Jiachen Li

Affiliations

University of California, Santa Barbara

papers

1,405

total citations

papers (21)

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

ICLR 2025arXiv

citations

Reward Guided Latent Consistency Distillation

ICLR 2025arXiv

citations

Interaction Modeling with Multiplex Attention

NEURIPS 2022arXiv

citations

UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

ICCV 2025arXiv

citations

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning

ICML 2024arXiv

citations

BCOT: A Markerless High-Precision 3D Object Tracking Benchmark

CVPR 2022arXiv

citations

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

NEURIPS 2020arXiv

citations

Multi-task Batch Reinforcement Learning with Metric Learning

NEURIPS 2020arXiv

citations

RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks

NEURIPS 2025arXiv

citations

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

CVPR 2025arXiv

citations

Prior-free 3D Object Tracking

CVPR 2025

citations

Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint

CVPR 2022

citations

Uncertainty-Aware Diffusion-Guided Refinement of 3D Scenes

ICCV 2025arXiv

citations

Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation

CVPR 2022

citations

Jiachen Li

Affiliations

papers (21)

OneFormer: One Transformer To Rule Universal Image Segmentation

Neighborhood Attention Transformer

LOKI: Long Term and Key Intentions for Trajectory Prediction

Shared Cross-Modal Trajectory Prediction for Autonomous Driving

Point-to-Box Network for Accurate Object Detection via Single Point Supervision

Learning Physical Dynamics with Subequivariant Graph Neural Networks

RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

Reward Guided Latent Consistency Distillation

Interaction Modeling with Multiplex Attention

UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning

BCOT: A Markerless High-Precision 3D Object Tracking Benchmark

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

Multi-task Batch Reinforcement Learning with Metric Learning

RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

Prior-free 3D Object Tracking

Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint

Uncertainty-Aware Diffusion-Guided Refinement of 3D Scenes

Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation

papers (21)

OneFormer: One Transformer To Rule Universal Image Segmentation

Neighborhood Attention Transformer

LOKI: Long Term and Key Intentions for Trajectory Prediction

Shared Cross-Modal Trajectory Prediction for Autonomous Driving

Point-to-Box Network for Accurate Object Detection via Single Point Supervision

Learning Physical Dynamics with Subequivariant Graph Neural Networks

RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

Reward Guided Latent Consistency Distillation

Interaction Modeling with Multiplex Attention

UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning

BCOT: A Markerless High-Precision 3D Object Tracking Benchmark

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

Multi-task Batch Reinforcement Learning with Metric Learning

RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

Prior-free 3D Object Tracking

Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint

Uncertainty-Aware Diffusion-Guided Refinement of 3D Scenes

Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation