REVIEW 16 cited by
Deconstructing Denoising Diffusion Models for Self-Supervised Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation. Our philosophy is to deconstruct a DDM, gradually transforming it into a classical Denoising Autoencoder (DAE). This deconstructive procedure allows us to explore how various components of modern DDMs influence self-supervised representation learning. We observe that only a very few modern components are critical for learning good representations, while many others are nonessential. Our study ultimately arrives at an approach that is highly simplified and to a large extent resembles a classical DAE. We hope our study will rekindle interest in a family of classical methods within the realm of modern self-supervised learning.
Forward citations
Cited by 16 Pith papers
-
VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection
VFM4SDG is a dual-prior framework that distills cross-domain stable relations from VFMs into DETR encoders and injects semantic-contextual priors into decoder queries to reduce missed detections in single-domain gener...
-
Revisiting Autoregressive Models for Generative Image Classification
Order-marginalized any-order AR models (RandAR) outperform diffusion generative classifiers on ImageNet and OOD sets and match strong SSL models at far lower cost.
-
Exploring the Alignment of Generation and Understanding in Protein Structure Modeling
Aligning a protein diffusion generator's internal representations to a pretrained structure encoder (ProteinMPNN) raises the MotifBench motif-scaffolding score from 39.2 to 47.1 (~20% relative) over the Protpardelle-1...
-
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning uses image segmentation as a generative proxy to align misaligned representation spaces in unified multimodal models and improve both perception and generative layout fidelity.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
-
VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection
VFM⁴SDG uses a frozen vision foundation model to inject cross-domain stability priors into both the encoding and decoding stages of object detectors, reducing missed detections in unseen environments.
-
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
-
T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
A text-to-LiDAR diffusion model with self-conditioned reconstruction guidance, directional position encoding, and two >100K-pair benchmarks, supporting multiple conditioning modalities.
-
Improving Visual Representation Alignment Generation with GRPO
VRPO applies generative representation policy optimization to dynamically align diffusion features with pretrained visual encoders, claiming +1.8 FID gains and 2.3x faster training versus REPA.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
-
CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting
CoGenCast couples a Qwen-based encoder-decoder with flow matching and reports strong MSE/MAE on ten time-series benchmarks.
-
T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
T2LDM++ adds a guidance network for reconstruction-based supervision in diffusion models to generate detailed LiDAR scenes from text and builds new Text-LiDAR benchmarks.
-
Xray-Visual Models: Scaling Vision models on Industry Scale Data
A 2-billion-parameter vision encoder trained on 15B+ image-text and billions of video-hashtag pairs reports SOTA ImageNet linear-probe, Kinetics, and retrieval numbers, but relies on proprietary data and has several v...
-
Real-Time 3D Vision-Language Embedding Mapping
Combining local embedding masking with confidence-weighted 3D integration yields, the paper claims, a real-time metric-accurate 3D map of vision-language embeddings for language-guided object localization.
-
Visualising relativistic effects in redshift space distortions of large scale structure
A qualitative visual study of how higher-order relativistic corrections distort galaxy clusters and voids into egg- or bean-like shapes with broken line-of-sight symmetry in redshift space.
Discussion (0). Sign in to comment.