Silent Hazards of Token Reduction in Vision-Language Models: The Hidden Impact on Consistency

Vision language models (VLMs) have excelled in visual reasoning but often incur high computational costs. One key reason is the redundancy of visual tokens. Although recent token reduction methods claim to achieve minimal performance loss, our extensive experiments reveal that token reduction can substantially alter a model's output distribution, leading to changes in prediction patterns that standard metrics such as accuracy loss do not fully capture. Such inconsistencies are especially concerning for practical applications where system stability is critical. To investigate this phenomenon, we analyze how token reduction influences the energy distribution of a VLM's internal representations using a lower-rank approximation via Singular Value Decomposition (SVD). Our results show that changes in the Inverse Participation Ratio of the singular value spectrum are strongly correlated with the model's consistency after token reduction. Based on these insights, we propose LoFi--a training-free visual token reduction method that utilizes the leverage score from SVD for token pruning. Experimental evaluations demonstrate that LoFi not only reduces computational costs with minimal performance degradation but also significantly outperforms state-of-the-art methods in terms of output consistency.

BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modelling

Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world applications demand for cross-domain approaches capable of controlled generation tailored to domain-specific constraints and instance-level requirements. In this paper, we argue that text can provide semantic insights, domain information and instance-specific temporal patterns, to guide and improve TSG. We introduce ``Text-Controlled TSG'', a task focused on generating realistic time series by incorporating textual descriptions. To address data scarcity in this setting, we propose a novel LLM-based Multi-Agent framework that synthesizes diverse, realistic text-to-TS datasets. Furthermore, we introduce BRIDGE, a hybrid text-controlled TSG framework that integrates semantic prototypes with text description for supporting domain-level guidance. This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by 12.52% on MSE and 6.34% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.

Origami-Inspired Soft Gripper with Tunable Constant Force Output

Soft robotic grippers gently and safely manipulate delicate objects due to their inherent adaptability and softness. Limited by insufficient stiffness and imprecise force control, conventional soft grippers are not suitable for applications that require stable grasping force. In this work, we propose a soft gripper that utilizes an origami-inspired structure to achieve tunable constant force output over a wide strain range. The geometry of each taper panel is established to provide necessary parameters such as protrusion distance, taper angle, and crease thickness required for 3D modeling and FEA analysis. Simulations and experiments show that by optimizing these parameters, our design can achieve a tunable constant force output. Moreover, the origami-inspired soft gripper dynamically adapts to different shapes while preventing excessive forces, with potential applications in logistics, manufacturing, and other industrial settings that require stable and adaptive operations

Learning Mask Invariant Mutual Information for Masked Image Modeling

Masked autoencoders (MAEs) represent a prominent self-supervised learning paradigm in computer vision. Despite their empirical success, the underlying mechanisms of MAEs remain insufficiently understood. Recent studies have attempted to elucidate the functioning of MAEs through contrastive learning and feature representation analysis, yet these approaches often provide only implicit insights. In this paper, we propose a new perspective for understanding MAEs by leveraging the information bottleneck principle in information theory. Our theoretical analyses reveal that optimizing the latent features to balance relevant and irrelevant information is key to improving MAE performance. Building upon our proofs, we introduce MI-MAE, a novel method that optimizes MAEs through mutual information maximization and minimization. By enhancing latent features to retain maximal relevant information between them and the output, and minimizing irrelevant information between them and the input, our approach achieves better performance. Extensive experiments on standard benchmarks show that MI-MAE significantly outperforms MAE models in tasks such as image classification, object detection, and semantic segmentation. Our findings validate the theoretical framework and highlight the practical advantages of applying the information bottleneck principle to MAEs, offering deeper insights for developing more powerful self-supervised learning models.

Mitigating the Impact of Prominent Position Shift in Drone-based RGBT Object Detection

Drone-based RGBT object detection plays a crucial role in many around-the-clock applications. However, real-world drone-viewed RGBT data suffers from the prominent position shift problem, i.e., the position of a tiny object differs greatly in different modalities. For instance, a slight deviation of a tiny object in the thermal modality will induce it to drift from the main body of itself in the RGB modality. Considering RGBT data are usually labeled on one modality (reference), this will cause the unlabeled modality (sensed) to lack accurate supervision signals and prevent the detector from learning a good representation. Moreover, the mismatch of the corresponding feature point between the modalities will make the fused features confusing for the detection head. In this paper, we propose to cast the cross-modality box shift issue as the label noise problem and address it on the fly via a novel Mean Teacher-based Cross-modality Box Correction head ensemble (CBC). In this way, the network can learn more informative representations for both modalities. Furthermore, to alleviate the feature map mismatch problem in RGBT fusion, we devise a Shifted Window-Based Cascaded Alignment (SWCA) module. SWCA mines long-range dependencies between the spatially unaligned features inside shifted windows and cascaded aligns the sensed features with the reference ones. Extensive experiments on two drone-based RGBT object detection datasets demonstrate that the correction results are both visually and quantitatively favorable, thereby improving the detection performance. In particular, our CBC module boosts the precision of the sensed modality ground truth by 25.52 aSim points. Overall, the proposed detector achieves an mAP_50 of 43.55 points on RGBTDronePerson and surpasses a state-of-the-art method by 8.6 mAP50 on a shift subset of DroneVehicle dataset. The code and data will be made publicly available.

VLA-Cache: Towards Efficient Vision-Language-Action Model via Adaptive Token Caching in Robotic Manipulation

Vision-Language-Action (VLA) model can process instructions and visual perception to directly generate actions as output in an end-to-end fashion due to its strong multi-modal reasoning capabilities. While the performance of VLA models is promising, their computational cost can be substantial. This raises challenge for applying them on robotics tasks, which requires real-time decision-making to respond quickly to environmental changes. Since robotic control involves sequential decision-making, the visual input often exhibits minimal variation between successive steps. A natural idea is to reuse the computational results of unchanged visual tokens from the last step. Motivated by this idea, we propose VLA-Cache, an efficient vision-language-action model. VLA-Cache incorporates a token-selection mechanism that compares the visual input at each step with the input from the previous step, adaptively identifying visual tokens with minimal changes. The computational results for these unchanged tokens are then reused in subsequent steps via KV-cache, thereby significantly improving the efficiency of the VLA-Cache model. Experimental results on both simulation (e.g., LIBERO benchmark and SIMPLER) and real-world robot valid VLA-Cache can achieve practical acceleration with minimal sacrifice in success rate.

Generative Physical AI in Vision: A Survey

Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication. This transformation builds upon a foundation of generative models to produce realistic images, videos, and 3D or 4D content. Traditionally, generative models primarily focus on visual fidelity while often neglecting the physical plausibility of generated content. This gap limits their effectiveness in applications requiring adherence to real-world physical laws, such as robotics, autonomous systems, and scientific simulations. As generative AI evolves to increasingly integrate physical realism and dynamic simulation, its potential to function as a "world simulator" expands-enabling the modeling of interactions governed by physics and bridging the divide between virtual and physical realities. This survey systematically reviews this emerging field of physics-aware generative AI in computer vision, categorizing methods based on how they incorporate physical knowledge-either through explicit simulation or implicit learning. We analyze key paradigms, discuss evaluation protocols, and identify future research directions. By offering a comprehensive overview, this survey aims to help future developments in physically grounded generation for vision. The reviewed papers are summarized at https://github.com/BestJunYu/Awesome-Physics-aware-Generation.

TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts

Time series generation models are crucial for applications like data augmentation and privacy preservation. Most existing time series generation models are typically designed to generate data from one specified domain. While leveraging data from other domain for better generalization is proved to work in other application areas, this approach remains challenging for time series modeling due to the large divergence in patterns among different real world time series categories. In this paper, we propose a multi-domain time series diffusion model with domain prompts, named TimeDP. In TimeDP, we utilize a time series semantic prototype module which defines time series prototypes to represent time series basis, each prototype vector serving as "word" representing some elementary time series feature. A prototype assignment module is applied to extract the extract domain specific prototype weights, for learning domain prompts as generation condition. During sampling, we extract "domain prompt" with few-shot samples from the target domain and use the domain prompts as condition to generate time series samples. Experiments demonstrate that our method outperforms baselines to provide the state-of-the-art in-domain generation quality and strong unseen domain generation capability.

Color Correction Meets Cross-Spectral Refinement: A Distribution-Aware Diffusion for Underwater Image Restoration

Underwater imaging often suffers from significant visual degradation, which limits its suitability for subsequent applications. While recent underwater image enhancement (UIE) methods rely on the current advances in deep neural network architecture designs, there is still considerable room for improvement in terms of cross-scene robustness and computational efficiency. Diffusion models have shown great success in image generation, prompting us to consider their application to UIE tasks. However, directly applying them to UIE tasks will pose two challenges, \textit{i.e.}, high computational budget and color unbalanced perturbations. To tackle these issues, we propose DiffColor, a distribution-aware diffusion and cross-spectral refinement model for efficient UIE. Instead of diffusing in the raw pixel space, we transfer the image into the wavelet domain to obtain such low-frequency and high-frequency spectra, it inherently reduces the image spatial dimensions by half after each transformation. Unlike single-noise image restoration tasks, underwater imaging exhibits unbalanced channel distributions due to the selective absorption of light by water. To address this, we design the Global Color Correction (GCC) module to handle the diverse color shifts, thereby avoiding potential global degradation disturbances during the denoising process. For the sacrificed image details caused by underwater scattering, we further present the Cross-Spectral Detail Refinement (CSDR) to enhance the high-frequency details, which are integrated with the low-frequency signal as input conditions for guiding the diffusion. This way not only ensures the high-fidelity of sampled content but also compensates for the sacrificed details. Comprehensive experiments demonstrate the superior performance of DiffColor over state-of-the-art methods in both quantitative and qualitative evaluations.

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting

Time series forecasting plays a crucial role in data mining, driving rapid advancements across numerous industries. With the emergence of large models, time series foundation models (TSFMs) have exhibited remarkable generalization capabilities, such as zero-shot learning, through large-scale pre-training. Meanwhile, Retrieval-Augmented Generation (RAG) methods have been widely employed to enhance the performance of foundation models on unseen data, allowing models to access to external knowledge. In this paper, we introduce TimeRAF, a Retrieval-Augmented Forecasting model that enhance zero-shot time series forecasting through retrieval-augmented techniques. We develop customized time series knowledge bases that are tailored to the specific forecasting tasks. TimeRAF employs an end-to-end learnable retriever to extract valuable information from the knowledge base. Additionally, we propose Channel Prompting for knowledge integration, which effectively extracts relevant information from the retrieved knowledge along the channel dimension. Extensive experiments demonstrate the effectiveness of our model, showing significant improvement across various domains and datasets.