Picture for Meng Zhao

Meng Zhao

Selective Complementary Feature Fusion and Modal Feature Compression Interaction for Brain Tumor Segmentation

Add code
Mar 20, 2025
Viaarxiv icon

Can xLLMs Understand the Structure of Dialog? Exploring Multilingual Response Generation in Complex Scenarios

Add code
Jan 20, 2025
Viaarxiv icon

Advancing Multi-Party Dialogue Systems with Speaker-ware Contrastive Learning

Add code
Jan 20, 2025
Viaarxiv icon

Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models

Add code
Oct 29, 2024
Figure 1 for Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models
Figure 2 for Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models
Figure 3 for Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models
Figure 4 for Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models
Viaarxiv icon

Self-Supervised State Space Model for Real-Time Traffic Accident Prediction Using eKAN Networks

Add code
Sep 09, 2024
Viaarxiv icon

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Add code
Aug 09, 2024
Figure 1 for VITA: Towards Open-Source Interactive Omni Multimodal LLM
Figure 2 for VITA: Towards Open-Source Interactive Omni Multimodal LLM
Figure 3 for VITA: Towards Open-Source Interactive Omni Multimodal LLM
Figure 4 for VITA: Towards Open-Source Interactive Omni Multimodal LLM
Viaarxiv icon

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

Add code
Jul 15, 2024
Figure 1 for AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Figure 2 for AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Figure 3 for AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Figure 4 for AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Viaarxiv icon

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Add code
Jun 16, 2024
Viaarxiv icon

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors

Add code
Jun 03, 2024
Viaarxiv icon

Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding

Add code
May 30, 2024
Figure 1 for Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding
Figure 2 for Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding
Figure 3 for Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding
Figure 4 for Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding
Viaarxiv icon