Lu Jiang

33

Papers

1,034

Total Citations

1

Affiliations

Affiliations

Google Research

Papers (33)

Language Model Beats Diffusion - Tokenizer is key to visual generation

Photorealistic Video Generation with Diffusion Models

SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

Long Context Tuning for Video Generation

RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval

RATT: A Thought Structure for Coherent and Correct LLM Reasoning

Spatial-Temporal Interplay in Human Mobility: A Hierarchical Reinforcement Learning Approach with Hypergraph Representation

Text-Driven Image Editing via Learnable Regions

VideoPoet: A Large Language Model for Zero-Shot Video Generation

Focal Visual-Text Attention for Visual Question Answering

Contrastive Adaptation Network for Unsupervised Domain Adaptation

Peeking Into the Future: Predicting Future Person Activities and Locations in Videos

Composing Text and Image for Image Retrieval - an Empirical Odyssey

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

Faster Meta Update Strategy for Noise-Robust Deep Learning

Regularizing Generative Adversarial Networks Under Limited Data

Pyramid Adversarial Training Improves ViT Performance

MaskGIT: Masked Generative Image Transformer

Visual Prompt Tuning for Generative Transfer Learning

MAGVIT: Masked Generative Video Transformer

A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection

Neural Design Network: Graphic Layout Generation with Constraints

BLT: Bidirectional Layout Transformer for Controllable Layout Generation

Improved Masked Image Generation with Token-Critic

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

Synthetic Video Enhances Physical Fidelity in Video Synthesis

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

VideoAuteur: Towards Long Narrative Video Generation

Reducing AUV Energy Consumption Through Dynamic Sensor Directions Switching via Deep Reinforcement Learning

Beyond Prompt Engineering: A Reinforced Token-Level Input Refinement for Large Language Models

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

StyleDrop: Text-to-Image Synthesis of Any Style

MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels