Papers by Xianlong Luo

4 papers
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)

Copied to clipboard

Challenge: Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap .
Approach: They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models.
Outcome: The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting .
Overcome Noise and Bias: Segmentation-Aided Multi-Granularity Denoising and Debiasing for Enhanced Quarduples Extraction in Dialogue (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating sentiment quadruples in dialogues face heightened noise and order bias challenges, leading to decreased robustness and accuracy.
Approach: They propose a Segmentation-Aided multi-grained denoising and debiasing method to address noise and order bias challenges in ABSA.
Outcome: The proposed method achieves word-level denoising and utterance-level demoising via topic-aware dialogue segmentation.
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)

Copied to clipboard

Challenge: Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context.
Approach: They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts.
Outcome: The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context.
Tagging-Assisted Generation Model with Encoder and Decoder Supervision for Aspect Sentiment Triplet Extraction (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in the ASTE task have been driven by Natural Language Generation-based approaches, but most NLG methods overlook the supervision of the encoder-decoder hidden representations and fail to fully utilize the semantic information provided by the labels.
Approach: They propose a tagging-assisted generation model with encoder and decoder supervision that enhances the supervision of the encoder-decoder through multiple-perspective tabbing assistance and label semantic representations.
Outcome: The proposed model enhances the supervision of the encoder and decoder through multiple-perspective tagging assistance and label semantic representations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations