Picture for Xianpei Han

Xianpei Han

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

Add code
Apr 01, 2025
Viaarxiv icon

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning

Add code
Apr 01, 2025
Viaarxiv icon

Large Language Models Often Say One Thing and Do Another

Add code
Mar 10, 2025
Viaarxiv icon

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models

Add code
Mar 05, 2025
Viaarxiv icon

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking

Add code
Feb 28, 2025
Viaarxiv icon

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch

Add code
Feb 24, 2025
Viaarxiv icon

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency

Add code
Feb 04, 2025
Viaarxiv icon

DeepRAG: Thinking to Retrieval Step by Step for Large Language Models

Add code
Feb 03, 2025
Figure 1 for DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
Figure 2 for DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
Figure 3 for DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
Figure 4 for DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
Viaarxiv icon

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

Add code
Jan 07, 2025
Viaarxiv icon

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

Add code
Jan 03, 2025
Figure 1 for Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Figure 2 for Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Figure 3 for Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Figure 4 for Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Viaarxiv icon