An MLLM-guided architecture with a mixture of frequency experts and relational alignment loss achieves state-of-the-art all-in-one image restoration, outperforming prior methods by up to 1.35 dB on the CDD11 dataset.
In: International confer- ence on machine learning
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
FoCo learns composition for zero-shot CIR via text-anchored visual aggregation and context-conditioned semantic completion trained jointly with cross-instance contrastive loss, reporting SOTA on four benchmarks.
SpectraDINO extends DINOv2 with lightweight per-modality adapters and staged distillation to handle NIR, SWIR, and LWIR in one backbone, but its SWIR gain is weakened by using the evaluation dataset for pretraining.
The paper presents the first generative photomosaic framework that synthesizes tiles via structure-aligned diffusion models and few-shot personalization instead of color-based matching from large tile collections.
VLMs caption real objects effectively but degrade on 3D-printed fakes in robotic scenes, while some standard metrics fail to detect the factual errors from this domain shift.
HyperVLP uses hyperbolic geometry in surgical video-language pre-training to preserve hierarchy across actions, steps, and phases, yielding gains in zero- and few-shot phase recognition.
DE-CM trains a flow-map consistency model on three sub-trajectories (coupling, instantaneous, noise-to-noisy) and reports 1.70 FID one-step on ImageNet 256.
citing papers explorer
-
Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
An MLLM-guided architecture with a mixture of frequency experts and relational alignment loss achieves state-of-the-art all-in-one image restoration, outperforming prior methods by up to 1.35 dB on the CDD11 dataset.
-
Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval
FoCo learns composition for zero-shot CIR via text-anchored visual aggregation and context-conditioned semantic completion trained jointly with cross-instance contrastive loss, reporting SOTA on four benchmarks.
-
SpectraDINO: Modality-Conditioned Adaptation of RGB Vision Foundation Models Across Infrared Bands
SpectraDINO extends DINOv2 with lightweight per-modality adapters and staged distillation to handle NIR, SWIR, and LWIR in one backbone, but its SWIR gain is weakened by using the evaluation dataset for pretraining.
-
Generative Phomosaic with Structure-Aligned and Personalized Diffusion
The paper presents the first generative photomosaic framework that synthesizes tiles via structure-aligned diffusion models and few-shot personalization instead of color-based matching from large tile collections.
-
Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding
VLMs caption real objects effectively but degrade on 3D-printed fakes in robotic scenes, while some standard metrics fail to detect the factual errors from this domain shift.
-
HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space
HyperVLP uses hyperbolic geometry in surgical video-language pre-training to preserve hierarchy across actions, steps, and phases, yielding gains in zero- and few-shot phase recognition.
-
Dual-End Consistency Model
DE-CM trains a flow-map consistency model on three sub-trajectories (coupling, instantaneous, noise-to-noisy) and reports 1.70 FID one-step on ImageNet 256.
- NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation