DDN: Discrete Distribution Networks - A Novel Generative Model for Image Reconstruction
By
diyer22
Hand-rolled, kettle-boiled, baked to perfection. Worth every minute at the bakery.
Summary
DDN (Discrete Distribution Networks) is a novel generative model accepted by ICLR 2025 that introduces a unique approach to image generation and reconstruction. The model operates by having each layer output multiple distinct images to approximate distributions, with a sampler selecting the most similar image to feed into subsequent layers. As the number of layers increases, the model progressively refines its output. The paper presents contributions in generative modeling with simple principles and unique properties, and the code has been publicly released.
Key quotes
· 5 pulledDDN: Discrete Distribution Networks
Accepted by ICLR 2025
The code has been released
Each layer of DDN outputs distinct images to approximate the distribution
The sampler then selects the image most similar to the target from these and feeds it into the next DDN layer
You might also wanna read
Feedback Distillation: A New Training Method for Improving LLM Reasoning in Theorem Proving
This paper introduces Feedback Distillation, a novel training method for reasoning models that improves upon standard GRPO (Group Relative P
arxiv.org·2h ago
PromptEmbedder: A Dual-LLM Framework for Efficient, Architecture-Agnostic Text Embedding
The article presents PromptEmbedder, a novel dual-LLM framework for efficient and transferable text embedding. It addresses the bottleneck o
arxiv.org·4d ago
Unified Framework for Variational Quantum Knowledge Graph Embeddings on NISQ Devices
This paper introduces a unified framework for variational quantum algorithms (VQAs) applied to knowledge graph embeddings on near-term NISQ
arxiv.org·4d ago
Contextual Rollout Bandits: A Neural Scheduling Framework for Efficient Reinforcement Learning with Verifiable Rewards
This paper introduces Contextual Rollout Bandits, a novel framework for Reinforcement Learning with Verifiable Rewards (RLVR) that addresses
arxiv.org·5d ago
Eureka: An LLM-Driven Framework for Automated Feature Engineering in Enterprise AI
This paper presents Eureka, an LLM-driven framework for automated feature engineering in machine learning. It treats feature engineering as
arxiv.org·5d ago
Sleep-Like Consolidation Mechanism Improves Long-Context Performance in Transformer Language Models
This paper proposes a sleep-like consolidation mechanism for transformer-based large language models to address the poor scaling of attentio
arxiv.org·5d ago