1376 papers
This paper introduces OddGridBench, a benchmark revealing that current multimodal large language models significantly underperform humans in detecting fine-grained visual discrepancies, and proposes OddGrid-GRPO, a reinforcement learning framework that effectively enhances this sensitivity through curriculum learning and distance-aware rewards.
The paper presents NLiPsCalib, an efficient and physics-consistent calibration framework that utilizes Near-Light Photometric Stereo and controllable light sources to enable high-fidelity 3D reconstruction of curved visuotactile sensors through simple contacts with everyday objects, thereby overcoming the cost and complexity of existing methods.
The paper introduces IntroSVG, an introspective framework that enhances text-to-SVG generation by employing a unified Visual Language Model in a closed-loop "generate-review-refine" cycle, where the model acts as both generator and critic to iteratively improve outputs based on visual rendering feedback.
The paper introduces See, Plan, Rewind (SPR), a progress-aware vision-language-action framework that enhances robotic manipulation robustness by dynamically grounding instructions into spatial subgoals and enabling closed-loop error recovery through state rewinding, achieving state-of-the-art performance on challenging benchmarks without additional training.
The paper introduces MDTrack, a novel multimodal object tracking framework that achieves state-of-the-art performance by employing a Mixture of Experts for adaptive modality-aware fusion and utilizing decoupled State Space Models with cross-attention mechanisms for independent yet synergistic temporal propagation.
CogBlender is a novel framework that enables continuous, multi-dimensional control over the cognitive properties of text-to-image generation by mapping cognitive space to visual semantics and dynamically steering the flow-matching process through interpolated velocity fields guided by cognitive anchors.
This paper introduces a novel, self-supervised feature field learning approach that enables the first feed-forward model for open-world 3D convex decomposition, producing high-quality, generalizable results across diverse representations like meshes, CAD models, and Gaussian splats to accelerate applications such as collision detection.
The paper introduces Stable Video Object Removal (SVOR), a robust framework that achieves state-of-the-art, flicker-free video object removal under real-world imperfections by employing a Mask Union strategy for stable erasure, a Denoising-Aware Segmentation head for precise localization, and a Curriculum Two-Stage training approach to handle shadows, abrupt motion, and defective masks.
This paper proposes novel training strategies and losses, including Gaussian scale resetting and an entropy constraint on alpha blending, to shorten the Gaussian lists used in 3D Gaussian splatting, thereby significantly accelerating the learning process without compromising rendering quality.
ForgeDreamer is a novel text-to-3D generation framework designed for industrial applications that overcomes domain adaptation and geometric reasoning limitations by integrating a Multi-Expert LoRA Ensemble for interference-free cross-category generalization and a Cross-View Hypergraph approach for capturing high-order structural dependencies to ensure manufacturing-level precision.
This paper introduces a large-scale framework for Vision-and-Language Navigation that leverages web-based room tour videos and implicit geometry representations to overcome simulator limitations, enabling robust zero-shot navigation agents with state-of-the-art performance across multiple benchmarks.
This paper proposes DiP, a novel multimodal graph representation learning framework that utilizes modality-specific pseudo nodes and dynamic information pathways to achieve adaptive, sparse, and linear-complexity message propagation, consistently outperforming existing baselines in link prediction and node classification tasks.
This paper introduces Poly-DETR, a lightweight instance segmentation framework that reformulates the task as sparse vertex regression using polar representation and specialized attention mechanisms, achieving superior performance and reduced memory consumption compared to traditional mask-based methods, particularly in high-resolution and domain-specific scenarios.
This paper introduces Geometric Semantic Decoupling (GSD), a parameter-free module that enhances the generalizability of AI-generated image detectors by explicitly removing dominant semantic priors from learned representations, thereby forcing models to rely on robust forensic artifacts rather than failing via "semantic fallback" when encountering unseen generation pipelines.
The paper proposes RAE-NWM, a navigation world model that operates in a dense DINOv2 feature space using a Conditional Diffusion Transformer with a decoupled head and time-driven gating to achieve superior structural stability and action accuracy compared to traditional latent-space approaches.
HelixTrack is a fully event-driven method that jointly tracks propeller-like objects and estimates their RPM with microsecond latency by back-warping events to a rotor plane and refining pose through phase-coupled geometry, validated on a newly introduced TQE dataset where it outperforms existing baselines.
The paper introduces UniField, a unified framework that leverages pre-trained 3D foundation models and a novel Field-Aware Spectral Rectification Mechanism to overcome data scarcity and spectral bias in MRI field-strength enhancement, supported by the release of a large-scale multi-field dataset that significantly outperforms state-of-the-art methods.
This paper proposes a lightweight distributed convolutional neural network (DisCNN) trained with a novel loss function that maps positive samples to a compact high-dimensional space while pushing negative samples to the origin, thereby disentangling positive-class features to achieve robust object recognition and detection even in complex backgrounds and for unseen classes.
TubeMLLM is a unified foundation model that integrates topological priors via natural language prompting and a shared-attention architecture to achieve state-of-the-art, robust, and zero-shot generalizable topology-aware perception and generation for vessel-like anatomy across diverse medical imaging modalities.
This paper proposes a geometry-aware metric learning framework using rotation- and scale-invariant inter-joint angle descriptors derived from static hand keypoints to achieve robust cross-lingual few-shot sign language recognition, significantly outperforming conventional coordinate-based methods across diverse sign languages.