The Moving Target Traveling Salesman Problem (MT-TSP) seeks a trajectory that intercepts several moving targets, within a particular time window for each target. When generic nonlinear target trajectories or kinematic constraints on the agent are present, no prior algorithm guarantees convergence to an optimal MT-TSP solution. Therefore, we introduce the Iterated Random Generalized (IRG) TSP framework. The idea behind IRG is to alternate between randomly sampling a set of agent configuration-time points, corresponding to interceptions of targets, and finding a sequence of interception points by solving a generalized TSP (GTSP). This alternation asymptotically converges to the optimum. We introduce two parallel algorithms within the IRG framework. The first algorithm, IRG-PGLNS, solves GTSPs using PGLNS, our parallelized extension of state-of-the-art solver GLNS. The second algorithm, Parallel Communicating GTSPs (PCG), solves GTSPs for several sets of points simultaneously. We present numerical results for three MT-TSP variants: one where intercepting a target only requires coming within a particular distance, another where the agent is a variable-speed Dubins car, and a third where the agent is a robot arm. We show that IRG-PGLNS and PCG converge faster than a baseline based on prior work. We further validate our framework with physical robot experiments.

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic, instance-based mixed-precision quantization promises a superior accuracy-efficiency trade-off by allocating higher precision only when needed. However, a critical bottleneck remains: existing methods require a costly dequantize-to-float and requantize-to-integer cycle to change precision, breaking the integer-only hardware paradigm and compromising performance gains. This paper introduces Dynamic Quantization Training (DQT), a novel framework that removes this bottleneck. At the core of DQT is a nested integer representation where lower-precision values are bit-wise embedded within higher-precision ones. This design, coupled with custom integer-only arithmetic, allows for on-the-fly bit-width switching through a near-zero-cost bit-shift operation. This makes DQT the first quantization framework to enable both dequantization-free static mixed-precision of the backbone network, and truly efficient dynamic, instance-based quantization through a lightweight controller that decides at runtime how to quantize each layer. We demonstrate DQT state-of-the-art performance on ResNet18 on CIFAR-10 and ResNet50 on ImageNet. On ImageNet, our 4-bit dynamic ResNet50 achieves 77.00% top-1 accuracy, an improvement over leading static (LSQ, 76.70%) and dynamic (DQNET, 76.94%) methods at a comparable BitOPs budget. Crucially, DQT achieves this with a bit-width transition cost of only 28.3M simple bit-shift operations, a drastic improvement over the 56.6M costly Multiply-Accumulate (MAC) floating-point operations required by previous dynamic approaches - unlocking a new frontier in efficient, adaptive AI.

Modern methods of generative modelling and unpaired data translation based on Schrödinger bridges and stochastic optimal control theory aim to transform an initial density to a target one in an optimal way. In the present paper, we assume that we only have access to i.i.d. samples from the initial and final distributions. This makes our setup suitable for both generative modelling and unpaired data translation. Relying on the stochastic optimal control approach, we choose an Ornstein-Uhlenbeck process as the reference one and estimate the corresponding Schrödinger potential. Introducing a risk function as the Kullback-Leibler divergence between couplings, we derive tight bounds on the generalization ability of an empirical risk minimizer over a class of Schrödinger potentials, including Gaussian mixtures. Thanks to the mixing properties of the Ornstein-Uhlenbeck process, we almost achieve fast rates of convergence, up to some logarithmic factors, in favourable scenarios. We also illustrate the performance of the suggested approach with numerical experiments.

Interactive theorem provers (ITPs) require manual formalization, which is labor-intensive and demands expert knowledge. While automated formalization offers a potential solution, it faces two major challenges: model hallucination (e.g., undefined predicates, symbol misuse, and version incompatibility) and the semantic gap caused by ambiguous or missing premises in natural language descriptions. To address these issues, we propose CRAMF, a Concept-driven Retrieval-Augmented Mathematical Formalization framework. CRAMF enhances LLM-based autoformalization by retrieving formal definitions of core mathematical concepts, providing contextual grounding during code generation. However, applying retrieval-augmented generation (RAG) in this setting is non-trivial due to the lack of structured knowledge bases, the polymorphic nature of mathematical concepts, and the high precision required in formal retrieval. We introduce a framework for automatically constructing a concept-definition knowledge base from Mathlib4, the standard mathematical library for the Lean 4 theorem prover, indexing over 26,000 formal definitions and 1,000+ core mathematical concepts. To address conceptual polymorphism, we propose contextual query augmentation with domain- and application-level signals. In addition, we design a dual-channel hybrid retrieval strategy with reranking to ensure accurate and relevant definition retrieval. Experiments on miniF2F, ProofNet, and our newly proposed AdvancedMath benchmark show that CRAMF can be seamlessly integrated into LLM-based autoformalizers, yielding consistent improvements in translation accuracy, achieving up to 62.1% and an average of 29.9% relative improvement.

Algorithms for solving \textit{nonlinear} fixed-point equations -- such as average-reward \textit{$Q$-learning} and \textit{TD-learning} -- often involve semi-norm contractions. Achieving parameter-free optimal convergence rates for these methods via Polyak--Ruppert averaging has remained elusive, largely due to the non-monotonicity of such semi-norms. We close this gap by (i.) recasting the averaged error as a linear recursion involving a nonlinear perturbation, and (ii.) taming the nonlinearity by coupling the semi-norm's contraction with the monotonicity of a suitably induced norm. Our main result yields the first parameter-free $\tilde{O}(1/\sqrt{t})$ optimal rates for $Q$-learning in both average-reward and exponentially discounted settings, where $t$ denotes the iteration index. The result applies within a broad framework that accommodates synchronous and asynchronous updates, single-agent and distributed deployments, and data streams obtained either from simulators or along Markovian trajectories.

Infrared and visible image fusion (IVIF) is essential for integrating thermal saliency with textural details to support downstream perception. However, most existing approaches suffer from "semantic blindness," leading to the erroneous suppression of thermal targets and the introduction of visual artifacts. To address this, we propose SAM-Guided Diffusion Fusion Network (SGDFuse), a novel Semantic-Guided Generation (SGG) framework that reframes IVIF as a semantically-steered generative task rather than simplistic pixel mapping. Our method uniquely couples high-level semantic priors from the Segment Anything Model (SAM) with the high-fidelity generative power of a conditional diffusion model. We employ a deliberate two-stage strategy to decouple multimodal alignment from iterative refinement: Stage I establishes a robust structural foundation via preliminary fusion, while Stage II utilizes dual-modality semantic masks as spatial anchors to guide the diffusion process toward a semantically coherent, high-fidelity reconstruction. Comprehensive experiments demonstrate that SGDFuse not only delivers state-of-the-art image quality but also enhances downstream task performance, confirming its effectiveness as a new Methodological Framework for semantically aware image fusion. The code is available at https://github.com/boshizhang123/SGDFuse.

Mixed-precision quantization (MPQ) is crucial for deploying deep neural networks on resource-constrained devices, but finding the optimal bit-width for each layer represents a complex combinatorial optimization problem. Current state-of-the-art methods rely on computationally expensive search algorithms or local sensitivity heuristic proxies like the Hessian, which fail to capture the cascading global effects of quantization error. In this work, we argue that the quantization sensitivity of a layer should not be measured by its local properties, but by its impact on the information flow throughout the entire network. We introduce InfoQ, a novel framework for MPQ that is training-free in the bit-width search phase. InfoQ assesses layer sensitivity by quantizing each layer at different bit-widths and measuring, through a single forward pass, the resulting change in mutual information in the subsequent layers. This quantifies how much each layer quantization impacts the network information flow. The resulting scores are used to formulate bit-width allocation as an integer linear programming problem, which is solved efficiently to minimize total sensitivity under a given budget (e.g., model size or BitOps). Our retraining-free search phase provides a superior search-time/accuracy trade-off (using two orders of magnitude less data compared to state-of-the-art methods such as LIMPQ), while yielding up to a 1% accuracy improvement for MobileNetV2 and ResNet18 on ImageNet at high compression rates (14X and 10.66X).

We present MVTOP, a novel transformer-based method for multi-view rigid object pose estimation. Through an early fusion of the view-specific features, our method can resolve pose ambiguities that would be impossible to solve with a single view or with a post-processing of single-view poses. MVTOP models the multi-view geometry via lines of sight that emanate from the respective camera centers. While the method assumes the camera interior and relative orientations are known for a particular scene, they can vary for each inference. This makes the method versatile. The use of the lines of sight enables MVTOP to correctly predict the correct pose with the merged multi-view information. To show the model's capabilities, we provide a synthetic data set that can only be solved with such holistic multi-view approaches since the poses in the dataset cannot be solved with just one view. Our method outperforms single-view and all existing multi-view approaches on our dataset and achieves competitive results on the YCB-V dataset. To the best of our knowledge, no holistic multi-view method exists that can resolve such pose ambiguities reliably. Our model is end-to-end trainable and does not require any additional data, e.g., depth.

Robust robot planning in dynamic, human-centric environments remains challenging due to multimodal uncertainty, the need for real-time adaptation, and safety requirements. Optimization-based planners enable explicit constraint handling but can be sensitive to initialization and struggle in dynamic settings. Learning-based planners capture multimodal solution spaces more naturally, but often lack reliable constraint satisfaction. In this paper, we introduce a unified generation-refinement framework that combines reward-guided conditional flow matching (CFM) with model predictive path integral (MPPI) control. Our key idea is a bidirectional information exchange between generation and optimization: reward-guided CFM produces diverse, informed trajectory priors for MPPI refinement, while the optimized MPPI trajectory warm-starts the next CFM generation step. Using autonomous social navigation as a motivating application, we demonstrate that the proposed approach improves the trade-off between safety, task performance, and computation time, while adapting to dynamic environments in real-time. The source code is publicly available at https://cfm-mppi.github.io.

Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In medicine, these models can admit conflicting predictions for the same patient -- a risk that is poorly understood and insufficiently addressed. In this study, we empirically analyze the extent, drivers, and ramifications of predictive multiplicity across diverse medical tasks and model architectures, and show that even small ensembles can mitigate/eliminate predictive multiplicity in practice. Our analysis reveals that (1) standard validation metrics fail to identify a uniquely optimal model and (2) a substantial amount of predictions hinges on arbitrary choices made during model development. Using multiple models instead of a single model reveals instances where predictions differ across equally plausible models -- highlighting patients that would receive arbitrary diagnoses if any single model were used. In contrast, (3) a small ensemble paired with an abstention strategy can effectively mitigate measurable predictive multiplicity in practice; predictions with high inter-model consensus may thus be amenable to automated classification. While accuracy is not a principled antidote to predictive multiplicity, we find that (4) higher accuracy achieved through increased model capacity reduces predictive multiplicity. Our findings underscore the clinical importance of accounting for model multiplicity and advocate for ensemble-based strategies to improve diagnostic reliability. In cases where models fail to reach sufficient consensus, we recommend deferring decisions to expert review.

Forecasting in financial markets remains a significant challenge due to their nonlinear and regime-dependent dynamics. Traditional deep learning models, such as long short-term memory networks and multilayer perceptrons, often struggle to generalize across shifting market conditions, highlighting the need for a more adaptive and interpretable approach. To address this, we introduce Kolmogorov-Arnold networks for stock prediction and explainable regimes (KASPER), a novel framework that integrates regime detection, sparse spline-based function modeling, and symbolic rule extraction. The framework identifies hidden market conditions using a Gumbel-Softmax-based mechanism, enabling regime-specific forecasting. For each regime, it employs Kolmogorov-Arnold networks with sparse spline activations to capture intricate price behaviors while maintaining robustness. Interpretability is achieved through symbolic learning based on Monte Carlo Shapley values, which extracts human-readable rules tailored to each regime. Applied to real-world financial time series from Yahoo Finance, the model achieves an $R^2$ score of 0.89, a Sharpe Ratio of 12.02, and a mean squared error as low as 0.0001, outperforming existing methods. This research establishes a new direction for regime-aware, transparent, and robust forecasting in financial markets.

Real-world Vehicle-to-Everything (V2X) cooperative perception systems often operate under heterogeneous sensor configurations due to cost constraints and deployment variability across vehicles and infrastructure. This heterogeneity poses significant challenges for feature fusion and perception reliability. To address these issues, we propose HeCoFuse, a unified framework designed for cooperative perception across mixed sensor setups where nodes may carry Cameras (C), LiDARs (L), or both. By introducing a hierarchical fusion mechanism that adaptively weights features through a combination of channel-wise and spatial attention, HeCoFuse can tackle critical challenges such as cross-modality feature misalignment and imbalanced representation quality. In addition, an adaptive spatial resolution adjustment module is employed to balance computational cost and fusion effectiveness. To enhance robustness across different configurations, we further implement a cooperative learning strategy that dynamically adjusts fusion type based on available modalities. Experiments on the real-world TUMTraf-V2X dataset demonstrate that HeCoFuse achieves 43.22% 3D mAP under the full sensor configuration (LC+LC), outperforming the CoopDet3D baseline by 1.17%, and reaches an even higher 43.38% 3D mAP in the L+LC scenario, while maintaining 3D mAP in the range of 21.74% to 43.38% across nine heterogeneous sensor configurations. These results, validated by our first-place finish in the CVPR 2025 DriveX challenge, establish HeCoFuse as the current state-of-the-art on TUM-Traf V2X dataset while demonstrating robust performance across diverse sensor deployments.

The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action spaces make them difficult to leverage. Our main insight is that skills performed across different embodiments produce visual similarities in motions that can be captured using off-the-shelf action representations such as optical flow. Moreover, World Models (WMs) can leverage sub-optimal data since they focus on modeling dynamics. In this work, we aim to improve visuomotor policies in low-data regimes by first pretraining a WM using optical flow as an embodiment-agnostic action representation to leverage accessible or easily collected data from multiple embodiments (robots, humans). Given a small set of demonstrations on a target embodiment, we finetune the WM on this data to better align the WM predictions, train a base policy, and learn a robust value function. Using our finetuned WM and value function, our approach evaluates action candidates from the base policy and selects the best one to improve performance. Our approach, which we term Latent Policy Steering (LPS), improves behavior-cloned policies by 10.6% on average across four Robomimic tasks, even though most of the pretraining data comes from the real world. In the real-world experiments, LPS achieves larger gains: 70% relative improvement with 30-50 target-embodiment demonstrations, and 44% relative improvement with 60-100 demonstrations, compared to a behavior-cloned baseline. Qualitative results can be found on the website: https://yiqiwang8177.github.io/LatentPolicySteering/.

Canine gait analysis using wearable inertial sensors is gaining attention in veterinary clinical settings, as it provides valuable insights into a range of mobility impairments. Neurological and orthopedic conditions cannot always be easily distinguished even by experienced clinicians. The current study explored and developed a deep learning approach using inertial sensor readings to assess whether neurological and orthopedic gait could facilitate gait analysis. Our investigation focused on optimizing both performance and generalizability in distinguishing between these gait abnormalities. Variations in sensor configurations, assessment protocols, and enhancements to deep learning model architectures were further suggested. Using a dataset of 29 dogs, our proposed approach achieved 96% accuracy in the multiclass classification task (healthy/orthopedic/neurological) and 82% accuracy in the binary classification task (healthy/non-healthy) when generalizing to unseen dogs. Our results demonstrate the potential of inertial-based deep learning models to serve as a practical and objective diagnostic and clinical aid to differentiate gait assessment in orthopedic and neurological conditions.

Thanks to recent advances in generative AI, computers can now simulate realistic and complex natural processes. We apply this capability to predict how wildfires spread, a task made difficult by the unpredictable nature of fire and the variety of environmental conditions it depends on. In this study, We present the first denoising diffusion model for predicting wildfire spread, a new kind of AI framework that learns to simulate fires not just as one fixed outcome, but as a range of possible scenarios. By doing so, it accounts for the inherent uncertainty of wildfire dynamics, a feature that traditional models typically fail to represent. Unlike deterministic approaches that generate a single prediction, our model produces ensembles of forecasts that reflect physically meaningful distributions of where fire might go next. This technology could help us develop smarter, faster, and more reliable tools for anticipating wildfire behavior, aiding decision-makers in fire risk assessment and response planning.

Vision Language Models (VLMs) provide rich semantic priors but are underexplored in Semi supervised Semantic Segmentation. Recent attempts to integrate VLMs to inject high level semantics overlook the semantic misalignment between visual and textual representations that arises from using domain invariant text embeddings without adapting them to dataset and image specific contexts. This lack of domain awareness, coupled with limited annotations, weakens the model semantic understanding by preventing effective vision language alignment. As a result, the model struggles with contextual reasoning, shows weak intra class discrimination, and confuses similar classes. To address these challenges, we propose Hierarchical Vision Language transFormer (HVLFormer), which achieves domain aware and domain robust alignment between visual and textual representations within a mask transformer architecture. Firstly, we transform text embeddings from pretrained VLMs into textual object queries, enabling the generation of multi scale, dataset aware queries that capture class semantics from coarse to fine granularity and enhance contextual reasoning. Next, we refine these queries by injecting image specific visual context to align textual semantics with local scene structures and enhance class discrimination. Finally, to achieve domain robustness, we introduce cross view and modal consistency regularization, which enforces prediction consistency within mask-transformer architecture across augmented views. Moreover, it ensures stable vision language alignment during decoding. With less than 1% training data, HVLFormer outperforms state of the art methods on Pascal VOC, COCO, ADE20K, and Cityscapes. Our code and results will be available on GitHub.

Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or 'table'), require masked diffusion for editing, ignore room boundaries, or rely on floor plan renderings that fail to capture complex layouts. LLM-based methods enable richer semantics via natural language, but lack editing functionality, are limited to rectangular layouts, or rely on weak spatial reasoning from implicit world models. We introduce ReSpace, a generative framework for autoregressive text-driven 3D indoor scene synthesis and editing. Our approach features a compact structured scene representation with explicit room boundaries that enables asset-agnostic deployment and frames scene manipulation as a next-token prediction task, supporting object addition, removal, and swapping via natural language. We employ supervised fine-tuning with a preference alignment stage to train a specialized language model for object addition that accounts for user instructions, spatial geometry, object semantics, and scene-level composition. We further introduce a voxelization-based evaluation metric capturing fine-grained geometric violations beyond 3D bounding boxes. Experiments surpass state-of-the-art on object addition and achieve superior human-perceived quality on the application of full scene synthesis, despite not being trained on it.

Entity relationship classification remains a challenging task in information extraction, especially in scenarios with limited labeled data and complex relational structures. In this study, we conduct a comparative analysis of three distinct AI agent architectures designed to perform relation classification using large language models (LLMs). The agentic architectures explored include (1) reflective self-evaluation, (2) hierarchical task decomposition, and (3) a novel multi-agent dynamic example generation mechanism, each leveraging different modes of reasoning and prompt adaptation. In particular, our dynamic example generation approach introduces real-time cooperative and adversarial prompting. We systematically compare their performance across multiple domains and model backends. Our experiments demonstrate that multi-agent coordination consistently outperforms standard few-shot prompting and approaches the performance of fine-tuned models. These findings offer practical guidance for the design of modular, generalizable LLM-based systems for structured relation extraction. The source codes and dataset are available at https://github.com/maryambrj/ALIEN.git.

Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and rich detailed information. In this paper, we leverage preference learning to enhance the performance of vision-language models in fine-grained video captioning, while mitigating several limitations inherent to direct preference optimization (DPO). First, we propose a pipeline for constructing preference pairs that leverages the intrinsic properties of VLMs along with partial assistance from large language models, achieving an optimal balance between cost and data quality. Second, we propose Synergistic Preference Optimization (SynPO), a novel optimization method offering significant advantages over DPO and its variants. SynPO prevents negative preferences from dominating the optimization, explicitly preserves the model's language capability to avoid deviation of the optimization objective, and improves training efficiency by eliminating the need for the reference model. We extensively evaluate SynPO not only on video captioning benchmarks (e.g., VDC, VDD, VATEX) but also across well-established NLP tasks, including general language understanding and preference evaluation, using diverse pretrained models. Results demonstrate that SynPO consistently outperforms DPO variants while achieving 20\% improvement in training efficiency. Code is available at https://github.com/longmalongma/SynPO

Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample diversity, predictive learning entails different sources of stochasticity and requires sampling consistency aligned with the ground-truth trajectory, which is a limitation we empirically observe in diffusion models. We argue that a key bottleneck in learning sampling-consistent predictive diffusion models lies in suboptimal predictive ability, which we attribute to the entanglement of condition understanding and target denoising within shared architectures and co-training schemes. To address this, we propose Foresight Diffusion (ForeDiff), a framework for predictive diffusion models that improves sampling consistency by decoupling condition understanding from target denoising. ForeDiff incorporates a separate deterministic predictive stream to process conditioning inputs independently of the denoising stream, and further leverages a pretrained predictor to extract informative representations that guide generation. Extensive experiments on robot video prediction and scientific spatiotemporal forecasting show that ForeDiff improves both predictive accuracy and sampling consistency over strong baselines, offering a promising direction for predictive diffusion models.

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel decoding, which increase answer diversity but scale poorly in efficiency. To address this efficiency-accuracy trade-off, we propose SSR (Speculative Parallel Scaling Reasoning), a training-free framework that leverages a key insight: by introducing speculative decoding at the step level, we can accelerate reasoning without sacrificing correctness. SSR integrates two components: a Selective Parallel Module (SPM) that identifies a small set of promising reasoning strategies via model-internal scoring, and Step-level Speculative Decoding (SSD), which enables efficient draft-target collaboration for fine-grained reasoning acceleration. Experiments on three mathematical benchmarks-AIME 2024, MATH-500, and LiveMathBench - demonstrate that SSR achieves strong gains over baselines. For instance, on LiveMathBench, SSR improves pass@1 accuracy by 13.84% while reducing computation to 80.5% of the baseline FLOPs. On MATH-500, SSR reduces compute to only 30% with no loss in accuracy.

Spike cameras offer unique sensing capabilities but their sparse, asynchronous output challenges semantic understanding, especially for Spike Video-Language Alignment (Spike-VLA) where models like CLIP underperform due to modality mismatch. We introduce SPKLIP, the first architecture specifically for Spike-VLA. SPKLIP employs a hierarchical spike feature extractor that adaptively models multi-scale temporal dynamics in event streams, and uses spike-text contrastive learning to directly align spike video with language, enabling effective few-shot learning. A full-spiking visual encoder variant, integrating SNN components into our pipeline, demonstrates enhanced energy efficiency. Experiments show state-of-the-art performance on benchmark spike datasets and strong few-shot generalization on a newly contributed real-world dataset. SPKLIP's energy efficiency highlights its potential for neuromorphic deployment, advancing event-based multimodal research. The source code and dataset are available at [link removed for anonymity].

The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly employed to address data scarcity, existing approaches either overlook the correctness of intermediate reasoning steps or depend on expensive process-level annotations to construct process reward models (PRM). To address the above problems, we propose an Iterative Preference Learning (IPL) that constructs a CoaT-tree through interative sampling, scores leaf nodes using rule-based reward, and backpropagates feedback to derive Thinking-level Direct Preference Optimization (T-DPO) pairs. To prevent overfitting during warm-up supervised fine-tuning, we further introduce a three-stage instruction evolution, which leverages GPT-4o to generate diverse Q\&A pairs based on real mobile UI screenshots, enhancing both generality and layout understanding. Experiments on three standard Mobile GUI-agent benchmarks demonstrate that our agent MobileIPL outperforms strong baselines, including continual pretraining models such as OS-ATLAS and UI-TARS. It achieves state-of-the-art performance across three standard Mobile GUI-Agents benchmarks and shows strong generalization to out-of-domain scenarios.

Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations into control actions. However, existing VLAs are primarily trained on successful expert demonstrations and lack structured supervision for failure diagnosis and recovery, limiting robustness in open-world scenarios. To address this limitation, we propose the Robotic Failure Analysis and Correction (RoboFAC) framework. We construct a large-scale failure-centric dataset comprising 9,440 erroneous manipulation trajectories and 78,623 QA pairs across 53 scenes in both simulation and real-world environments, with systematically categorized failure types. Leveraging this dataset, we develop a lightweight multimodal model specialized for task understanding, failure analysis, and failure correction, enabling efficient local deployment while remaining competitive with large proprietary models. Experimental results demonstrate that RoboFAC achieves a 34.1% higher failure analysis accuracy compared to GPT-4o. Furthermore, we integrated RoboFAC as an external supervisor in a real-world VLA control pipeline, yielding a 29.1% relative improvement across four tasks while significantly reducing latency relative to GPT-4o. These results demonstrate that RoboFAC enables systematic failure diagnosis and recovery, significantly enhancing VLA recovery capabilities. Our model and dataset are publicly available at https://github.com/MINT-SJTU/RoboFAC.

The success of Transformers lies in their ability to improve inference through two complementary strategies: the permanent refinement of model parameters via in-weight learning (IWL), and the ephemeral modulation of inferences via in-context learning (ICL), which leverages contextual information maintained in the model's activations. Evolutionary biology tells us that the predictability of the environment across timescales predicts the extent to which analogous strategies should be preferred. Genetic evolution adapts to stable environmental features by gradually modifying the genotype over generations. Conversely, environmental volatility favors plasticity, which enables a single genotype to express different traits within a lifetime, provided there are reliable cues to guide the adaptation. We operationalize these dimensions (environmental stability and cue reliability) in controlled task settings (sinusoid regression and Omniglot classification) to characterize their influence on learning in Transformers. We find that stable environments favor IWL, often exhibiting a sharp transition when conditions are static. Conversely, reliable cues favor ICL, particularly when the environment is volatile. Furthermore, an analysis of learning dynamics reveals task-dependent transitions between strategies (ICL to IWL and vice versa). We demonstrate that these transitions are governed by (1) the asymptotic optimality of the strategy with respect to the environment, and (2) the optimization cost of acquiring that strategy, which depends on the task structure and the learner's inductive bias.

The proliferation of connected vehicles within the Internet of Vehicles (IoV) ecosystem presents critical challenges in ensuring scalable, real-time, and privacy-preserving traffic management. Existing centralized IoV solutions often suffer from high latency, limited scalability, and reliance on proprietary Artificial Intelligence (AI) models, creating significant barriers to widespread deployment, particularly in dynamic and privacy-sensitive environments. Meanwhile, integrating Large Language Models (LLMs) in vehicular systems remains underexplored, especially concerning prompt optimization and effective utilization in federated contexts. To address these challenges, we propose the Federated Prompt-Optimized Traffic Transformer (FPoTT), a novel framework that leverages open-source LLMs for predictive IoV management. FPoTT introduces a dynamic prompt optimization mechanism that iteratively refines textual prompts to enhance trajectory prediction. The architecture employs a dual-layer federated learning paradigm, combining lightweight edge models for real-time inference with cloud-based LLMs to retain global intelligence. A Transformer-driven synthetic data generator is incorporated to augment training with diverse, high-fidelity traffic scenarios in the Next Generation Simulation (NGSIM) format. Extensive evaluations demonstrate that FPoTT, utilizing EleutherAI Pythia-1B, achieves 99.86% prediction accuracy on real-world data while maintaining high performance on synthetic datasets. These results underscore the potential of open-source LLMs in enabling secure, adaptive, and scalable IoV management, offering a promising alternative to proprietary solutions in smart mobility ecosystems.

Unsupervised novelty detection (UND), aimed at identifying novel samples, is essential in fields like medical diagnosis, cybersecurity, and industrial quality control. Most existing UND methods assume that the training data and testing normal data originate from the same domain and only consider the distribution variation between training data and testing data. However, in real scenarios, it is common for normal testing and training data to originate from different domains, a challenge known as domain shift. The discrepancies between training and testing data often lead to incorrect classification of normal data as novel by existing methods. A typical situation is that testing normal data and training data describe the same subject, yet they differ in the background conditions. To address this problem, we introduce a novel method that separates subject information from background variation encapsulating the domain information to enhance detection performance under domain shifts. The proposed method minimizes the mutual information between the representations of the subject and background while modelling the background variation using a deep Gaussian mixture model, where the novelty detection is conducted on the subject representations solely and hence is not affected by the variation of domains. Extensive experiments demonstrate that our model generalizes effectively to unseen domains and significantly outperforms baseline methods, especially under substantial domain shifts between training and testing data.

This report presents UniAnimate-DiT, an advanced project that leverages the cutting-edge and powerful capabilities of the open-source Wan2.1 model for consistent human image animation. Specifically, to preserve the robust generative capabilities of the original Wan2.1 model, we implement Low-Rank Adaptation (LoRA) technique to fine-tune a minimal set of parameters, significantly reducing training memory overhead. A lightweight pose encoder consisting of multiple stacked 3D convolutional layers is designed to encode motion information of driving poses. Furthermore, we adopt a simple concatenation operation to integrate the reference appearance into the model and incorporate the pose information of the reference image for enhanced pose alignment. Experimental results show that our approach achieves visually appearing and temporally consistent high-fidelity animations. Trained on 480p (832x480) videos, UniAnimate-DiT demonstrates strong generalization capabilities to seamlessly upscale to 720P (1280x720) during inference. The training and inference code is publicly available at https://github.com/ali-vilab/UniAnimate-DiT.

Accurately predicting spatio-temporal network traffic is essential for dynamically managing computing resources in modern communication systems and minimizing energy consumption. Although spatio-temporal traffic prediction has received extensive research attention, further improvements in prediction accuracy and computational efficiency remain necessary. In particular, existing decomposition-based methods or hybrid architectures often incur heavy overhead when capturing local and global feature correlations, necessitating novel approaches that optimize accuracy and complexity. In this paper, we propose an efficient spatio-temporal network traffic prediction framework, DP-LET, which consists of a data processing module, a local feature enhancement module, and a Transformer-based prediction module. The data processing module is designed for high-efficiency denoising of network data and spatial decoupling. In contrast, the local feature enhancement module leverages multiple Temporal Convolutional Networks (TCNs) to capture fine-grained local features. Meanwhile, the prediction module utilizes a Transformer encoder to model long-term dependencies and assess feature relevance. A case study on real-world cellular traffic prediction demonstrates the practicality of DP-LET, which maintains low computational complexity while achieving state-of-the-art performance, significantly reducing MSE by 31.8% and MAE by 23.1% compared to baseline models.

The exponential growth of AI-generated images (AIGIs) underscores the urgent need for robust and generalizable detection methods. In this paper, we establish two key principles for AIGI detection through systematic analysis: (1) All Patches Matter: Unlike conventional image classification where discriminative features concentrate on object-centric regions, each patch in AIGIs inherently contains synthetic artifacts due to the uniform generation process, suggesting that every patch serves as an important artifact source for detection. (2) More Patches Better: Leveraging distributed artifacts across more patches improves detection robustness by capturing complementary forensic evidence and reducing over-reliance on specific patches, thereby enhancing robustness and generalization. However, our counterfactual analysis reveals an undesirable phenomenon: naively trained detectors often exhibit a Few-Patch Bias, discriminating between real and synthetic images based on minority patches. We identify Lazy Learner as the root cause: detectors preferentially learn conspicuous artifacts in limited patches while neglecting broader artifact distributions. To address this bias, we propose the Panoptic Patch Learning (PPL) framework, involving: (1) Random Patch Replacement that randomly substitutes synthetic patches with real counterparts to compel models to identify artifacts in underutilized regions, encouraging the broader use of more patches; (2) Patch-wise Contrastive Learning that enforces consistent discriminative capability across all patches, ensuring uniform utilization of all patches. Extensive experiments across two different settings on several benchmarks verify the effectiveness of our approach.