3919 papers
FedARKS is a novel federated learning framework for person re-identification that overcomes the limitations of global feature reliance and uniform averaging by introducing Robust Knowledge and Knowledge Selection mechanisms to capture subtle domain-invariant details and prioritize high-quality client contributions for improved domain generalization.
The paper proposes Cross-Resolution Distribution Matching Distillation (RMD), a novel framework that bridges cross-resolution distribution gaps using logSNR-based mapping and noise re-injection to achieve high-fidelity, few-step multi-resolution cascaded inference with up to 33.4X speedup on SDXL and 25.6X on Wan2.1-14B.
Place-it-R1 is an end-to-end framework that leverages Multimodal Large Language Models (MLLMs) with Chain-of-Thought reasoning to orchestrate video diffusion via a "Think-then-Place" paradigm, ensuring physically consistent and environment-aware video object insertion through iterative refinement and user-controllable plausibility-fidelity trade-offs.
This paper introduces Spatial Colour Mixing as a stress test revealing that Vision-Language Models suffer from systematic perceptual weaknesses under structured color distortions where humans remain robust, suggesting that perception-aware preprocessing can significantly improve model reliability.
This paper introduces a Virtual Treatment (VT) framework that utilizes dose-aware multimodal conditional image-to-image translation, specifically leveraging diffusion-based models, to synthesize plausible longitudinal CT scans of non-small cell lung cancer (NSCLC) tumor evolution under radiotherapy, thereby supporting in-silico treatment monitoring and adaptive radiotherapy research.
This paper introduces VLM-RobustBench, a comprehensive benchmark evaluating the robustness of four vision-language model families across 133 corruption settings, revealing that current models are semantically strong but spatially fragile, with low-severity geometric distortions causing significantly larger performance drops than visually severe photometric corruptions.
This paper introduces Reflective Flow Sampling (RF-Sampling), a training-free, theoretically-grounded inference framework that significantly enhances text-prompt alignment and generation quality for flow-based models like FLUX by implicitly performing gradient ascent on alignment scores through flow inversion and textual representation integration.
FreeOcc is a training-free pipeline that leverages pretrained foundation models to generate dense 3D semantic and panoptic occupancy predictions from multi-view images without requiring domain-specific training, achieving performance comparable to state-of-the-art weakly supervised methods.
This paper proposes a semi-supervised framework for breast ultrasound segmentation that leverages training-free, appearance-based prompts in vision-language models to generate structurally consistent pseudo-labels, which are then refined through a dual-teacher mechanism and contrastive learning to achieve fully supervised-level performance with only 2.5% labeled data.
JOPP-3D is a novel open-vocabulary semantic segmentation framework that jointly leverages panoramic images and 3D point clouds to enable language-driven scene understanding, achieving significant performance improvements over state-of-the-art methods in both 2D and 3D domains.
This paper proposes a novel framework that enhances 3D medical image generation by fine-tuning pre-trained diffusion models with Proximal Policy Optimization guided by a multi-scale reward system, resulting in improved image quality and superior utility for downstream clinical classification tasks.
This paper addresses the scalability limitations of training-free diffusion segmentors by identifying and bridging gaps in attention map aggregation and token score imbalances through proposed techniques of auto aggregation and per-pixel rescaling, thereby enabling better utilization of powerful generative models for semantic segmentation.
This paper proposes a two-stage framework that first trains a contrastive encoder on labeled invented alphabets and then uses teacher-student distillation to learn unsupervised, deformation-invariant embeddings for historically attested scripts, effectively bridging supervised discriminative learning with unsupervised discovery of latent cross-script similarities without requiring ground-truth evolutionary relationships.
This paper introduces the Motion Turing Test framework and the HHMotion dataset to evaluate human-likeness in humanoid robots by analyzing kinematic data, revealing current motion deviations and demonstrating that a specialized baseline model outperforms multimodal large language models in automatically predicting human-likeness scores.
This paper introduces CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that leverages patient context, guideline-based severity weighting, and a comprehensive error taxonomy to achieve superior alignment with radiologist judgments compared to existing metrics.
The paper introduces SpaCRD, a transfer learning-based multimodal deep fusion method that integrates histology images and spatial transcriptomics data to achieve robust and accurate cancer region detection across diverse samples, platforms, and batches, outperforming existing state-of-the-art methods.
This paper proposes ALANet, an adaptive language-aware network that effectively removes complex image reflections by integrating filtering and optimization strategies to mitigate the negative impact of inaccurate machine-generated language descriptions, alongside the introduction of a new CRLAV dataset for evaluation.
This paper introduces a point-supervised framework for skeleton-based human action segmentation that leverages multimodal features and a novel pseudo-labeling strategy to achieve competitive performance with significantly reduced annotation costs compared to fully-supervised methods.
VG3S is a novel framework that enhances 3D semantic occupancy prediction for autonomous driving by integrating strong geometric priors from frozen Vision Foundation Models into Gaussian splatting via a hierarchical feature adapter, achieving significant performance gains on the nuScenes benchmark.
The paper introduces CoE, a training-free multimodal summarization framework that leverages a Hierarchical Event Graph to guide a Chain-of-Events reasoning process, effectively addressing limitations in cross-modal grounding and temporal modeling while achieving state-of-the-art performance across diverse datasets.