4370 papers
This paper proposes the Structural Action Transformer (SAT), a novel 3D dexterous manipulation policy that reframes actions as variable-length, unordered joint trajectories and utilizes an Embodied Joint Codebook to achieve superior sample efficiency and cross-embodiment skill transfer from heterogeneous datasets.
The paper introduces ProFound, a domain-specialized vision foundation model pre-trained on over 22,000 prostate MRI volumes via self-supervised learning, which demonstrates superior or competitive performance across 11 diverse clinical tasks compared to state-of-the-art specialized and foundation models.
This paper introduces BLOCK, an open-source bi-stage pipeline that leverages a large multimodal model to generate consistent 3D character previews and a fine-tuned FLUX.2 model with a novel EvolveLoRA curriculum to decode these previews into pixel-perfect Minecraft skins.
This paper proposes UniRain, a unified image deraining framework that combines a RAG-based dataset distillation pipeline for selecting high-quality training samples and a multi-objective reweighted optimization strategy within an asymmetric MoE architecture to effectively restore images degraded by diverse rain streaks and raindrops across both daytime and nighttime conditions.
This paper proposes a novel self-supervised pretraining method that leverages structure-aware distillation from visual foundation models to overcome annotation bottlenecks and semantic collapse, enabling scalable learning of versatile, fine-grained representations from dense event streams.
Dual-Solver is a generalized ODE solver for diffusion models that employs learnable parameters to dynamically interpolate prediction types, select integration domains, and adjust residuals, thereby significantly improving image quality and CLIP scores in low-function-evaluation regimes across various backbones.
This technical report introduces Phi-4-reasoning-vision-15B, a compact open-weight multimodal model that achieves competitive performance in scientific, mathematical, and UI reasoning through strategic architecture choices, rigorous data curation, and a hybrid training approach, demonstrating that smaller models can excel with significantly less compute.
GeoSeg is a training-free, zero-shot framework that leverages MLLM reasoning combined with bias-aware coordinate refinement and dual-route prompting to achieve instruction-grounded segmentation in remote sensing imagery, addressing the lack of generalizable solutions and data scarcity in the domain.
This paper introduces RIVER, a novel benchmark and framework designed to evaluate and improve the real-time interactive capabilities of video large language models by addressing their current limitations in online processing, long-term memory, and proactive anticipation through a three-task system of Retrospective Memory, Live-Perception, and Proactive Anticipation.
This paper introduces a diagnostic framework using face pareidolia to reveal that vision models' behavior under visual ambiguity is primarily governed by their representational architecture, with vision-language models exhibiting semantic overactivation, pure vision models adopting uncertainty-based abstention, and detection models relying on conservative priors to suppress false positives.
This paper introduces SAFE, a two-stage framework that leverages weak supervision, contrastive learning, and feature-space ensemble methods to systematically expand sparse expert annotations of diabetic retinopathy lesions, thereby significantly improving both patch-level detection accuracy and downstream disease classification performance.
The paper proposes DPAD, a method that enhances reasoning segmentation by introducing a discriminative perception mechanism through anchored object descriptions, which effectively guides Multimodal Large Language Models to generate more focused and efficient reasoning chains while significantly improving localization accuracy and reducing verbosity.
This paper proposes a novel framework for radiology report generation that enhances reinforcement learning efficiency through a diagnostic diversity-based data sampling strategy and a Diagnostic Token-weighted Policy Optimization (DiTPO) method, achieving state-of-the-art clinical accuracy with significantly fewer training samples by prioritizing diagnostically critical content.
The paper proposes Volumetric Directional Diffusion (VDD), a novel framework that anchors generative trajectories to a deterministic consensus prior to predict 3D boundary residuals, thereby achieving state-of-the-art anatomically coherent uncertainty quantification for ambiguous medical image segmentation while avoiding the topological fractures common in standard diffusion models.
The paper proposes DQE-CIR, a novel composed image retrieval method that enhances query discriminativeness and fine-grained retrieval accuracy by integrating learnable attribute weights for precise vision-language alignment and a target relative negative sampling strategy to mitigate relevance suppression and semantic confusion.
This paper addresses the lack of benchmarks for long-term visual localization in dynamic benthic environments by introducing a curated multi-year underwater dataset, a novel footprint-based ground-truthing method that outperforms traditional distance-threshold approaches, and a benchmark evaluation demonstrating that state-of-the-art visual place recognition methods struggle significantly in these challenging underwater settings.
This paper introduces MELT, a lightweight backdoor attack framework for multi-encoder diffusion models like Stable Diffusion 3, demonstrating that tuning fewer than 0.2% of parameters via low-rank adapters is sufficient to achieve effective attacks while identifying the minimal encoder subsets required for different objectives.
This study demonstrates that for cell-level histopathological image analysis under extreme spatial constraints, task-specific architectures trained on sufficient data outperform foundation models in both accuracy and efficiency, while offering comparable robustness to blur perturbations.
EgoPoseFormer v2 is a transformer-based framework that significantly advances egocentric human motion estimation for AR/VR by combining a novel architecture with an uncertainty-aware auto-labeling system to achieve state-of-the-art accuracy and temporal consistency on large-scale unlabeled datasets.
This paper proposes a CLIP-guided multi-task regression framework that leverages level-aware vision-language embeddings to robustly predict plant age and leaf count from multi-view imagery, achieving significant accuracy improvements on the GroMo25 benchmark while simplifying the pipeline and handling incomplete inputs.