Zhenting Wang

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Productive LLM Hallucinations: Conditions, Mechanisms, and Benefits

TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching

EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning

Read the Scene, Not the Script: Outcome-Aware Safety for LLMs

Exploring the Entropy Mechanism in LLM Agents On-policy Optimization

How to Evaluate and Mitigate IP Infringement in Visual Generative AI?

Visual Agents as Fast and Slow Thinkers

Continuous Concepts Removal in Text-to-image Diffusion Models

LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

ProSec: Fortifying Code LLMs with Proactive Security Alignment

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering

Hallucinating LLM Could Be Creative

Combating Hidden Vulnerabilities in Computer Vision Tasks