Picture for Ji Qi

Ji Qi

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

Add code
Apr 21, 2025
Viaarxiv icon

An artificially intelligent magnetic resonance spectroscopy quantification method: Comparison between QNet and LCModel on the cloud computing platform CloudBrain-MRS

Add code
Mar 06, 2025
Viaarxiv icon

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay

Add code
Dec 05, 2024
Figure 1 for p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Figure 2 for p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Figure 3 for p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Figure 4 for p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Viaarxiv icon

Weakly Supervised Framework Considering Multi-temporal Information for Large-scale Cropland Mapping with Satellite Imagery

Add code
Nov 27, 2024
Viaarxiv icon

Class-RAG: Content Moderation with Retrieval Augmented Generation

Add code
Oct 18, 2024
Figure 1 for Class-RAG: Content Moderation with Retrieval Augmented Generation
Figure 2 for Class-RAG: Content Moderation with Retrieval Augmented Generation
Figure 3 for Class-RAG: Content Moderation with Retrieval Augmented Generation
Figure 4 for Class-RAG: Content Moderation with Retrieval Augmented Generation
Viaarxiv icon

ExpLLM: Towards Chain of Thought for Facial Expression Recognition

Add code
Sep 04, 2024
Figure 1 for ExpLLM: Towards Chain of Thought for Facial Expression Recognition
Figure 2 for ExpLLM: Towards Chain of Thought for Facial Expression Recognition
Figure 3 for ExpLLM: Towards Chain of Thought for Facial Expression Recognition
Figure 4 for ExpLLM: Towards Chain of Thought for Facial Expression Recognition
Viaarxiv icon

CogVLM2: Visual Language Models for Image and Video Understanding

Add code
Aug 29, 2024
Figure 1 for CogVLM2: Visual Language Models for Image and Video Understanding
Figure 2 for CogVLM2: Visual Language Models for Image and Video Understanding
Figure 3 for CogVLM2: Visual Language Models for Image and Video Understanding
Figure 4 for CogVLM2: Visual Language Models for Image and Video Understanding
Viaarxiv icon

Exploring The Neural Burden In Pruned Models: An Insight Inspired By Neuroscience

Add code
Jul 27, 2024
Viaarxiv icon

LVBench: An Extreme Long Video Understanding Benchmark

Add code
Jun 12, 2024
Figure 1 for LVBench: An Extreme Long Video Understanding Benchmark
Figure 2 for LVBench: An Extreme Long Video Understanding Benchmark
Figure 3 for LVBench: An Extreme Long Video Understanding Benchmark
Figure 4 for LVBench: An Extreme Long Video Understanding Benchmark
Viaarxiv icon

An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning

Add code
Feb 23, 2024
Viaarxiv icon