Picture for Rui Shao

Rui Shao

TIME: Temporal-sensitive Multi-dimensional Instruction Tuning and Benchmarking for Video-LLMs

Add code
Mar 13, 2025
Viaarxiv icon

Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation

Add code
Mar 13, 2025
Viaarxiv icon

LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant

Add code
Mar 05, 2025
Viaarxiv icon

Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy

Add code
Feb 27, 2025
Viaarxiv icon

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

Add code
Jan 27, 2025
Figure 1 for FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
Figure 2 for FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
Figure 3 for FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
Figure 4 for FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
Viaarxiv icon

SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation

Add code
Oct 19, 2024
Figure 1 for SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
Figure 2 for SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
Figure 3 for SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
Figure 4 for SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
Viaarxiv icon

Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks

Add code
Aug 07, 2024
Viaarxiv icon

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding

Add code
Jul 19, 2024
Viaarxiv icon

MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models

Add code
Jul 17, 2024
Viaarxiv icon

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Add code
Apr 07, 2024
Viaarxiv icon