Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
hub Canonical reference
Zero-Shot Text-to-Image Generation
Canonical reference. 70% of citing Pith papers cite this work as background.
33
Pith papers citing it
Background
70% of classified citations
abstract
Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part labels or segmentation masks supplied during training. We describe a simple approach for this task based on a transformer that autoregressively models the text and image tokens as a single stream of data. With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.
hub tools
citation-role summary
background 8
method 2
citation-polarity summary
representative citing papers
LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
LiveGesture introduces the first fully streamable zero-lookahead co-speech full-body gesture generation model using a causal vector-quantized tokenizer and hierarchical autoregressive transformers that matches offline SOTA on BEAT2.
FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.
LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
Latent diffusion models achieve state-of-the-art inpainting and competitive results on unconditional generation, scene synthesis, and super-resolution by performing the diffusion process in the latent space of pretrained autoencoders with cross-attention conditioning, while cutting computational and
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
LAION-400M is a publicly released open dataset of 400 million CLIP-filtered image-text pairs with embeddings and kNN indices for efficient search.
BEiT pre-trains vision transformers via masked image modeling on visual tokens and reaches 83.2% ImageNet top-1 accuracy for the base model and 86.3% for the large model using only ImageNet-1K data.
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.
SEDGE provides conditions and algorithms for reliably generating extrapolated data outside the training distribution under structural assumptions on the data-generating process.
MoT decouples non-embedding parameters by modality in transformers to match dense multi-modal performance with roughly one-third to one-half the FLOPs.
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
Chameleon is an early-fusion token model that handles mixed image-text sequences for understanding and generation, achieving competitive or superior performance to larger models like Llama-2, Mixtral, and Gemini-Pro on captioning, VQA, text, and image tasks.
VideoPoet is a large language model that performs zero-shot video generation with audio from diverse multimodal conditioning signals.
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
HPD v2 is the largest human preference dataset for text-to-image images with 798k choices, and HPS v2 is the resulting CLIP-based scorer that better predicts human judgments and responds to model improvements.
DDPO uses policy gradients on the denoising process to optimize diffusion models for arbitrary rewards like human feedback or compressibility.
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
EVA-CLIP delivers improved CLIP training recipes that yield 82.0% zero-shot ImageNet-1K accuracy for a 5B-parameter model after only 9 billion samples.
citing papers explorer
-
Decision Transformer: Reinforcement Learning via Sequence Modeling
Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
-
LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
-
Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
-
LiveGesture Streamable Co-Speech Gesture Generation Model
LiveGesture introduces the first fully streamable zero-lookahead co-speech full-body gesture generation model using a causal vector-quantized tokenizer and hierarchical autoregressive transformers that matches offline SOTA on BEAT2.
-
FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.
-
LAION-5B: An open large-scale dataset for training next generation image-text models
LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.
-
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
-
Hierarchical Text-Conditional Image Generation with CLIP Latents
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
-
High-Resolution Image Synthesis with Latent Diffusion Models
Latent diffusion models achieve state-of-the-art inpainting and competitive results on unconditional generation, scene synthesis, and super-resolution by performing the diffusion process in the latent space of pretrained autoencoders with cross-attention conditioning, while cutting computational and
-
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
-
LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
LAION-400M is a publicly released open dataset of 400 million CLIP-filtered image-text pairs with embeddings and kNN indices for efficient search.
-
BEiT: BERT Pre-Training of Image Transformers
BEiT pre-trains vision transformers via masked image modeling on visual tokens and reaches 83.2% ImageNet top-1 accuracy for the base model and 86.3% for the large model using only ImageNet-1K data.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
-
Ensemble Distributionally Robust Bayesian Optimisation
A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.
-
SEDGE: Structural Extrapolated Data Generation
SEDGE provides conditions and algorithms for reliably generating extrapolated data outside the training distribution under structural assumptions on the data-generating process.
-
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
MoT decouples non-embedding parameters by modality in transformers to match dense multi-modal performance with roughly one-third to one-half the FLOPs.
-
Emu3: Next-Token Prediction is All You Need
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
-
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Chameleon is an early-fusion token model that handles mixed image-text sequences for understanding and generation, achieving competitive or superior performance to larger models like Llama-2, Mixtral, and Gemini-Pro on captioning, VQA, text, and image tasks.
-
VideoPoet: A Large Language Model for Zero-Shot Video Generation
VideoPoet is a large language model that performs zero-shot video generation with audio from diverse multimodal conditioning signals.
-
Demystifying CLIP Data
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
-
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
HPD v2 is the largest human preference dataset for text-to-image images with 798k choices, and HPS v2 is the resulting CLIP-based scorer that better predicts human judgments and responds to model improvements.
-
Training Diffusion Models with Reinforcement Learning
DDPO uses policy gradients on the denoising process to optimize diffusion models for arbitrary rewards like human feedback or compressibility.
-
Shap-E: Generating Conditional 3D Implicit Functions
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
-
EVA-CLIP: Improved Training Techniques for CLIP at Scale
EVA-CLIP delivers improved CLIP training recipes that yield 82.0% zero-shot ImageNet-1K accuracy for a 5B-parameter model after only 9 billion samples.
-
Text and Code Embeddings by Contrastive Pre-Training
Contrastive pre-training on unsupervised data at scale creates text and code embeddings that set new state-of-the-art results on classification and semantic search benchmarks.
-
Florence: A New Foundation Model for Computer Vision
Florence is a new vision foundation model that learns universal visual-language representations from web-scale data and reports state-of-the-art results on 44 benchmarks including 83.74% zero-shot ImageNet top-1 accuracy.
-
GSPMD: General and Scalable Parallelization for ML Computation Graphs
GSPMD automatically infers tensor partitioning from limited user annotations to parallelize single-device ML programs across thousands of TPUs, reporting 50-62% utilization for up to trillion-parameter models.
-
VideoGPT: Video Generation using VQ-VAE and Transformers
VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.
-
Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction
Rennala MVR improves time complexity over Rennala SGD for smooth nonconvex stochastic optimization in heterogeneous parallel systems under a mean-squared smoothness assumption.
-
Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models
Target-based prompting lets users define fairness distributions for skin tones in generative AI, shifting outputs closer to chosen targets across 36 tested prompts for occupations and contexts.
-
DetailCLIP: Injecting Image Details into CLIP's Feature Space
A patch-based fusion method extends CLIP to high-resolution images by retaining multi-scale details for improved class-prompted retrieval.
-
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
CogVideo is a large-scale transformer pretrained for text-to-video generation that outperforms public models in evaluations.
- BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps