Picture for Yihong Tang

Yihong Tang

INTENT: Trajectory Prediction Framework with Intention-Guided Contrastive Clustering

Add code
Mar 06, 2025
Viaarxiv icon

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents

Add code
Feb 28, 2025
Viaarxiv icon

The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents

Add code
Feb 28, 2025
Viaarxiv icon

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning

Add code
Oct 21, 2024
Viaarxiv icon

High and Low Resolution Tradeoffs in Roadside Multimodal Sensing

Add code
Oct 02, 2024
Figure 1 for High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
Figure 2 for High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
Figure 3 for High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
Figure 4 for High and Low Resolution Tradeoffs in Roadside Multimodal Sensing
Viaarxiv icon

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems

Add code
Sep 25, 2024
Figure 1 for RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
Figure 2 for RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
Figure 3 for RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
Figure 4 for RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
Viaarxiv icon

MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space

Add code
Jul 02, 2024
Viaarxiv icon

Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement

Add code
Feb 16, 2024
Viaarxiv icon

Synergizing Spatial Optimization with Large Language Models for Open-Domain Urban Itinerary Planning

Add code
Feb 11, 2024
Viaarxiv icon

DialogBench: Evaluating LLMs as Human-like Dialogue Systems

Add code
Nov 03, 2023
Viaarxiv icon