← Search

Duc Anh Do

4 accepted papers

2025

Arena-Bench 2.0: A Comprehensive Benchmark of Social Navigation Approaches in Collaborative Environments

IROS 2025

Social navigation has become increasingly important for robots operating in human environments, yet many newly proposed navigation methods remain narrowly tailored or exist only as proof-of-concept prototypes. Building on our previous work with Arena, a social navigation development platform, we now

Cited by 0SourceScholar
2025

Discrete Diffusion Language Model for Efficient Text Summarization

NAACL 2025findings

While diffusion models excel at conditionally generating high-quality images, prior works in discrete diffusion models were not evaluated on conditional long-text generation. This work addresses the limitations of prior discrete diffusion models for conditional long-text generation, particularly in…

Cited by 0SourcePDFScholar
2024

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

ACL 2024long

We propose RESTA to perform LLM realignment towards safety, which gets compromised due to downstream task fine-tuning. RESTA stands for REstoring Safety through Task Arithmetic. At its core, it involves a simple arithmetic addition of a safety vector to the weights of the compromised model. We demon…

2024

ToXCL: A Unified Framework for Toxic Speech Detection and Explanation

NAACL 2024long

The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one consists of coded or indirect language. Therefore, it is crucial for models not only to detect implicit toxic speech but…