4069 papers
CityGuard is a privacy-preserving, graph-aware transformer framework that enables robust, bias-resilient person re-identification across distributed urban cameras by integrating dispersion-adaptive metric learning, spatially conditioned attention for coarse geometric alignment, and differentially private embeddings to balance retrieval accuracy with data protection.
The paper introduces CARE, a molecular-guided foundation model that utilizes a two-stage pretraining strategy to automatically partition whole slide images into biologically relevant, adaptive regions, achieving superior performance across diverse pathology tasks with significantly less pretraining data than existing models.
This paper introduces MasqLoRA, the first systematic framework that exploits the modular nature of Low-Rank Adaptation (LoRA) to stealthily inject backdoors into text-to-image diffusion models, enabling attackers to trigger malicious visual outputs via specific textual prompts while maintaining benign behavior otherwise.
The paper introduces RobustVisRAG, a causality-guided dual-path framework that disentangles visual semantics from degradation factors to significantly improve retrieval and generation performance under various visual distortions, validated by a new large-scale benchmark and substantial experimental gains.
This paper proposes LFG, a label-free, teacher-guided framework that leverages unposed, in-the-wild ego-centric videos to pretrain a unified pseudo-4D representation for autonomous driving, achieving state-of-the-art planning performance on the NAVSIM benchmark using only a single monocular camera without relying on poses, labels, or LiDAR.
Diffusion Probe is a model-agnostic framework that leverages statistical properties of early-stage cross-attention maps in text-to-image diffusion models to accurately predict final image quality, thereby enabling efficient early termination of low-potential generations and reducing computational overhead.
DiffusionHarmonizer is an online, single-step generative framework that leverages a custom data curation pipeline to transform imperfect neural reconstruction renderings into temporally consistent, photorealistic simulations, effectively resolving artifacts and harmonizing inserted dynamic objects for autonomous robot development.
UFO-4D introduces a unified feedforward framework that reconstructs dense, explicit 4D representations from just two unposed images by jointly estimating dynamic 3D Gaussian splats, geometry, motion, and camera pose through a self-supervised approach that leverages shared geometric primitives to significantly outperform prior methods.
Dr. Seg challenges the assumption that language-based GRPO training transfers seamlessly to visual perception by introducing a plug-and-play framework with a Look-to-Confirm mechanism and Distribution-Ranked Reward module that significantly enhances performance in complex visual scenarios without requiring architectural modifications.
This paper proposes AlignVAR, a globally consistent visual autoregressive framework for image super-resolution that overcomes locality bias and error accumulation through Spatial Consistency Autoregression and Hierarchical Consistency Constraint, achieving superior structural coherence and perceptual fidelity with significantly faster inference and fewer parameters than diffusion-based methods.
The paper introduces SOLACE, a fully unsupervised post-training framework for text-to-image generation that leverages intrinsic self-confidence signals derived from noise recovery to optimize model performance without external reward models or annotated datasets.
Dr. Occ is a novel 3D semantic occupancy prediction framework for autonomous driving that leverages a depth-guided view transformer for precise geometric alignment and a region-guided expert transformer to address spatial class imbalance, achieving significant performance improvements over existing vision-only baselines on the Occ3D-nuScenes benchmark.
FreeAct is a novel quantization framework that improves Large Language Model performance by relaxing rigid one-to-one transformation constraints to dynamically allocate token-specific activation transformations, thereby addressing the distinct distribution patterns in diffusion and multimodal models.
Kiwi-Edit addresses the limitations of instruction-based video editing and the scarcity of reference-guided training data by introducing a scalable data generation pipeline to create the RefVIE dataset and a unified architecture that synergizes learnable queries with latent visual features to achieve state-of-the-art controllable video editing.
Track4World is a feedforward model that enables efficient, holistic 3D tracking of every pixel in a monocular video by leveraging a global 3D scene representation and a novel 3D correlation scheme to simultaneously estimate dense 2D/3D flows and reconstruct 4D dynamics.
The paper introduces PVT-GDLA, a linear-time decoder architecture featuring Gated Differential Linear Attention that combines noise-canceling kernel paths, adaptive gating, and local token mixing to achieve state-of-the-art, high-fidelity medical image segmentation with superior efficiency compared to existing CNN and Transformer baselines.
This paper introduces MultiShadow, a diffusion-based framework that leverages multimodal conditioning and attention mechanisms to generate physically plausible, geometrically consistent shadows for multiple foreground objects simultaneously, addressing a critical gap in existing single-object shadow generation methods.
The paper introduces IoUCert, a novel formal verification framework that overcomes the challenges of non-linear coordinate transformations and IoU metrics to enable the first robustness verification of realistic, anchor-based object detection models like SSD and YOLO.
This paper proposes a DMD-augmented Unpaired Neural Schrödinger Bridge framework that enhances Ultra-Low Field (64 mT) MRI image quality by leveraging diffusion-guided distribution matching and anatomical structure preservation to achieve superior realism and structural fidelity in translating unpaired 64 mT scans to 3 T quality.
The paper presents TumorFlow, a biophysically-conditioned generative framework that synthesizes realistic, patient-specific 3D longitudinal MRI sequences of glioblastoma growth by integrating tumor-infiltration maps with mechanistic growth models to enable controllable progression visualization and synthetic data generation.