CEA assembles per-token low-rank residual updates via dense affinities over hyper-adapter-generated components to improve all-in-one image restoration on spatially non-uniform degradations.
Title resolution pending
11 Pith papers cite this work. Polarity classification is still indexing.
years
2026 11representative citing papers
Training on automatically generated hard negative captions improves vision-language models' zero-shot detection of fine-grained image-text mismatches and robustness to noisy inputs.
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
HARMES is the first large-scale dataset to combine wrist IMU, environmental, and audio sensors for recognizing 15 household activities across over 80 hours of data from 20 participants.
Error in approximating the tangent conditional score by the unconditional score in diffusion models is bounded by dimension-free conditional mutual information, with a projected-Langevin method outperforming baselines in inpainting and super-resolution.
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
SIAM achieves state-of-the-art whole-head MRI segmentation of 16 structures including extra-cerebral tissues by training on synthetic data from just six manual templates, matching or exceeding prior methods on 301 scans across eight heterogeneous datasets.
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
ProtoFair introduces a fairness-aware contrastive loss that uses unsupervised prototype clustering to create pseudo-counterfactual pairs, encouraging representations invariant to sensitive attributes while integrating with standard SSL frameworks.
Gaussian and linear cropping strategies for large point clouds improve 3D neural network performance over spherical crops, especially in outdoor scenes, and achieve new state-of-the-art results.
The paper delivers a chronological history of Fréchet distances connecting early abstract set theory to curve metrics, optimal transport, and the FID metric in generative models.
citing papers explorer
-
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
CEA assembles per-token low-rank residual updates via dense affinities over hyper-adapter-generated components to improve all-in-one image restoration on spatially non-uniform degradations.
-
HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
Training on automatically generated hard negative captions improves vision-language models' zero-shot detection of fine-grained image-text mismatches and robustness to noisy inputs.
-
Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
-
HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound
HARMES is the first large-scale dataset to combine wrist IMU, environmental, and audio sensors for recognizing 15 household activities across over 80 hours of data from 20 participants.
-
Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees
Error in approximating the tangent conditional score by the unconditional score in diffusion models is bounded by dimension-free conditional mutual information, with a projected-Langevin method outperforming baselines in inpainting and super-resolution.
-
Advancing Aesthetic Image Generation via Composition Transfer
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
-
SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training
SIAM achieves state-of-the-art whole-head MRI segmentation of 16 structures including extra-cerebral tissues by training on synthetic data from just six manual templates, matching or exceeding prior methods on 301 scans across eight heterogeneous datasets.
-
MooD: Perception-Enhanced Efficient Affective Image Editing via Continuous Valence-Arousal Modeling
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
-
ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs
ProtoFair introduces a fairness-aware contrastive loss that uses unsupervised prototype clustering to create pseudo-counterfactual pairs, encouraging representations invariant to sensitive attributes while integrating with standard SSL frameworks.
-
From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments
Gaussian and linear cropping strategies for large point clouds improve 3D neural network performance over spherical crops, especially in outdoor scenes, and achieve new state-of-the-art results.
-
A Brief History of Fr\'echet Distances: From Curves and Probability Laws to FID
The paper delivers a chronological history of Fréchet distances connecting early abstract set theory to curve metrics, optimal transport, and the FID metric in generative models.