Picture for Jian Hu

Jian Hu

V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning

Add code
Mar 14, 2025
Viaarxiv icon

CoS: Chain-of-Shot Prompting for Long Video Understanding

Add code
Feb 10, 2025
Figure 1 for CoS: Chain-of-Shot Prompting for Long Video Understanding
Figure 2 for CoS: Chain-of-Shot Prompting for Long Video Understanding
Figure 3 for CoS: Chain-of-Shot Prompting for Long Video Understanding
Figure 4 for CoS: Chain-of-Shot Prompting for Long Video Understanding
Viaarxiv icon

INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation

Add code
Jan 30, 2025
Figure 1 for INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation
Figure 2 for INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation
Figure 3 for INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation
Figure 4 for INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation
Viaarxiv icon

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

Add code
Jan 04, 2025
Figure 1 for REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Figure 2 for REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Figure 3 for REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Figure 4 for REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Viaarxiv icon

Ultra-slender Coaxial Antagonistic Tubular Robot for Ambidextrous Manipulation

Add code
Dec 25, 2024
Viaarxiv icon

InvSeg: Test-Time Prompt Inversion for Semantic Segmentation

Add code
Oct 15, 2024
Viaarxiv icon

Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation

Add code
Aug 27, 2024
Viaarxiv icon

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Add code
May 20, 2024
Figure 1 for OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Figure 2 for OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Figure 3 for OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Figure 4 for OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Viaarxiv icon

Design and Visual Servoing Control of a Hybrid Dual-Segment Flexible Neurosurgical Robot for Intraventricular Biopsy

Add code
Feb 23, 2024
Figure 1 for Design and Visual Servoing Control of a Hybrid Dual-Segment Flexible Neurosurgical Robot for Intraventricular Biopsy
Figure 2 for Design and Visual Servoing Control of a Hybrid Dual-Segment Flexible Neurosurgical Robot for Intraventricular Biopsy
Figure 3 for Design and Visual Servoing Control of a Hybrid Dual-Segment Flexible Neurosurgical Robot for Intraventricular Biopsy
Figure 4 for Design and Visual Servoing Control of a Hybrid Dual-Segment Flexible Neurosurgical Robot for Intraventricular Biopsy
Viaarxiv icon

Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects

Add code
Dec 18, 2023
Viaarxiv icon