Mengdi Wang

Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP

2023 · arXiv (Cornell University)

In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact representation and uses …

Visual Adversarial Examples Jailbreak Aligned Large Language Models

2023 · arXiv (Cornell University)

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and …

Opportunities and challenges of diffusion models for generative AI

2024 · National Science Review

Diffusion models, a powerful and universal generative artificial intelligence technology, have achieved tremendous success and opened up new possibilities in diverse applications. In these applications, diffusion models provide flexible high-dimensional data modeling, and act as …

RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework

2025

Recent advances of large language models in the field of Verilog generation have raised several ethical and security concerns, such as code copyright protection and dissemination of malicious code. Researchers have employed watermarking techniques to …

DISC: Dynamic Decomposition Improves LLM Inference Scaling

2025 · arXiv (Cornell University)

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or …