NeurIPS 2025 论文列表

We introduce Cycle-Sync, a robust and global framework for estimating camera poses (both rotations and locations). Our core innovation is a location solver that adapts message-passing least squares (MPLS) - originally developed for group synchronization - to the camera localization setting. We modify MPLS to emphasize cycle-consistent information, redefine cycle consistencies using estimated distances from previous iterations, and incorporate a Welsch-type robust loss. We establish the strongest known deterministic exact-recovery guarantee for camera location estimation, demonstrating that cycle consistency alone enables the lowest sample complexity to date. To further boost robustness, we introduce a plug-and-play outlier rejection module inspired by robust subspace recovery, and we fully integrate cycle consistency into MPLS for rotation averaging. Our global approach avoids the need for bundle adjustment. Experiments on synthetic and real datasets show that Cycle-Sync consistently outperforms leading pose estimators, including full structure-from-motion pipelines with bundle adjustment.

Stereo Depth Estimation in real-world environments poses significant challenges due to dynamic domain shifts, sparse or unreliable supervision, and the high cost of acquiring dense ground-truth labels. While recent Test-Time Adaptation (TTA) methods offer promising solutions, most rely on static target domain assumptions and input-invariant adaptation strategies, limiting their effectiveness under continual shifts. In this paper, we propose RobIA, a novel Robust, Instance-Aware framework for Continual Test-Time Adaptation (CTTA) in stereo depth estimation. RobIA integrates two key components: (1) Attend-and-Excite Mixture-of-Experts (AttEx-MoE), a parameter-efficient module that dynamically routes input to frozen experts via lightweight self-attention mechanism tailored to epipolar geometry, and (2) Robust AdaptBN Teacher, a PEFT-based teacher model that provides dense pseudo-supervision by complementing sparse handcrafted labels. This strategy enables input-specific flexibility, broad supervision coverage, improving generalization under domain shift. Extensive experiments demonstrate that RobIA achieves superior adaptation performance across dynamic target domains while maintaining computational efficiency.

Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability literature. However, recent work has demonstrated phenomenology of model representations that lies outside the scope of this hypothesis, showing signatures of hierarchical, nonlinear, and multi-dimensional features. This raises the question: do SAEs represent features that possess structure at odds with their motivating hypothesis? If not, does avoiding this mismatch help identify said features and gain further insights into neural network representations? To answer these questions, we take a construction-based approach and re-contextualize the popular matching pursuit (MP) algorithm from sparse coding to design MP-SAE—an SAE that unrolls its encoder into a sequence of residual-guided steps, allowing it to capture hierarchical and nonlinearly accessible features. Comparing this architecture with existing SAEs on a mixture of synthetic and natural data settings, we show: (i) hierarchical concepts induce conditionally orthogonal features, which existing SAEs are unable to faithfully capture, and (ii) the nonlinear encoding step of MP-SAE recovers highly meaningful features, helping us unravel shared structure in the seemingly dichotomous representation spaces of different modalities in a vision-language model, hence demonstrating the assumption that useful features are solely linearly accessible is insufficient. We also show that the sequential encoder principle of MP-SAE affords an additional benefit of adaptive sparsity at inference time, which may be of independent interest. Overall, we argue our results provide credence to the idea that interpretability should begin with the phenomenology of representations, with methods emerging from assumptions that fit it.

Large vision models (LVM) based gait recognition has achieved impressive performance. However, existing LVM-based approaches may overemphasize gait priors while neglecting the intrinsic value of LVM itself, particularly the rich, distinct representations across its multi-layers. To adequately unlock LVM's potential, this work investigates the impact of layer-wise representations on downstream recognition tasks. Our analysis reveals that LVM's intermediate layers offer complementary properties across tasks, integrating them yields an impressive improvement even without rich well-designed gait priors. Building on this insight, we propose a simple and universal baseline for LVM-based gait recognition, termed BiggerGait. Comprehensive evaluations on CCPG, CAISA-B*, SUSTech1K, and CCGR_MINI validate the superiority of BiggerGait across both within- and cross-domain tasks, establishing it as a simple yet practical baseline for gait representation learning. All the models and code are available at https://github.com/ShiqiYu/OpenGait/.

Improving the visual understanding ability of vision-language models (VLMs) is crucial for enhancing their performance across various tasks. While using multiple pretrained visual experts has shown great promise, it often incurs significant computational costs during training and inference. To address this challenge, we propose HAWAII, a novel framework that distills knowledge from multiple visual experts into a single vision encoder, enabling it to inherit the complementary strengths of several experts with minimal computational overhead. To mitigate conflicts among different teachers and switch between different teacher-specific knowledge, instead of using a fixed set of adapters for multiple teachers, we propose to use teacher-specific Low-Rank Adaptation (LoRA) adapters with a corresponding router. Each adapter is aligned with a specific teacher, avoiding noisy guidance during distillation. To enable efficient knowledge distillation, we propose fine-grained and coarse-grained distillation. At the fine-grained level, token importance scores are employed to emphasize the most informative tokens from each teacher adaptively. At the coarse-grained level, we summarize the knowledge from multiple teachers and transfer it to the student using a set of general-knowledge LoRA adapters with a router. Extensive experiments on various vision-language tasks demonstrate the superiority of HAWAII, compared to the popular open-source VLMs.

Large vision-language models (LVLMs) excel at multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We present Dropout Decoding, a novel inference-time approach that quantifies the uncertainty of visual tokens and selectively masks uncertain tokens to improve decoding. Our method measures the uncertainty of each visual token by projecting it onto the text space and decomposing it into aleatoric and epistemic components. Specifically, we focus on epistemic uncertainty, which captures perception-related errors more effectively. Inspired by dropout regularization, we introduce uncertainty-guided token dropout, which applies the dropout principle to input visual tokens instead of model parameters, and during inference rather than training. By aggregating predictions from an ensemble of masked decoding contexts, we can robustly mitigate errors arising from visual token misinterpretations. Evaluations on benchmarks including CHAIR, THRONE, and MMBench demonstrate that Dropout Decoding significantly reduces object hallucinations (OH) and enhances both reliability and quality of LVLM outputs across diverse visual contexts.

Blind-spot denoising (BSD) method is a powerful paradigm for zero-shot image denoising by training models to predict masked target pixels from their neighbors. However, they struggle with real-world noise exhibiting strong local correlations, where efforts to suppress noise correlation often weaken pixel-value dependencies, adversely affecting denoising performance. This paper presents a theoretical analysis quantifying the impact of replacing masked pixels with observations exhibiting weaker noise correlation but potentially reduced similarity, revealing a trade-off that impacts the statistical risk of the estimation. Guided by this insight, we propose a computational scheme that replaces masked pixels with distant ones of similar appearance and lower noise correlation. This strategy improves the prediction by balancing noise suppression and structural consistency. Experiments confirm the effectiveness of our method, outperforming existing zero-shot BSD methods.

State space models (SSMs) have recently garnered significant attention in computer vision. However, due to the unique characteristics of image data, adapting SSMs from natural language processing to computer vision has not outperformed the state-of-the-art convolutional neural networks (CNNs) and Vision Transformers (ViTs). Existing vision SSMs primarily leverage manually designed scans to flatten image patches into sequences locally or globally. This approach disrupts the original semantic spatial adjacency of the image and lacks flexibility, making it difficult to capture complex image structures. To address this limitation, we propose Dynamic Adaptive Scan (DAS), a data-driven method that adaptively allocates scanning orders and regions. This enables more flexible modeling capabilities while maintaining linear computational complexity and global modeling capacity. Based on DAS, we further propose the vision backbone DAMamba, which significantly outperforms popular vision Mamba models in vision tasks such as image classification, object detection, instance segmentation, and semantic segmentation. Notably, it surpasses some of the latest state-of-the-art CNNs and ViTs.

Vision-Language Models (VLMs) have demonstrated great potential in interpreting remote sensing (RS) images through language-guided semantic. However, the effectiveness of these VLMs critically depends on high-quality image-text training data that captures rich semantic relationships between visual content and language descriptions. Unlike natural images, RS lacks large-scale interleaved image-text pairs from web data, making data collection challenging. While current approaches rely primarily on rule-based methods or flagship VLMs for data synthesis, a systematic framework for automated quality assessment of such synthetically generated RS vision-language data is notably absent. To fill this gap, we propose a novel score model trained on large-scale RS vision-language preference data for automated quality assessment. Our empirical results demonstrate that fine-tuning CLIP or advanced VLMs (e.g., Qwen2-VL) with the top 30% of data ranked by our score model achieves superior accuracy compared to both full-data fine-tuning and CLIP-score-based ranking approaches. Furthermore, we demonstrate applications of our scoring model for reinforcement learning (RL) training and best-of-N (BoN) test-time scaling, enabling significant improvements in VLM performance for RS tasks. Our code, model, and dataset are publicly available.

Joint Alignment (JA) of images aims to align a collection of images into a unified coordinate frame, such that semantically-similar features appear at corresponding spatial locations. Most existing approaches often require long training times, large-capacity models, and extensive hyperparameter tuning. We introduce FastJAM, a rapid, graph-based method that drastically reduces the computational complexity of joint alignment tasks. FastJAM leverages pairwise matches computed by an off-the-shelf image matcher, together with a rapid nonparametric clustering, to construct a graph representing intra- and inter-image keypoint relations. A graph neural network propagates and aggregates these correspondences, efficiently predicting per-image homography parameters via image-level pooling. Utilizing an inverse-compositional loss, that eliminates the need for a regularization term over the predicted transformations (and thus also obviates the hyperparameter tuning associated with such terms), FastJAM performs image JA quickly and effectively. Experimental results on several benchmarks demonstrate that FastJAM achieves results better than existing modern JA methods in terms of alignment quality, while reducing computation time from hours or minutes to mere seconds. Our code is available at our project webpage, https://bgu-cs-vil.github.io/FastJAM/.

We present 4KAgent, a unified agentic super-resolution generalist system designed to universally upscale any image to 4K resolution (and even higher, if applied iteratively). Our system can transform images from extremely low resolutions with severe degradations, for example, highly distorted inputs at $256\times 256$, into crystal-clear, photorealistic 4K outputs. 4KAgent comprises three core components: (1) Profiling, a module that customizes the 4KAgent pipeline based on bespoke use cases; (2) A Perception Agent, which leverages vision-language models alongside image quality assessment experts to analyze the input image and make a tailored restoration plan; and (3) A Restoration Agent, which executes the plan, following a recursive execution-reflection paradigm, guided by a quality-driven mixture-of-expert policy to select the optimal output for each step. Additionally, 4KAgent embeds a specialized face restoration pipeline, significantly enhancing facial details in portrait and selfie photos. We rigorously evaluate our 4KAgent across 11 distinct task categories encompassing a total of 26 diverse benchmarks, setting new state-of-the-art on a broad spectrum of imaging domains. Our evaluations cover natural images, portrait photos, AI-generated content, satellite imagery, fluorescence microscopy, and medical imaging like fundoscopy, ultrasound, and X-ray, demonstrating superior performance in terms of both perceptual (e.g., NIQE, MUSIQ) and fidelity (e.g., PSNR) metrics. By establishing a novel agentic paradigm for low-level vision tasks, we aim to catalyze broader interest and innovation within vision-centric autonomous agents across diverse research communities. We release all the code, models, and results at: https://4kagent.github.io.

When applied sequentially to video, frame-based networks often exhibit temporal inconsistency—for example, outputs that flicker between frames. This problem is amplified when the network inputs contain time-varying corruptions. In this work, we introduce a general approach for adapting frame-based models for stable and robust inference on video. We describe a class of stability adapters that can be inserted into virtually any architecture and a resource-efficient training process that can be performed with a frozen base network. We introduce a unified conceptual framework for describing temporal stability and corruption robustness, centered on a proposed accuracy-stability-robustness loss. By analyzing the theoretical properties of this loss, we identify the conditions where it produces well-behaved stabilizer training. Our experiments validate our approach on several vision tasks including denoising (NAFNet), image enhancement (HDRNet), monocular depth (Depth Anything v2), and semantic segmentation (DeepLabv3+). Our method improves temporal stability and robustness against a range of image corruptions (including compression artifacts, noise, and adverse weather), while preserving or improving the quality of predictions.

Deepfake detection remains a pressing challenge, particularly in real-world settings where smartphone-captured media from digital screens often introduces Moiré artifacts that can distort detection outcomes. This study systematically evaluates state-of-the-art (SOTA) deepfake detectors on Moiré-affected videos—an issue that has received little attention. We collected a dataset of 12,832 videos, spanning 35.64 hours, from Celeb-DF, DFD, DFDC, UADFV, and FF++ datasets, capturing footage under diverse real-world conditions, including varying screens, smartphones, lighting setups, and camera angles. To further examine the influence of Moiré patterns on deepfake detection, we conducted additional experiments using our DeepMoiréFake, referred to as (DMF) dataset, and two synthetic Moiré generation techniques. Across 15 top-performing detectors, our results show that Moiré artifacts degrade performance by as much as 25.4\%, while synthetically generated Moiré patterns lead to a 21.4\% drop in accuracy. Surprisingly, demoiréing methods, intended as a mitigation approach, instead worsened the problem, reducing accuracy by up to 16\%. These findings underscore the urgent need for detection models that can robustly handle Moiré distortions alongside other real-world challenges, such as compression, sharpening, and blurring. By introducing the DMF dataset, we aim to drive future research toward closing the gap between controlled experiments and practical deepfake detection.

Foundation Vision Encoders have become indispensable across a wide range of dense vision tasks. However, their operation at low spatial feature resolutions necessitates subsequent feature decompression to enable full-resolution processing. To address this limitation, we introduce JAFAR, a lightweight and flexible feature upsampler designed to enhance the spatial resolution of visual features from any Foundation Vision Encoder to any target resolution. JAFAR features an attention-based upsampling module that aligns the spatial representations of high-resolution queries with semantically enriched low-resolution keys via Spatial Feature Transform modulation. Despite the absence of high-resolution feature ground truth; we find that learning at low upsampling ratios and resolutions generalizes surprisingly well to much higher scales. Extensive experiments demonstrate that JAFAR recovers intricate pixel-level details and consistently outperforms existing feature upsampling techniques across a diverse set of dense downstream applications.

Despite their impressive performance across a wide range of tasks, Large Vision-Language Models (LVLMs) remain prone to hallucination. In this study, we propose a comprehensive intervention framework aligned with the transformer’s causal architecture in LVLMs, integrating the effects of different intervention paths on hallucination. We find that hallucinations in LVLMs do not arise from a single causal path, but rather from the interplay among image-to-input-text, image-to-output-text, and text-to-text pathways. For the first time, we also find that LVLMs rely on different pathways depending on the question–answer alignment format. Building on these insights, we propose simple yet effective methods to identify and intervene on critical hallucination heads within each pathway, tailored to discriminative and generative formats. Experiments across multiple benchmarks demonstrate that our approach consistently reduces hallucinations across diverse alignment types.

Event-based cameras offer unique advantages such as high temporal resolution, high dynamic range, and low power consumption. However, the massive storage requirements and I/O burdens of existing synthetic data generation pipelines and the scarcity of real data prevent event-based training datasets from scaling up, limiting the development and generalization capabilities of event vision models. To address this challenge, we introduce Video-to-Voxel (V2V), an approach that directly converts conventional video frames into event-based voxel grid representations, bypassing the storage-intensive event stream generation entirely. V2V enables a 150× reduction in storage requirements while supporting on-the-fly parameter randomization for enhanced model robustness. Leveraging this efficiency, we train several video reconstruction and optical flow estimation model architectures on 10,000 diverse videos totaling 52 hours—an order of magnitude larger than existing event datasets, yielding substantial improvements.

The expansion of instruction-tuning data has enabled foundation language models to exhibit improved instruction adherence and superior performance across diverse downstream tasks. Semantically-rich 3D human motion is being progressively integrated with these foundation models to enhance multimodal understanding and cross-modal generation capabilities. However, the modality gap between human motion and text raises unresolved concerns about catastrophic forgetting during this integration. In addition, developing autoregressive-compatible pose representations that preserve generalizability across heterogeneous downstream tasks remains a critical technical barrier. To address these issues, we propose the Human Motion-Vision-Language Model (HMVLM), a unified framework based on the Mixture of Expert Low-Rank Adaption(MoE LoRA) strategy. The framework leverages the gating network to dynamically allocate LoRA expert weights based on the input prompt, enabling synchronized fine-tuning of multiple tasks. To mitigate catastrophic forgetting during instruction-tuning, we introduce a novel zero expert that preserves the pre-trained parameters for general linguistic tasks. For pose representation, we implement body-part-specific tokenization by partitioning the human body into different joint groups, enhancing the spatial resolution of the representation. Experiments show that our method effectively alleviates knowledge forgetting during instruction-tuning and achieves remarkable performance across diverse human motion downstream tasks.

Computer-Aided Design (CAD) plays a foundational role in modern manufacturing and product development, often requiring designers to modify or build upon existing models. Converting 3D scans into parametric CAD representations—a process known as CAD reverse engineering—remains a significant challenge due to the high precision and structural complexity of CAD models. Existing deep learning-based approaches typically fall into two categories: bottom-up, geometry-driven methods, which often fail to produce fully parametric outputs, and top-down strategies, which tend to overlook fine-grained geometric details. Moreover, current methods neglect an essential aspect of CAD modeling: sketch-level constraints. In this work, we introduce a novel approach to CAD reverse engineering inspired by how human designers manually perform the task. Our method leverages multi-plane cross-sections to extract 2D patterns and capture fine parametric details more effectively. It enables the reconstruction of detailed and editable CAD models, outperforming state-of-the-art methods and, for the first time, incorporating sketch constraints directly into the reconstruction process.

Joint-embedding self-supervised learning (SSL) commonly relies on transformations such as data augmentation and masking to learn visual representations, a task achieved by enforcing invariance or equivariance with respect to these transformations applied to two views of an image. This dominant two-view paradigm in SSL often limits the flexibility of learned representations for downstream adaptation by creating performance trade-offs between high-level invariance-demanding tasks such as image classification and more fine-grained equivariance-related tasks. In this work, we propose $\textit{seq-JEPA}$, a world modeling framework that introduces architectural inductive biases into joint-embedding predictive architectures to resolve this trade-off. Without relying on dual equivariance predictors or loss terms, seq-JEPA simultaneously learns two architecturally segregated representations: one equivariant to specified transformations and another invariant to them. To do so, our model processes short sequences of different views (observations) of inputs. Each encoded view is concatenated with an embedding of the relative transformation (action) that produces the next observation in the sequence. These view-action pairs are passed through a transformer encoder that outputs an aggregate representation. A predictor head then conditions this aggregate representation on the upcoming action to predict the representation of the next observation. Empirically, seq-JEPA demonstrates strong performance on both equivariant and invariant benchmarks without sacrificing one for the other. Furthermore, it excels at tasks that inherently require aggregating a sequence of observations, such as path integration across actions and predictive learning across eye movements.