Related papers: M2P2: Multimodal Persuasion Prediction using Adapt…

This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to empower the clustering-based speaker diarization system to handle overlapped…

Current video-to-audio (V2A) methods struggle in complex multi-event scenarios (video scenarios involving multiple sound sources, sound events, or transitions) due to two critical limitations. First, existing methods face challenges in…

Bias in Large Language Models (LLMs) poses significant risks to trustworthiness, manifesting primarily as stereotypical biases (e.g., gender or racial stereotypes) and structural biases (e.g., lexical overlap or position preferences).…

Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…

Multimodal Machine Translation (MMT) typically enhances text-only translation by incorporating aligned visual features. Despite the remarkable progress, state-of-the-art MMT approaches often rely on paired image-text inputs at inference and…

Accurate diagnosis of Mendelian diseases is crucial for precision therapy and assistance in preimplantation genetic diagnosis. However, existing methods often fall short of clinical standards or depend on extensive datasets to build…

A long line of work in social psychology has studied variations in people's susceptibility to persuasion -- the extent to which they are willing to modify their opinions on a topic. This body of literature suggests an interesting…

Vision-language models such as CLIP achieve strong visual-textual alignment, but often suffer from overfitting and limited interpretability when adapted through continuous prompt learning. While discrete prompt optimization improves…

Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on…

With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments.…

Traditional psychological models of belief revision focus on face-to-face interactions, but with the rise of social media, more effective models are needed to capture belief revision at scale, in this rich text-based online discourse. Here,…

Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the approach introduces substantial computational overhead resulting…

Multimodal regression aims to predict a continuous target from heterogeneous input sources and typically relies on fusion strategies such as early or late fusion. However, existing methods lack principled tools to disentangle and quantify…

Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that…

Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict. Crucially, conflicts differ in resolvability: benign conflicts stem from missing, weak, or…

Dynamic Optimization Problems (DOPs) are challenging to address due to their complex nature, i.e., dynamic environment variation. Evolutionary Computation methods are generally advantaged in solving DOPs since they resemble dynamic…

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

Multimodal sentiment analysis is a key technology in the fields of human-computer interaction and affective computing. Accurately recognizing human emotional states is crucial for facilitating smooth communication between humans and…

We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward…

Determining the plausibility of causal relations between clauses is a commonsense reasoning task that requires complex inference ability. The general approach to this task is to train a large pretrained language model on a specific dataset.…