1863 papers
The paper proposes C2FMAE, a coarse-to-fine masked autoencoder that resolves the tension between global semantics and local details in self-supervised learning by employing a cascaded decoder and progressive masking curriculum on a newly constructed multi-granular dataset to achieve hierarchical visual understanding and superior performance across various vision tasks.
This paper introduces BEACON, a language-conditioned navigation system that overcomes the limitations of existing 2D image-space methods by predicting an occlusion-aware Bird's-Eye View affordance heatmap from surround-view RGB-D observations, thereby significantly improving the accuracy of inferring traversable targets in occluded regions.
ReCoSplat is an autoregressive feed-forward Gaussian Splatting model that overcomes the training-inference pose mismatch dilemma through a novel Render-and-Compare module and achieves state-of-the-art online novel view synthesis with efficient long-sequence handling via hybrid KV cache compression.
This paper challenges the standard view of superposition in neural networks by demonstrating that, unlike in idealized uncorrelated settings where interference is merely noise, realistic feature correlations allow models to arrange features so that interference becomes constructive, thereby naturally forming the semantic clusters and cyclical structures observed in real language models.
This paper introduces "differentiable microscopy" (), a data-driven, top-down design framework that automatically optimizes optical systems for phase retrieval, demonstrating superior performance over existing methods and experimentally validating its effectiveness on biological samples.
This paper proposes a mutual conditional blended-target domain adaptation framework that aligns categorical distributions and rectifies classifier bias through uncertainty-guided discrimination and low-level feature augmentation, achieving state-of-the-art performance even without explicit domain labels and under label distribution shifts.
The paper introduces altiro3D, a free library that synthesizes realistic 3D experiences and novel views from a single RGB image or video by combining monocular depth estimation, inpainting, and optimized projection algorithms to generate multi-viewpoint light fields for free-view displays.
This paper introduces PD-REAL, a novel large-scale RGB-D dataset for unsupervised anomaly detection based on Play-Doh models, and proposes a multi-scale teacher-student framework with hierarchical distillation that leverages 3D information to achieve superior detection accuracy compared to existing methods.
DivCon introduces a divide-and-conquer framework that decouples text-to-image generation into simplified numerical/spatial reasoning and progressive object synthesis steps, enabling lightweight models to achieve superior layout accuracy and perceptual quality for complex multi-object prompts without relying on closed-source large language models.
This paper presents a comprehensive survey and benchmark of deepfake generation and detection, unifying task definitions, reviewing state-of-the-art methods across four key generation fields and forgery detection, and analyzing current challenges and future research directions.
This paper proposes three high-quality, controlled test sets (Hadrian, Eclipse, and ND-Twins) designed to challenge face verification models on natural variations in facial attributes and similar-looking identities, while introducing "Goldilocks" rules to ensure balanced difficulty and demographic fairness without artificially degrading image quality.
This paper identifies a "corruption stage" in few-shot fine-tuned diffusion models caused by a narrowed learning distribution and proposes a Bayesian Neural Network approach with variational inference to broaden this distribution, thereby mitigating corruption and improving image fidelity, quality, and diversity without additional inference costs.
This paper proposes RDM, a recurrent diffusion model that leverages Normalizing Flows to condition generation on preceding noisy frames, enabling efficient, long-duration human motion synthesis with reduced computational costs while maintaining high alignment with text prompts.
The paper proposes PiVOT, a visual prompting mechanism that leverages a pretrained CLIP foundation model to automatically generate and refine online visual prompts, thereby enhancing generic object tracking by effectively suppressing distractors through contrastive guidance.
ExpGest is a novel diffusion-based framework that generates expressive, controllable full-body gestures by leveraging synchronized audio and text guidance, along with a specialized noise emotion classifier, to overcome the limitations of existing methods that often produce stiff, upper-body-only movements.
This paper introduces a neurosymbolic system that reconstructs medical images using visual primitives to generate high-level structural explanations, achieving superior classification accuracy and transparency compared to conventional deep learning models in diagnosing histological abnormalities.
This paper proposes an input-adaptive framework for diffusion models that dynamically adjusts the generative trajectory and sampling steps for each sample based on its complexity, thereby maintaining generation quality while reducing the average number of required steps.
This paper introduces HarmonicEval, a reference-free, multi-criteria evaluation metric for vision-language models that aggregates criterion-wise scores to better align with human judgments across diverse multi-modal tasks, supported by the newly constructed MMHE benchmark containing 18,000 expert human evaluations.
This paper proposes a method that leverages pretrained vision-language models to learn compact, abstract symbolic world models from limited visual demonstrations, enabling zero-shot generalization and long-horizon planning for complex robotic tasks across novel objects, environments, and goals.
This paper proposes efficient data reduction strategies for semi-supervised adversarial training that utilize latent clustering techniques to select or generate critical boundary-adjacent samples, significantly reducing data requirements and computational costs while maintaining state-of-the-art robustness.