Junnan Li

papers

6,934

total citations

papers (13)

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

NEURIPS 2023arXiv

2,995

citations

Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

NEURIPS 2021arXiv

2,525

citations

BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

NEURIPS 2023arXiv

480

citations

VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

CVPR 2025arXiv

citations

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning

ECCV 2024

citations

Learning From Noisy Data With Robust Representation Learning

ICCV 2021

citations

From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models

CVPR 2023

citations

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

ECCV 2020

citations

Junnan Li

papers (13)

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

CoMatch: Semi-Supervised Learning With Contrastive Graph Regularization

Align and Prompt: Video-and-Language Pre-Training With Entity Prompts

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding

Open Vocabulary Object Detection with Pseudo Bounding-Box Labels

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning

Learning From Noisy Data With Robust Representation Learning

From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

papers (13)

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

CoMatch: Semi-Supervised Learning With Contrastive Graph Regularization

Align and Prompt: Video-and-Language Pre-Training With Entity Prompts

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding

Open Vocabulary Object Detection with Pseudo Bounding-Box Labels

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning

Learning From Noisy Data With Robust Representation Learning

From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation