10 papers
Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning
Xinmeng Xu, Haoran Xie, S. Joe Qin +3
Stage-wise audio-visual encoders propagate fused intermediate states across layers, making the formation of later representations depend on the readiness of earlier fusion states.…
ATRIE: Adaptive Tuning for Robust Inference and Emotion in Persona-Driven Speech Synthesis
Aoduo Li, Haoran Lv, Hongjian Xu +5
High-fidelity character voice synthesis is a cornerstone of immersive multimedia applications, particularly for interacting with anime avatars and digital humans. However, existing…
Calibration and Transformation-Free Weight-Only LLMs Quantization via Dynamic Grouping
Xinzhe Zheng, Zhen-Qun Yang, Zishan Liu +4
Large Language Models (LLMs) deliver strong performance but are difficult to deploy under tight memory and compute constraints. Low-bit post-training quantization (PTQ) is a promis…
Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction
Wenna Lai, Haoran Xie, Guandong Xu +2
Aspect sentiment quad prediction (ASQP) is inherently challenging to predict a structured quadruple with four core sentiment elements, including aspect term (a), aspect category (c…
Emotion-Enhanced Multi-Task Learning with LLMs for Aspect Category Sentiment Analysis
Yaping Chai, Haoran Xie, Joe S. Qin
Aspect category sentiment analysis (ACSA) has achieved remarkable progress with large language models (LLMs), yet existing approaches primarily emphasize sentiment polarity while o…
CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering
Zongxi Li, Yang Li, Haoran Xie +1
Users often assume that large language models (LLMs) share their cognitive alignment of context and intent, leading them to omit critical information in question-answering (QA) and…