Picture for Runjian Chen

Runjian Chen

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

Add code
Apr 24, 2024
Figure 1 for MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Figure 2 for MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Figure 3 for MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Figure 4 for MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Viaarxiv icon

Towards Implicit Prompt For Text-To-Image Models

Add code
Mar 08, 2024
Figure 1 for Towards Implicit Prompt For Text-To-Image Models
Figure 2 for Towards Implicit Prompt For Text-To-Image Models
Figure 3 for Towards Implicit Prompt For Text-To-Image Models
Figure 4 for Towards Implicit Prompt For Text-To-Image Models
Viaarxiv icon

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

Add code
Feb 25, 2024
Viaarxiv icon

CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement

Add code
Nov 20, 2023
Figure 1 for CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
Figure 2 for CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
Figure 3 for CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
Figure 4 for CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
Viaarxiv icon

SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving

Add code
Sep 25, 2023
Figure 1 for SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
Figure 2 for SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
Figure 3 for SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
Figure 4 for SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
Viaarxiv icon

MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training

Add code
Mar 23, 2023
Figure 1 for MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
Figure 2 for MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
Figure 3 for MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
Figure 4 for MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
Viaarxiv icon

Failure-aware Policy Learning for Self-assessable Robotics Tasks

Add code
Feb 25, 2023
Figure 1 for Failure-aware Policy Learning for Self-assessable Robotics Tasks
Figure 2 for Failure-aware Policy Learning for Self-assessable Robotics Tasks
Figure 3 for Failure-aware Policy Learning for Self-assessable Robotics Tasks
Figure 4 for Failure-aware Policy Learning for Self-assessable Robotics Tasks
Viaarxiv icon

CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer

Add code
Jun 17, 2022
Figure 1 for CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Figure 2 for CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Figure 3 for CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Figure 4 for CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Viaarxiv icon

CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving

Add code
Jun 08, 2022
Figure 1 for CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
Figure 2 for CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
Figure 3 for CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
Figure 4 for CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
Viaarxiv icon

RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs

Add code
Jan 17, 2022
Figure 1 for RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs
Figure 2 for RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs
Figure 3 for RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs
Figure 4 for RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs
Viaarxiv icon