OcclusionFormer adds explicit Z-order modeling via a new SA-Z dataset and volume-rendering compositing in a diffusion transformer to resolve occlusion ambiguities in layout-grounded image synthesis.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
representative citing papers
A new shared video-image tokenizer enables large language models to surpass diffusion models on standard visual generation benchmarks.
TRACE’s fixed-k cross-entropy mask search and COPAIR’s coarse-pair warm-start raise search-based visual attribution faithfulness and enable high single-point RePOPE repair rates.
PTA adapts VLMs at test time by maintaining and updating class-specific knowledge prototypes from test samples, achieving higher accuracy than cache-based methods with far less speed loss.
MARCO achieves new state-of-the-art semantic correspondence on SPair-71k, AP-10K and PF-PASCAL by combining coarse-to-fine refinement with self-distillation on DINOv2, delivering larger gains at fine thresholds and on unseen keypoints and categories while using 3x fewer parameters and running 10x更快.
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
A two-stage alignment framework that first fuses visual modalities (RGB, flow, skeleton) then introduces text, achieving 21% SRCC improvement on a new clinical AQA dataset and gains on two public benchmarks.
DiffRGD is a plug-and-play inference-time guidance method that casts each diffusion sampling step as constrained optimization on a spherical manifold and solves it with Riemannian gradient descent to preserve the Gaussian latent structure.
CARE is a parameter-efficient framework that aggregates predictions from noisy labels, VLM text embeddings, and visual features with class-frequency-based agreement thresholds to rectify labels in long-tailed noisy datasets.
Intermediate layers in LLMs consistently provide stronger features than final layers across tasks and architectures, as quantified by a new framework of information-theoretic, geometric, and invariance metrics.
citing papers explorer
-
OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation
OcclusionFormer adds explicit Z-order modeling via a new SA-Z dataset and volume-rendering compositing in a diffusion transformer to resolve occlusion ambiguities in layout-grounded image synthesis.
-
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
A new shared video-image tokenizer enables large language models to surpass diffusion models on standard visual generation benchmarks.
-
A Good Initialization is All You Need for Faithful Visual Attribution
TRACE’s fixed-k cross-entropy mask search and COPAIR’s coarse-pair warm-start raise search-based visual attribution faithfulness and enable high single-point RePOPE repair rates.
-
Prototype-Based Test-Time Adaptation of Vision-Language Models
PTA adapts VLMs at test time by maintaining and updating class-specific knowledge prototypes from test samples, achieving higher accuracy than cache-based methods with far less speed loss.
-
MARCO: Navigating the Unseen Space of Semantic Correspondence
MARCO achieves new state-of-the-art semantic correspondence on SPair-71k, AP-10K and PF-PASCAL by combining coarse-to-fine refinement with self-distillation on DINOv2, delivering larger gains at fine thresholds and on unseen keypoints and categories while using 3x fewer parameters and running 10x更快.
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment
A two-stage alignment framework that first fuses visual modalities (RGB, flow, skeleton) then introduces text, achieving 21% SRCC improvement on a new clinical AQA dataset and gains on two public benchmarks.
-
DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent
DiffRGD is a plug-and-play inference-time guidance method that casts each diffusion sampling step as constrained optimization on a spherical manifold and solves it with Riemannian gradient descent to preserve the Gaussian latent structure.
-
CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
CARE is a parameter-efficient framework that aggregates predictions from noisy labels, VLM text embeddings, and visual features with class-frequency-based agreement thresholds to rectify labels in long-tailed noisy datasets.
-
Layer by Layer: Uncovering Hidden Representations in Language Models
Intermediate layers in LLMs consistently provide stronger features than final layers across tasks and architectures, as quantified by a new framework of information-theoretic, geometric, and invariance metrics.