Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Sunday 30 November
We present CycliST, a novel benchmark dataset designed to evaluate Video Language Models (VLM) on their ability for textual reasoning over cyclical state transitions. CycliST captures fundamental aspects of real-world processes by generating synthetic, richly structured video sequences featuring periodic patterns in object motion and visual attributes. CycliST employs a tiered evaluation system that progressively increases difficulty through variations in the number of cyclic objects, scene clutter, and lighting conditions, challenging state-of-the-art models on their spatio-temporal cognition. We conduct extensive experiments with current state-of-the-art VLMs, both open-source and proprietary, and reveal their limitations in generalizing to cyclical dynamics such as linear and orbital motion, as well as time-dependent changes in visual attributes like color and scale. Our results demonstrate that present-day VLMs struggle to reliably detect and exploit cyclic patterns, lack a notion of temporal understanding, and are unable to extract quantitative insights from scenes, such as the number of objects in motion, highlighting a significant technical gap that needs to be addressed. More specifically, we find no single model consistently leads in performance: neither size nor architecture correlates strongly with outcomes, and no model succeeds equally well across all tasks. By providing a targeted challenge and a comprehensive evaluation framework, CycliST paves the way for visual reasoning models that surpass the state-of-the-art in understanding periodic patterns.
Computer Vision
Accelerating Inference of Masked Image Generators via Reinforcement Learning
Masked Generative Models (MGM)s demonstrate strong capabilities in generating high-fidelity images. However, they need many sampling steps to create high-quality generations, resulting in slow inference speed. In this work, we propose Speed-RL, a novel paradigm for accelerating a pretrained MGMs to generate high-quality images in fewer steps. Unlike conventional distillation methods which formulate the acceleration problem as a distribution matching problem, where a few-step student model is trained to match the distribution generated by a many-step teacher model, we consider this problem as a reinforcement learning problem. Since the goal of acceleration is to generate high quality images in fewer steps, we can combine a quality reward with a speed reward and finetune the base model using reinforcement learning with the combined reward as the optimization target. Through extensive experiments, we show that the proposed method was able to accelerate the base model by a factor of 3x while maintaining comparable image quality.
Read the full abstract
Computer Vision
Generalised Medical Phrase Grounding
Medical phrase grounding (MPG) maps textual descriptions of radiological findings to corresponding image regions. These grounded reports are easier to interpret, especially for non-experts. Existing MPG systems mostly follow the referring expression comprehension (REC) paradigm and return exactly one bounding box per phrase. Real reports often violate this assumption. They contain multi-region findings, non-diagnostic text, and non-groundable phrases, such as negations or descriptions of normal anatomy. Motivated by this, we reformulate the task as generalised medical phrase grounding (GMPG), where each sentence is mapped to zero, one, or multiple scored regions. To realise this formulation, we introduce the first GMPG model: MedGrounder. We adopted a two-stage training regime: pre-training on report sentence–anatomy box alignment datasets and fine-tuning on report sentence–human annotated box datasets. Experiments on PadChest-GR and MS-CXR show that MedGrounder achieves strong zero-shot transfer and outperforms REC-style and grounded report generation baselines on multi-region and non-groundable phrases, while using far fewer human box annotations. Finally, we show that MedGrounder can be composed with existing report generators to produce grounded reports without retraining the generator.
Read the full abstract
Computer Vision · Cross-listed from cs.RO
Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer
Recent progress in GPU-accelerated, photorealistic simulation has opened a scalable data-generation path for robot learning, where massive physics and visual randomization allow policies to generalize beyond curated environments. Building on these advances, we develop a teacher-student-bootstrap learning framework for vision-based humanoid loco-manipulation, using articulated-object interaction as a representative high-difficulty benchmark. Our approach introduces a staged-reset exploration strategy that stabilizes long-horizon privileged-policy training, and a GRPO-based fine-tuning procedure that mitigates partial observability and improves closed-loop consistency in sim-to-real RL. Trained entirely on simulation data, the resulting policy achieves robust zero-shot performance across diverse door types and outperforms human teleoperators by up to 31.7% in task completion time under the same whole-body control stack. This represents the first humanoid sim-to-real policy capable of diverse articulated loco-manipulation using pure RGB perception.
Read the full abstract
Computer Vision
Parameter Reduction Improves Vision Transformers: A Comparative Study of Sharing and Width Reduction
Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on ViT-B/16 trained on ImageNet-1K, we study two simple parameter-reduction strategies applied to the MLP blocks, each removing 32.7% of the baseline parameters. Our GroupedMLP variant shares MLP weights between adjacent transformer blocks and achieves 81.47% top-1 accuracy while maintaining the baseline computational cost. Our ShallowMLP variant halves the MLP hidden dimension and reaches 81.25% top-1 accuracy with a 38% increase in inference throughput. Both models outperform the 86.6M-parameter baseline (81.05%) and exhibit substantially improved training stability, reducing peak-to-final accuracy degradation from 0.47% to the range 0.03% to 0.06%. These results suggest that, for ViT-B/16 on ImageNet-1K with a standard training recipe, the model operates in an overparameterized regime in which MLP capacity can be reduced without harming performance and can even slightly improve it. More broadly, our findings suggest that architectural constraints such as parameter sharing and reduced width may act as useful inductive biases, and highlight the importance of how parameters are allocated when designing Vision Transformers. All code is available at: https://github.com/AnanthaPadmanaban-KrishnaKumar/parameter-efficient-vit-mlps.
Read the full abstract
Computer Vision
TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
Vision-language models (VLMs) have made great strides in addressing temporal understanding tasks, which involve characterizing visual changes across a sequence of images. However, recent works have suggested that when making predictions, VLMs may rely on static feature biases, such as background or object features, rather than dynamic visual changes. Static feature biases are a type of shortcut and can contribute to systematic prediction errors on downstream tasks; as a result, identifying and characterizing error-inducing static feature biases is critical prior to real-world model deployment. In this work, we introduce TRoVe, an automated approach for discovering error-inducing static feature biases learned by temporal VLMs. Given a trained VLM and an annotated validation dataset associated with a downstream classification task, TRoVe extracts candidate static features from the dataset and scores each feature by (i) the effect of the feature on classification errors as well as (ii) the extent to which the VLM relies on the feature when making predictions. In order to quantitatively evaluate TRoVe, we introduce an evaluation framework consisting of 101 trained temporal VLMs paired with ground-truth annotations for learned static feature biases. We use this framework to demonstrate that TRoVe can accurately identify error-inducing static feature biases in VLMs, achieving a 28.6% improvement over the closest baseline. Finally, we apply TRoVe to 7 off-the-shelf VLMs and 2 temporal understanding tasks, surfacing previously-unknown static feature biases and demonstrating that knowledge of learned biases can aid in improving model performance at test time. Our code is available at https://github.com/Stanford-AIMI/TRoVe.
Read the full abstract
Computer Vision
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
Recovering pixel-wise geometric properties from a single image is fundamentally ill-posed due to appearance ambiguity and non-injective mappings between 2D observations and 3D structures. While discriminative regression models achieve strong performance through large-scale supervision, their success is bounded by the scale, quality, and diversity of available data, as well as by limited physical reasoning. Recent diffusion models exhibit powerful world priors that encode geometry and semantics learned from massive image-text data, yet directly reusing their stochastic generative formulation is suboptimal for deterministic geometric inference: the former is optimized for diverse and high-fidelity image generation, whereas the latter requires stable and accurate predictions. In this work, we propose Lotus-2, a two-stage deterministic framework for stable, accurate and fine-grained geometric dense prediction, aiming to provide an optimal adaptation protocol to fully exploit the pre-trained generative priors. Specifically, in the first stage, the core predictor employs a single-step deterministic formulation with a clean-data objective and a lightweight local continuity module (LCM) to generate globally coherent structures without grid artifacts. In the second stage, the detail sharpener performs a constrained multi-step rectified-flow refinement within the manifold defined by the core predictor, enhancing fine-grained geometry through noise-free deterministic flow matching. Using only 59K training samples, less than 1% of existing large-scale datasets, Lotus-2 establishes new state-of-the-art results in monocular depth estimation and highly competitive surface normal prediction. These results demonstrate that diffusion models can serve as deterministic world priors, enabling high-quality geometric reasoning beyond traditional discriminative and generative paradigms.
Read the full abstract
Computer Vision · Cross-listed from cs.RO
FOM-Nav: Frontier-Object Maps for Object Goal Navigation
This paper addresses the Object Goal Navigation problem, where a robot must efficiently find a target object in an unknown environment. Existing implicit memory-based methods struggle with long-term memory retention and planning, while explicit map-based approaches lack rich semantic information. To address these challenges, we propose FOM-Nav, a modular framework that enhances exploration efficiency through Frontier-Object Maps and vision-language models. Our Frontier-Object Maps are built online and jointly encode spatial frontiers and fine-grained object information. Using this representation, a vision-language model performs multimodal scene understanding and high-level goal prediction, which is executed by a low-level planner for efficient trajectory generation. To train FOM-Nav, we automatically construct large-scale navigation datasets from real-world scanned environments. Extensive experiments validate the effectiveness of our model design and constructed dataset. FOM-Nav achieves state-of-the-art performance on the MP3D and HM3D benchmarks, particularly in navigation efficiency metric SPL, and yields promising results on a real robot.
Read the full abstract
Computer Vision
LISA-3D: Lifting Language-Image Segmentation to 3D via Multi-View Consistency
Text-driven 3D reconstruction requires masks that understand free-form instructions and remain stable under viewpoint changes. We present LISA-3D, a two-stage framework that adapts the instruction-following segmenter LISA with geometry-aware Low-Rank Adaptation (LoRA) layers while keeping the SAM-3D reconstructor frozen. During training, paired RGB-D frames and camera poses define a differentiable reprojection loss that enforces cross-view agreement without additional 3D-text annotations. At deployment, the adapted segmenter can produce an RGBA prompt for SAM-3D from one RGB image; when registered RGB-D views are available, optional logit fusion further improves the prompt. On ScanRefer and Nr3D, geometry-aware tuning improves both 2D masks and lifted 3D reconstructions while updating only 11.6M parameters. Our results separate geometry-aware training gains from optional multi-view inference gains, providing a modular route from language grounding to object-centric 3D reconstruction.
Read the full abstract
Computer Vision
Provenance-Driven Reliable Semantic Medical Image Vector Reconstruction via Lightweight Blockchain-Verified Latent Fingerprints
Medical imaging is essential for clinical diagnosis, yet real-world data frequently suffers from corruption, noise, and potential tampering, challenging the reliability of AI-assisted interpretation. Conventional reconstruction techniques prioritize pixel-level recovery and may produce visually plausible outputs while compromising anatomical fidelity, an issue that can directly impact clinical outcomes. We propose a semantic-aware medical image reconstruction framework that integrates high-level latent embeddings with a hybrid U-Net architecture to preserve clinically relevant structures during restoration. To ensure trust and accountability, we incorporate a lightweight blockchain-based provenance layer using scale-free graph design, enabling verifiable recording of each reconstruction event without imposing significant overhead. Extensive evaluation across multiple datasets and corruption types demonstrates improved structural consistency, restoration accuracy, and provenance integrity compared with existing approaches. By uniting semantic-guided reconstruction with secure traceability, our solution advances dependable AI for medical imaging, enhancing both diagnostic confidence and regulatory compliance in healthcare environments.
Read the full abstract
Computer Vision
S2AM3D: Scale-controllable Part Segmentation of 3D Point Clouds
Part-level point cloud segmentation has recently attracted significant attention in 3D computer vision. Nevertheless, existing research is constrained by two major challenges: native 3D models lack generalization due to data scarcity, while introducing 2D pre-trained knowledge often leads to inconsistent segmentation results across different views. To address these challenges, we propose S2AM3D, which incorporates 2D segmentation priors with 3D consistent supervision. We design a point-consistent part encoder that aggregates multi-view 2D features through native 3D contrastive learning, producing globally consistent point features. A scale-aware prompt decoder is then proposed to enable real-time adjustment of segmentation granularity via continuous scale signals. Simultaneously, we introduce a large-scale, high-quality part-level point cloud dataset with more than 100k samples, providing ample supervision signals for model training. Extensive experiments demonstrate that S2AM3D achieves leading performance across multiple evaluation settings, exhibiting exceptional robustness and controllability when handling complex structures and parts with significant size variations.
Read the full abstract
Computer Vision
PhotoFramer: Multi-modal Image Composition Instruction
Composition matters during the photo-taking process, yet many casual users struggle to frame well-composed images. To provide composition guidance, we introduce PhotoFramer, a multi-modal composition instruction framework. Given a poorly composed image, PhotoFramer first describes how to improve the composition in natural language and then generates a well-composed example image. To train such a model, we curate a large-scale dataset. Inspired by how humans take photos, we organize composition guidance into a hierarchy of sub-tasks: shift, zoom-in, and view-change tasks. Shift and zoom-in data are sampled from existing cropping datasets, while view-change data are obtained via a two-stage pipeline. First, we sample pairs with varying viewpoints from multi-view datasets, and train a degradation model to transform well-composed photos into poorly composed ones. Second, we apply this degradation model to expert-taken photos to synthesize poor images to form training pairs. Using this dataset, we finetune a model that jointly processes and generates both text and images, enabling actionable textual guidance with illustrative examples. Extensive experiments demonstrate that textual instructions effectively steer image composition, and coupling them with exemplars yields consistent improvements over exemplar-only baselines. PhotoFramer offers a practical step toward composition assistants that make expert photographic priors accessible to everyday users.
Read the full abstract
Computer Vision
MM-ACT: Learn from Multimodal Parallel Generation to Act
A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token space and performs generation across all three modalities. MM-ACT adopts a re-mask parallel decoding strategy for text and image generation, and employs a one-step parallel decoding strategy for action generation to improve efficiency. We introduce Context-Shared Multimodal Learning, a unified training paradigm that supervises generation in all three modalities from a shared context, enhancing action generation through cross-modal learning. Experiments were conducted on the LIBERO simulation and Franka real-robot setups as well as RoboTwin2.0 to assess in-domain and out-of-domain performances respectively. Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0 with an additional gain of 9.25% from cross-modal learning. We release our codes, models and data at https://github.com/HHYHRHY/MM-ACT.
Read the full abstract
Computer Vision
Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction
Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless and readily available source of data, capturing an unparalleled diversity of human activities, objects, and environments. However, accurately and scalably extracting 4D interaction data from these in-the-wild videos remains a significant and unsolved challenge. To overcome the annotation bottleneck, we introduce an efficient sparse contact annotation paradigm. To scale this process, we develop InterPoint, a multi-modal predictor that drives a human-in-the-loop data engine. Building upon these efficiently acquired annotations, we introduce 4DHOISolver, a novel optimization framework that constrains the ill-posed 4D HOI reconstruction problem, maintaining high spatio-temporal coherence and physical plausibility. Leveraging this framework, we introduce Open4DHOI, a new large-scale 4D HOI dataset featuring a diverse catalog of 135 object types and 133 actions. Furthermore, we demonstrate the effectiveness of our reconstructions by enabling an RL-based agent to imitate the recovered motions. Data and code will be publicly available at https://github.com/wenboran2002/open4dhoi_code.
Read the full abstract
Computer Vision
Adaptive Evidential Learning for Temporal-Semantic Robustness in Moment Retrieval
In the domain of moment retrieval, accurately identifying temporal segments within videos based on natural language queries remains challenging. Traditional methods often employ pre-trained models that struggle with fine-grained information and deterministic reasoning, leading to difficulties in aligning with complex or ambiguous moments. To overcome these limitations, we explore Deep Evidential Regression (DER) to construct a vanilla Evidential baseline. However, this approach encounters two major issues: the inability to effectively handle modality imbalance and the structural differences in DER's heuristic uncertainty regularizer, which adversely affect uncertainty estimation. This misalignment results in high uncertainty being incorrectly associated with accurate samples rather than challenging ones. Our observations indicate that existing methods lack the adaptability required for complex video scenarios. In response, we propose Debiased Evidential Learning for Moment Retrieval (DEMR), a novel framework that incorporates a Reflective Flipped Fusion (RFF) block for cross-modal alignment and a query reconstruction task to enhance text sensitivity, thereby reducing bias in uncertainty estimation. Additionally, we introduce a Geom-regularizer to refine uncertainty predictions, enabling adaptive alignment with difficult moments and improving retrieval accuracy. Extensive testing on standard datasets and debiased datasets ActivityNet-CD and Charades-CD demonstrates significant enhancements in effectiveness, robustness, and interpretability, positioning our approach as a promising solution for temporal-semantic robustness in moment retrieval. The code is publicly available at https://github.com/KaijingOfficial/DEMR.
Read the full abstract
Computer Vision
Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentation
3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms. To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability. Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference.
Read the full abstract
Computer Vision
SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding
Grounding complex, compositional visual queries with multiple objects and relationships is a fundamental challenge for vision-language models. While standard phrase grounding methods excel at localizing single objects, they lack the structural inductive bias to parse intricate relational descriptions, often failing as queries become more descriptive. To address this structural deficit, we focus on scene-graph grounding, a powerful but less-explored formulation where the query is an explicit graph of objects and their relationships. However, existing methods for this task also struggle, paradoxically showing decreased performance as the query graph grows – failing to leverage the very information that should make grounding easier. We introduce SceneProp, a novel method that resolves this issue by reformulating scene-graph grounding as a Maximum a Posteriori (MAP) inference problem in a Markov Random Field (MRF). By performing global inference over the entire query graph, SceneProp finds the optimal assignment of image regions to nodes that jointly satisfies all constraints. This is achieved within an end-to-end framework via a differentiable implementation of the Belief Propagation algorithm. Experiments on four benchmarks show that our dedicated focus on the scene-graph grounding formulation allows SceneProp to significantly outperform prior work. Critically, its accuracy consistently improves with the size and complexity of the query graph, demonstrating for the first time that more relational context can, and should, lead to better grounding. Codes are available at https://github.com/keitaotani/SceneProp.
Read the full abstract
Computer Vision
LAHNet: Local Attentive Hashing Network for Point Cloud Registration
Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field is essential for enhancing feature distinctiveness. In this paper, we propose a Local Attentive Hashing Network for point cloud registration, called LAHNet, which introduces a local attention mechanism with the inductive bias of locality of convolution-like operators into point cloud descriptors. Specifically, a Group Transformer is designed to capture reasonable long-range context between points. This employs a linear neighborhood search strategy, Locality-Sensitive Hashing, enabling uniformly partitioning point clouds into non-overlapping windows. Meanwhile, an efficient cross-window strategy is adopted to further expand the reasonable feature receptive field. Furthermore, building on this effective windowing strategy, we propose an Interaction Transformer to enhance the feature interactions of the overlap regions within point cloud pairs. This computes an overlap matrix to match overlap regions between point cloud pairs by representing each window as a global signal. Extensive results demonstrate that LAHNet can learn robust and distinctive features, achieving significant registration results on real-world indoor and outdoor benchmarks.
Read the full abstract
Computer Vision
ForamDeepSlice: A High-Accuracy Deep Learning Framework for Foraminifera Species Classification from 2D Micro-CT Slices
This study presents a comprehensive deep learning pipeline for the automated classification of foraminifera species using 2D micro-CT slices derived from 3D scans. We curated a scientifically rigorous dataset of 97 micro-CT scanned specimens spanning 27 species, from which we selected 12 representative species with sufficient specimen counts (at least four 3D models each) for robust classification. To ensure methodological integrity and prevent data leakage, we employed specimen-level data splitting, resulting in 109,617 high-quality 2D slices (44,103 for training, 14,046 for validation, and 51,468 for testing). We evaluated seven state-of-the-art 2D convolutional neural network (CNN) architectures using transfer learning. Our final ensemble model, ForamDeepSlice (FDS), combining ConvNeXt-Large and EfficientNetV2-Small, achieved a test accuracy of 95.64%, with a top-3 accuracy of 99.6% and an area under the ROC curve (AUC) of 0.998 across all species. To facilitate practical deployment, we developed an interactive advanced dashboard that supports real-time slice classification and 3D slice matching using advanced similarity metrics, including SSIM, NCC, and the Dice coefficient. This work establishes new benchmarks for AI-assisted micropaleontological identification and provides a fully reproducible framework for foraminifera classification research, bridging the gap between deep learning and applied geosciences.
Read the full abstract
Computer Vision
Learning Projection-Aware 360-Degree Image Rectification via Dual-Projection Fusion
Panoramic cameras provide a 360{\deg} field of view and are widely used in panoramic vision, immersive visual computing, and robotic perception. However, changes in camera orientation can produce non-upright panoramas, introducing geometric variations that can complicate downstream visual analysis. Existing vision-based rectification methods usually operate within a single projection domain, limiting their ability to jointly exploit local geometric structures and global contextual information. To address this, we formulate 360{\deg} image rectification as a projection-aware representation learning problem and propose a dual-projection framework for upright panoramic rectification. A convolutional neural network branch captures local geometric structures from equirectangular projection (ERP) inputs, while a vision transformer branch models global contextual cues from cubemap projections. Cross-projection feature transformation and multi-level feature fusion enable effective interaction between these complementary representations. The learned representation supports collaborative inclination estimation and upright panorama generation, with the two tasks providing complementary geometric and appearance supervision. Experiments on SUN360 and M3D show consistent improvements over existing methods, achieving accuracies within a 1{\deg} error threshold of 65.9% and 85.2% and Fréchet Inception Distance scores of 5.87 and 3.26, respectively. Ablation studies verify the contributions of dual-projection representation, cross-projection feature transformation and fusion, and collaborative multi-task learning. The proposed framework provides a projection-aware visual computing approach for panoramic rectification. Code, pretrained models, and training/testing scripts are available at https://github.com/YuhaoShine/DualProjectionFusion.
Read the full abstract
Computer Vision
TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model
Recent advancements in diffusion models have significantly improved the realism and generalizability of character-driven animation, enabling the synthesis of high-quality motion from just a single RGB image and a set of driving poses. Nevertheless, generating temporally coherent long-form content remains challenging. Existing approaches are constrained by computational and memory limitations, as they are typically trained on short video segments, thus performing effectively only over limited frame lengths and hindering their potential for extended coherent generation. To address these constraints, we propose TalkingPose, a novel diffusion-based framework specifically designed for producing long-form, temporally consistent human upper-body animations. TalkingPose leverages driving frames to precisely capture expressive facial and hand movements, transferring these seamlessly to a target actor through a stable diffusion backbone. To ensure continuous motion and enhance temporal coherence, we introduce a feedback-driven mechanism built upon image-based diffusion models. Notably, this mechanism does not incur additional computational costs or require secondary training stages, enabling the generation of animations with unlimited duration. Additionally, we introduce a comprehensive, large-scale dataset to serve as a new benchmark for human upper-body animation.
Read the full abstract
Computer Vision
Hierarchical Semantic Alignment for Image Clustering
Image clustering is a classic problem in computer vision, which categorizes images into different groups. Recent studies utilize nouns as external semantic knowledge to improve clustering performance. However, these methods often overlook the inherent ambiguity of nouns, which can distort semantic representations and degrade clustering quality. To address this issue, we propose a hierarChical semAntic alignmEnt method for image clustering, dubbed CAE, which improves clustering performance in a training-free manner. In our approach, we incorporate two complementary types of textual semantics: caption-level descriptions, which convey fine-grained attributes of image content, and noun-level concepts, which represent high-level object categories. We first select relevant nouns from WordNet and descriptions from caption datasets to construct a semantic space aligned with image features. Then, we align image features with selected nouns and captions via optimal transport to obtain a more discriminative semantic space. Finally, we combine the enhanced semantic and image features to perform clustering. Extensive experiments across 8 datasets demonstrate the effectiveness of our method, notably surpassing the state-of-the-art training-free approach with a 4.2% improvement in accuracy and a 2.9% improvement in adjusted rand index (ARI) on the ImageNet-1K dataset.
Read the full abstract
Computer Vision
SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been explored, but it compromises spatiotemporal reasoning. Although some methods suggest that incorporating additional 3D inputs can help, they usually rely on large VLMs to fuse 3D and 2D inputs and still lack temporal understanding. Therefore, we propose SwiftVLA, an architecture that enhances a compact model with 4D understanding while preserving design efficiency. Specifically, our approach features a pretrained 4D visual geometry transformer with a temporal cache that extracts 4D features from 2D images. Then, to enhance the VLM's ability to exploit both 2D images and 4D features, we introduce Fusion Tokens, a set of learnable tokens trained with a future prediction objective to generate unified representations for action generation. Finally, we introduce a mask-and-reconstruct strategy that masks 4D inputs to the VLM and trains the VLA to reconstruct them, enabling the VLM to learn effective 4D representations and allowing the 4D branch to be dropped at inference with minimal performance loss. Experiments in real and simulated environments show that SwiftVLA outperforms lightweight baselines and rivals VLAs up to 7 times larger, achieving comparable performance on edge devices while being 18 times faster and reducing memory footprint by 12 times.
Read the full abstract
Computer Vision
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams. In streaming video scenarios, the primary bottleneck lies in the Vision Transformer (ViT) encoding stage, where redundant processing of temporally similar frames leads to inefficiency. Additionally, inflated token sequences during LLM pre-filling further exacerbate latency and memory overhead. To address these challenges, we propose Streaming Token Compression (STC), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs, optimizing both ViT encoding and LLM pre-filling stages to accelerate processing. STC introduces two token-level accelerators: STC-Cacher, which reduces ViT encoding overhead by caching and reusing features from temporally similar frames, and STC-Pruner, which compresses the visual token sequence before it enters the LLM, preserving only the most salient tokens based on both spatial and temporal relevance. Extensive experiments on four baseline streaming VideoLLMs across five benchmarks demonstrate that STC outperforms other compression methods. Notably, STC retains up to 99% of accuracy on the ReKV framework while reducing ViT encoding latency and LLM pre-filling latency by 24.5% and 45.3%.
Read the full abstract
Computer Vision
Multilingual Training-Free Remote Sensing Image Captioning
Remote sensing image captioning has advanced rapidly through encoder–decoder models, although the reliance on large annotated datasets and the focus on English restricts global applicability. To address these limitations, we propose the first training-free multilingual approach, based on retrieval-augmented prompting. For a given aerial image, we employ a domain-adapted SigLIP2 encoder to retrieve related captions and few-shot examples from a datastore, which are then provided to a language model. We explore two variants: an image-blind setup, where a multilingual Large Language Model (LLM) generates the caption from textual prompts alone, and an image-aware setup, where a Vision–Language Model (VLM) jointly processes the prompt and the input image. To improve the coherence of the retrieved content, we introduce a graph-based re-ranking strategy using PageRank on a graph of images and captions. Experiments on four benchmark datasets across ten languages demonstrate that our approach is competitive with fully supervised English-only systems and generalizes to other languages. Results also highlight the importance of re-ranking with PageRank, yielding up to 35% improvements in performance metrics. Additionally, it was observed that while VLMs tend to generate visually grounded but lexically diverse captions, LLMs can achieve stronger BLEU and CIDEr scores. Lastly, directly generating captions in the target language consistently outperforms other translation-based strategies. Overall, our work delivers one of the first systematic evaluations of multilingual, training-free captioning for remote sensing imagery, advancing toward more inclusive and scalable multimodal Earth observation systems.
Read the full abstract
Computer Vision
HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
Hand-object interaction (HOI) inherently involves dynamics where human manipulations produce distinct spatio-temporal effects on objects. However, existing semantic HOI benchmarks focused either on manipulation or on the resulting effects at a coarse level, lacking fine-grained spatio-temporal reasoning to capture the underlying dynamics in HOI. We introduce HanDyVQA, a fine-grained video question-answering benchmark that comprehensively covers both the manipulation and effect aspects of HOI. HanDyVQA comprises six complementary question types (Action, Process, Objects, Location, State Change, and Object Parts), totalling 11.1K multiple-choice QA pairs. Collected QA pairs recognizing manipulation styles, hand/object motions, and part-level state changes. HanDyVQA also includes 10.3K segmentation masks for Objects and Object Parts questions, enabling the evaluation of object/part-level reasoning in video object segmentation. We evaluated recent video foundation models on our benchmark and found that even the best-performing model, Gemini-2.5-Pro, reached only 73% average accuracy, which is far from human performance (97%). Further analysis shows the remaining challenges in spatial relationship, motion, and part-level geometric understanding. We also found that integrating explicit HOI-related cues into visual features improves performance, offering insights for developing future models with a deeper understanding of HOI dynamics.
Read the full abstract
Computer Vision · Cross-listed from cs.MM
Audio-Visual World Models: Learning Physically Grounded Multisensory Dynamics
World models simulate environmental dynamics to enable embodied agents to plan and reason about future states. While real-world perception is inherently multimodal, existing approaches focus primarily on visual observations, leaving crucial spatial and temporal acoustic cues underexplored. In this work, we present a unified formulation of Audio-Visual World Models (AVWM), casting multimodal environment simulation under action control as a partially observable Markov decision process with synchronized audio-visual observations. As a foundational benchmark, we construct AVW-4k, comprising 30 hours of action-annotated binaural audio-visual trajectories across 76 indoor environments. To capture these physically grounded multisensory dynamics, we propose AV-CDiT (Audio-Visual Conditional Diffusion Transformer), featuring a novel modality expert architecture that balances visual and auditory learning, optimized via a three-stage training strategy. Extensive experiments demonstrate that AV-CDiT achieves high-fidelity prediction across both visual and auditory modalities. Furthermore, we validate its practical utility in embodied navigation, showing that AVWM significantly enhances a pretrained agent in continuous audio-visual navigation tasks.
Read the full abstract
Computer Vision
Look, Recite, Then Answer: Enhancing VLM Performance via Self-Generated Knowledge Hints
Vision-Language Models (VLMs) exhibit significant performance plateaus in specialized domains like precision agriculture, primarily due to "Reasoning-Driven Hallucination" where linguistic priors override visual perception. A key bottleneck is the "Modality Gap": visual embeddings fail to reliably activate the fine-grained expert knowledge already encoded in model parameters. We propose "Look, Recite, Then Answer," a parameter-efficient framework that enhances VLMs via self-generated knowledge hints while keeping backbone models frozen. The framework decouples inference into three stages: (1) Look generates objective visual descriptions and candidate sets; (2) Recite employs a lightweight 1.7B router to transform visual cues into targeted queries that trigger candidate-specific parametric knowledge; (3) Answer performs parallel evidence alignment between descriptions and recited knowledge to select the most consistent label. On AgroBench, our method achieves state-of-the-art results, improving Weed Identification accuracy by 23.52% over Qwen2-VL-72B and surpassing GPT-4o without external search overhead. This modular design mitigates hallucinations by transforming passive perception into active, controllable knowledge retrieval
Read the full abstract
Computer Vision
Quantum-Inspired Spectral Geometry for Neural Operator Equivalence and Structured Pruning
The rapid growth of multimodal intelligence on resource-constrained and heterogeneous domestic hardware exposes critical bottlenecks: multimodal feature heterogeneity, real-time requirements in dynamic scenarios, and hardware-specific operator redundancy. This work introduces a quantum-inspired geometric framework for neural operators that represents each operator by its normalized singular value spectrum on the Bloch hypersphere. We prove a tight spectral-to-functional equivalence theorem showing that vanishing Fubini–Study/Wasserstein-2 distance implies provable functional closeness, establishing the first rigorous foundation for cross-modal and cross-architecture operator substitutability. Based on this metric, we propose Quantum Metric-Driven Functional Redundancy Graphs (QM-FRG) and one-shot structured pruning. Controlled simulation validates the superiority of the proposed metric over magnitude and random baselines. An extensive experimental validation on large-scale multimodal transformers and domestic heterogeneous hardware (Huawei Ascend, Cambricon MLU, Kunlunxin) hardware is deferred to an extended journal version currently in preparation.
Read the full abstract
Computer Vision
Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling
3D Gaussian Splatting (3DGS) has emerged as a revolutionary 3D representation. However, its substantial data size poses a major barrier to widespread adoption. While feed-forward 3DGS compression offers a practical alternative to costly per-scene per-train compressors, existing methods struggle to model long-range spatial dependencies, due to the limited receptive field of transform coding networks and the inadequate context capacity in entropy models. In this work, we propose a novel feed-forward 3DGS compression framework that effectively models long-range correlations to enable highly compact and generalizable 3D representations. Central to our approach is a large-scale context structure that comprises thousands of Gaussians based on Morton serialization. We then design a fine-grained space-channel auto-regressive entropy model to fully leverage this expansive context. Furthermore, we develop an attention-based transform coding model to extract informative latent priors by aggregating features from a wide range of neighboring Gaussians. Our method yields a $20\times$ compression ratio for 3DGS in a feed-forward inference and achieves state-of-the-art performance among generalizable codecs.