Related papers: M2P2: Multimodal Persuasion Prediction using Adapt…
Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play…
In this paper, we argue that the design and development of multimodal datasets for natural language processing (NLP) challenges should be enhanced in two significant respects: to more broadly represent commonsense semantic inferences; and…
Multimodal foundation models have achieved impressive progress across a wide range of vision-language tasks. However, existing approaches often adopt fixed or task-specific fusion strategies, neglecting the intrinsic variability of modality…
Large pre-trained Vision Language Models (VLMs) demonstrate excellent generalization capabilities but remain highly susceptible to adversarial examples, posing potential security risks. To improve the robustness of VLMs against adversarial…
Multimodal deep learning (MDL) has emerged as a transformative approach in computational pathology. By integrating complementary information from multiple data sources, MDL models have demonstrated superior predictive performance across…
Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly with representation learning, making it difficult to…
Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, traditional DPO methods…
During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…
Implicit discourse relation classification is a challenging task due to the absence of discourse connectives. To overcome this issue, we design an end-to-end neural model to explicitly generate discourse connectives for the task, inspired…
Automatic Video Dubbing (AVD) generates speech aligned with lip motion and facial emotion from scripts. Recent research focuses on modeling multimodal context to enhance prosody expressiveness but overlooks two key issues: 1) Multiscale…
Over the past decade, wearable computing devices (``smart glasses'') have undergone remarkable advancements in sensor technology, design, and processing power, ushering in a new era of opportunity for high-density human behavior data.…
Recently, prompt learning has garnered considerable attention for its success in various Vision-Language (VL) tasks. However, existing prompt-based models are primarily focused on studying prompt generation and prompt strategies with…
Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is…
Automatic speech-based affect recognition of individuals in dyadic conversation is a challenging task, in part because of its heavy reliance on manual pre-processing. Traditional approaches frequently require hand-crafted speech features…
Sentiment analysis plays a crucial role in various domains, such as business intelligence and financial forecasting. Large language models (LLMs) have become a popular paradigm for sentiment analysis, leveraging multi-task learning to…
Multimodal aspect-based sentiment analysis(MABSA) seeks to identify aspect terms within paired image-text data and determine their fine grained sentiment polarities, representing a fundamental task for improving the effectiveness of…
Multi-agent debate improves LLM reasoning, yet agreement among agents is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus-based stopping commits that error to an automated action…
Modelling persuasion strategies as predictors of task outcome has several real-world applications and has received considerable attention from the computational linguistics community. However, previous research has failed to account for the…
Phonetic information and linguistic knowledge are an essential component of a Text-to-speech (TTS) front-end. Given a language, a lexicon can be collected offline and Grapheme-to-Phoneme (G2P) relationships are usually modeled in order to…
Large Language Models (LLMs) have become increasingly popular due to their ability to process and generate natural language. However, as they are trained on massive datasets of text, LLMs can inherit harmful biases and produce outputs that…