueezeNet-P. This pruned model improves CIFAR-10 accuracy by 6% and reduces parameters by 19% compared to the original SNN-SqueezeNet. Crucially, it narrows the gap with CNN-SqueezeNet, achieving nearly the same accuracy (only 1% lower) but with an 88.1% reduction in energy consumption due to sparse spike-driven computations. Together, these findings establish lightweight SNNs as practical, low-power alternatives for edge deployment, highlighting a viable path toward deploying high-performance, low-power intelligence on the edge.

Computing node importance in networks is a long-standing fundamental problem that has driven extensive study of various centrality measures. A particularly well-known centrality measure is betweenness centrality, which becomes computationally prohibitive on large-scale networks. Graph Neural Network (GNN) models have thus been proposed to predict node rankings according to their relative betweenness centrality. However, state-of-the-art methods fail to generalize to high-diameter graphs such as road networks. We propose BRAVA-GNN, a lightweight GNN architecture that leverages the empirically observed correlation linking betweenness centrality to degree-based quantities, in particular multi-hop degree mass. This correlation motivates the use of degree masses as size-invariant node features and synthetic training graphs that closely match the degree distributions of real networks. Furthermore, while previous work relies on scale-free synthetic graphs, we leverage the hyperbolic random graph model, which reproduces power-law exponents outside the scale-free regime, better capturing the structure of real-world graphs like road networks. This design enables BRAVA-GNN to generalize across diverse graph families while using 54x fewer parameters than the most lightweight existing GNN baseline. Extensive experiments on 19 real-world networks, spanning social, web, email, and road graphs, show that BRAVA-GNN achieves up to 214% improvement in Kendall-Tau correlation and up to 70x speedup in inference time over state-of-the-art GNN-based approaches, particularly on challenging road networks.

We present a complete framework for fast motion planning of non-holonomic autonomous mobile robots in highly complex but structured environments. Conventional grid-based planners struggle with scalability, while many kinematically-feasible planners impose a significant computational burden due to their search space complexity. To overcome these limitations, our approach introduces a deterministic free-space decomposition that creates a compact graph of overlapping rectangular corridors. This method enables a significant reduction in the search space, without sacrificing path resolution. The framework then performs online motion planning by finding a sequence of rectangles and generating a near-time-optimal, kinematically-feasible trajectory using an analytical planner. The result is a highly efficient solution for large-scale navigation. We validate our framework through extensive simulations and on a physical robot. The implementation is publicly available as open-source software.

Sustaining long-term interactions remains a bottleneck for Large Language Models (LLMs), as their limited context windows struggle to manage dialogue histories that extend over time. Existing memory systems often treat interactions as disjointed snippets, failing to capture the underlying narrative coherence of the dialogue stream. We propose TraceMem, a cognitively-inspired framework that weaves structured, narrative memory schemata from user conversational traces through a three-stage pipeline: (1) Short-term Memory Processing, which employs a deductive topic segmentation approach to demarcate episode boundaries and extract semantic representation; (2) Synaptic Memory Consolidation, a process that summarizes episodes into episodic memories before distilling them alongside semantics into user-specific traces; and (3) Systems Memory Consolidation, which utilizes two-stage hierarchical clustering to organize these traces into coherent, time-evolving narrative threads under unifying themes. These threads are encapsulated into structured user memory cards, forming narrative memory schemata. For memory utilization, we provide an agentic search mechanism to enhance reasoning process. Evaluation on the LoCoMo benchmark shows that TraceMem achieves state-of-the-art performance with a brain-inspired architecture. Analysis shows that by constructing coherent narratives, it surpasses baselines in multi-hop and temporal reasoning, underscoring its essential role in deep narrative comprehension. Additionally, we provide an open discussion on memory systems, offering our perspectives and future outlook on the field. Our code implementation is available at: https://github.com/YimingShu-teay/TraceMem

Large Language Models (LLMs) are becoming increasingly multilingual, supporting hundreds of languages, especially high resource ones. Unfortunately, Dialect variations are still underrepresented due to limited data and linguistic variation. In this work, we adapt a pre-trained LLM to improve dialectal performance. Specifically, we use Low Rank Adaptation (LoRA) fine-tuning on monolingual and English Dialect parallel data, adapter merging and dialect-aware MBR decoding to improve dialectal fidelity generation and translation. Experiments on Syrian, Moroccan, and Saudi Arabic show that merging and MBR improve dialectal fidelity while preserving semantic accuracy. This combination provides a compact and effective framework for robust dialectal Arabic generation.

We study fine-grained referring image segmentation via a decoupled reason-then-segment pipeline. A vision-language model (VLM) receives an image and a natural-language query, reasons about the scene, and emits structured spatial prompts: a bounding box plus two interior keypoints for every referred instance. A frozen promptable segmenter (SAM 2) converts these prompts into high-quality masks. Within our GenSeg-R1 framework we finetune Qwen3-VL models (4B and 8B parameters) using Group Relative Policy Optimization (GRPO), requiring no supervised reasoning-chain annotations. On RefCOCOg validation our best model (GenSeg-R1-8B) achieves 0.7127 cIoU and 0.7382 mIoU, substantially outperforming the corresponding Qwen3-VL Instruct baselines (+15.3 and +21.9 points, respectively) and surpassing Seg-Zero-7B [3] by +3.3 cIoU under identical evaluation. We further introduce GenSeg-R1-G, a variant trained on GRefCOCO [9] with a SAM 2 in-the-loop reward that directly optimizes mask quality. On GRefCOCO validation GenSeg-R1-G achieves 76.69% target mIoU with 82.40% accuracy on negative (no-target) prompts, substantially outperforming Seg-R1-7B and Seg-Zero-7B, which lack no-target detection capability. On ReasonSeg test, GenSeg-R1-4B reaches 68.40% mIoU, surpassing Seg-Zero-7B by +7.0 and Seg-R1-7B by +10.7 points.

Knowledge distillation (KD) is a tool to compress a larger system (teacher) into a smaller one (student). In machine translation, studies typically report only the translation quality of the student and omit the computational complexity of performing KD, making it difficult to select among the many available KD choices under compute-induced constraints. In this study, we evaluate representative KD methods by considering both translation quality and computational cost. We express computational cost as a carbon footprint using the machine learning life cycle assessment (MLCA) tool. This assessment accounts for runtime operational emissions and amortized hardware production costs throughout the KD model life cycle (teacher training, distillation, and inference). We find that (i) distillation overhead dominates the total footprint at small deployment volumes, (ii) inference dominates at scale, making KD beneficial only beyond a task-dependent usage threshold, and (iii) word-level distillation typically offers more favorable footprint-quality trade-offs than sequence-level distillation. Our protocol provides reproducible guidance for selecting KD methods under explicit quality and compute-induced constraints.

Univariate time series (UTS), where each timestamp records a single variable, serve as crucial indicators in web systems and cloud servers. Anomaly detection in UTS plays an essential role in both data mining and system reliability management. However, existing reconstruction-based and prediction-based methods struggle to capture certain subtle anomalies, particularly small point anomalies and slowly rising anomalies. To address these challenges, we propose a novel prediction-based framework named Contextual and Seasonal LSTMs (CS-LSTMs). CS-LSTMs are built upon a noise decomposition strategy and jointly leverage contextual dependencies and seasonal patterns, thereby strengthening the detection of subtle anomalies. By integrating both time-domain and frequency-domain representations, CS-LSTMs achieve more accurate modeling of periodic trends and anomaly localization. Extensive evaluations on public benchmark datasets demonstrate that CS-LSTMs consistently outperform state-of-the-art methods, highlighting their effectiveness and practical value in robust time series anomaly detection.

Liver fibrosis poses a substantial challenge in clinical practice, emphasizing the necessity for precise liver segmentation and accurate disease staging. Based on the CARE Liver 2025 Track 4 Challenge, this study introduces a multi-task deep learning framework developed for liver segmentation (LiSeg) and liver fibrosis staging (LiFS) using multiparametric MRI. The LiSeg phase addresses the challenge of limited annotated images and the complexities of multi-parametric MRI data by employing a semi-supervised learning model that integrates image segmentation and registration. By leveraging both labeled and unlabeled data, the model overcomes the difficulties introduced by domain shifts and variations across modalities. In the LiFS phase, we employed a patchbased method which allows the visualization of liver fibrosis stages based on the classification outputs. Our approach effectively handles multimodality imaging data, limited labels, and domain shifts. The proposed method has been tested by the challenge organizer on an independent test set that includes in-distribution (ID) and out-of-distribution (OOD) cases using three-channel MRIs (T1, T2, DWI) and seven-channel MRIs (T1, T2, DWI, GED1-GED4). The code is freely available. Github link: https://github.com/mileywang3061/Care-Liver

In today's connected world, the generation of massive streaming data across diverse domains has become commonplace. In the presence of concept drift, class imbalance, label scarcity, and new class emergence, they jointly degrade representation stability, bias learning toward outdated distributions, and reduce the resilience and reliability of detection in dynamic environments. This paper proposes SCIL (Streaming Class-Incremental Learning) to address these challenges. The SCIL framework integrates an autoencoder (AE) with a multi-layer perceptron for multi-class prediction, uses a dual-loss strategy (classification and reconstruction) for prediction and new class detection, employs corrected pseudo-labels for online training, manages classes with queues, and applies oversampling to handle imbalance. The rationale behind the method's structure is elucidated through ablation studies and a comprehensive experimental evaluation is performed using both real-world and synthetic datasets that feature class imbalance, incremental classes, and concept drifts. Our results demonstrate that SCIL outperforms strong baselines and state-of-the-art methods. Based on our commitment to Open Science, we make our code and datasets available to the community.

Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI planning, which requires more sophisticated data collection. In reality, the exploration process of a CUA across apps/desktops/web pages typically follows a tree structure, with earlier functional entry points often being explored more frequently. Thus, organizing large-scale trajectories into tree structures can reduce data cost and streamline the data scaling of GUI planning. In this work, we propose TreeCUA to efficiently scale GUI automation with tree-structured verifiable evolution. We propose a multi-agent collaborative framework to explore the environment, verify actions, summarize trajectories, and evaluate quality to generate high-quality and scalable GUI trajectories. To improve efficiency, we devise a novel tree-based topology to store and replay duplicate exploration nodes, and design an adaptive exploration algorithm to balance the depth (\emph{i.e.}, trajectory difficulty) and breadth (\emph{i.e.}, trajectory diversity). Moreover, we develop world knowledge guidance and global memory backtracking to avoid low-quality generation. Finally, we naturally extend and propose the TreeCUA-DPO method from abundant tree node information, improving GUI planning capability by referring to the branch information of adjacent trajectories. Experimental results show that TreeCUA and TreeCUA-DPO offer significant improvements, and out-of-domain (OOD) studies further demonstrate strong generalization. All trajectory node information and code will be available at https://github.com/UITron-hub/TreeCUA.

This paper presents RANT, an ant-inspired multi-robot exploration framework for noisy, uncertain environments. A team of differential-drive robots navigates a 10 x 10 m terrain, collects noisy probe measurements of a hidden richness field, and builds local probabilistic maps while the supervisor maintains a global evaluation. RANT combines particle-filter localisation, a behaviour-based controller with gradient-driven hotspot exploitation, and a lightweight no-revisit coordination mechanism based on virtual pheromone blocking. We experimentally analyse how team size, localisation fidelity, and coordination influence coverage, hotspot recall, and redundancy. Results show that particle filtering is essential for reliable hotspot engagement, coordination substantially reduces overlap, and increasing team size improves coverage but yields diminishing returns due to interference.

Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes. However, real-world outdoor exploration typically occurs in unknown environments where detailed navigation instructions are unavailable. Instead, only coarse-grained positional or directional guidance can be provided, requiring UAVs to autonomously navigate through continuous planning and obstacle avoidance. To bridge this gap, we propose AutoFly, an end-to-end Vision-Language-Action (VLA) model for autonomous UAV navigation. AutoFly incorporates a pseudo-depth encoder that derives depth-aware features from RGB inputs to enhance spatial reasoning, coupled with a progressive two-stage training strategy that effectively aligns visual, depth, and linguistic representations with action policies. Moreover, existing VLN datasets have fundamental limitations for real-world autonomous navigation, stemming from their heavy reliance on explicit instruction-following over autonomous decision-making and insufficient real-world data. To address these issues, we construct a novel autonomous navigation dataset that shifts the paradigm from instruction-following to autonomous behavior modeling through: (1) trajectory collection emphasizing continuous obstacle avoidance, autonomous planning, and recognition workflows; (2) comprehensive real-world data integration. Experimental results demonstrate that AutoFly achieves a 3.9% higher success rate compared to state-of-the-art VLA baselines, with consistent performance across simulated and real environments.

3D affordance grounding aims to highlight the actionable regions on 3D objects, which is crucial for robotic manipulation. Previous research primarily focused on learning affordance knowledge from static cues such as language and images, which struggle to provide sufficient dynamic interaction context that can reveal temporal and causal cues. To alleviate this predicament, we collect a comprehensive video-based 3D affordance dataset, \textit{VIDA}, which contains 38K human-object-interaction videos covering 16 affordance types, 38 object categories, and 22K point clouds. Based on \textit{VIDA}, we propose a strong baseline: VideoAfford, which activates multimodal large language models with additional affordance segmentation capabilities, enabling both world knowledge reasoning and fine-grained affordance grounding within a unified framework. To enhance action understanding capability, we leverage a latent action encoder to extract dynamic interaction priors from HOI videos. Moreover, we introduce a \textit{spatial-aware} loss function to enable VideoAfford to obtain comprehensive 3D spatial knowledge. Extensive experimental evaluations demonstrate that our model significantly outperforms well-established methods and exhibits strong open-world generalization with affordance reasoning abilities. All datasets and code will be publicly released to advance research in this area.

The proliferation of hateful content in online videos poses severe threats to individual well-being and societal harmony. However, existing solutions for video hate detection either rely heavily on large-scale human annotations or lack fine-grained temporal precision. In this work, we propose LELA, the first training-free Large Language Model (LLM) based framework for hate video localization. Distinct from state-of-the-art models that depend on supervised pipelines, LELA leverages LLMs and modality-specific captioning to detect and temporally localize hateful content in a training-free manner. Our method decomposes a video into five modalities, including image, speech, OCR, music, and video context, and uses a multi-stage prompting scheme to compute fine-grained hateful scores for each frame. We further introduce a composition matching mechanism to enhance cross-modal reasoning. Experiments on two challenging benchmarks, HateMM and MultiHateClip, demonstrate that LELA outperforms all existing training-free baselines by a large margin. We also provide extensive ablations and qualitative visualizations, establishing LELA as a strong foundation for scalable and interpretable hate video localization.

Feature selection (FS) remains essential for building accurate and interpretable detection models, particularly in high-dimensional malware datasets. Conventional FS methods such as Extra Trees, Variance Threshold, Tree-based models, Chi-Squared tests, ANOVA, Random Selection, and Sequential Attention rely primarily on statistical heuristics or model-driven importance scores, often overlooking the semantic context of features. Motivated by recent progress in LLM-driven FS, we investigate whether large language models (LLMs) can guide feature selection in a zero-shot setting, using only feature names and task descriptions, as a viable alternative to traditional approaches. We evaluate multiple LLMs (GPT-5.0, GPT-4.0, Gemini-2.5 etc.) on the EMBOD dataset (a fusion of EMBER and BODMAS benchmark datasets), comparing them against established FS methods across several classifiers, including Random Forest, Extra Trees, MLP, and KNN. Performance is assessed using accuracy, precision, recall, F1, AUC, MCC, and runtime. Our results demonstrate that LLM-guided zero-shot feature selection achieves competitive performance with traditional FS methods while offering additional advantages in interpretability, stability, and reduced dependence on labeled data. These findings position zero-shot LLM-based FS as a promising alternative strategy for effective and interpretable malware detection, paving the way for knowledge-guided feature selection in security-critical applications

We introduce MILE-RefHumEval, a reference-free framework for evaluating Large Language Models (LLMs) without ground-truth annotations or evaluator coordination. It leverages an ensemble of independently prompted evaluators guided by a human-aligned schema, supporting both discrete and continuous scoring judgement. With task-specific prompts from best candidate selection, summarization and image captioning to dialogue, MILE-RefHumEval provides flexible, interpretable, and scalable assessments. Experiments show it aligns closely with human judgments, outperforms prior methods, and reduces computational overhead, offering an efficient, robust, and human-aligned solution for real-world LLM evaluation.

Real-world contact-rich manipulation demands robots to perceive temporal tactile feedback, capture subtle surface deformations, and reason about object properties as well as force dynamics. Although optical tactile sensors are uniquely capable of providing such rich information, existing tactile datasets and models remain limited. These resources primarily focus on object-level attributes (e.g., material) while largely overlooking fine-grained tactile temporal dynamics during physical interactions. We consider that advancing dynamic tactile perception requires a systematic hierarchy of dynamic perception capabilities to guide both data collection and model design. To address the lack of tactile data with rich dynamic information, we present ToucHD, a large-scale hierarchical tactile dataset spanning tactile atomic actions, real-world manipulations, and touch-force paired data. Beyond scale, ToucHD establishes a comprehensive tactile dynamic data ecosystem that explicitly supports hierarchical perception capabilities from the data perspective. Building on it, we propose AnyTouch 2, a general tactile representation learning framework for diverse optical tactile sensors that unifies object-level understanding with fine-grained, force-aware dynamic perception. The framework captures both pixel-level and action-specific deformations across frames, while explicitly modeling physical force dynamics, thereby learning multi-level dynamic perception capabilities from the model perspective. We evaluate our model on benchmarks that covers static object properties and dynamic physical attributes, as well as real-world manipulation tasks spanning multiple tiers of dynamic perception capabilities-from basic object-level understanding to force-aware dexterous manipulation. Experimental results demonstrate consistent and strong performance across sensors and tasks.