← Search

Xinpeng Dong

2 accepted papers

2026

LUGS: Latent-aware Guidance for Efficient Unmasking in Diffusion Large Language Models

ICML 2026poster

Diffusion Language Models (DLMs) have emerged as a flexible alternative to autoregressive (AR) models. They can decode tokens in any order, but the generation quality critically depends on the decoding strategy. Existing approaches predominantly rely on local heuristics, such as confidence or entrop…

Cited by 0SourceScholar
2025

ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models

ICML 2025poster

Pre-trained vision-language models (VLMs) have revolutionized the field of machine learning, demonstrating exceptional performance across a wide range of tasks. However, their robustness remains vulnerable to the spurious-correlation problem. Existing works often involve fine-tuning the model with l…

Cited by 0SourcePDFScholar