相关论文: A Mixture-of-Experts Model for Multimodal Emotion …

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the…

Speech Emotion Recognition (SER) aims to help the machine to understand human's subjective emotion from only audio information. However, extracting and utilizing comprehensive in-depth audio information is still a challenging task. In this…

We present Bayesian Mixture of Experts (Bayesian-MoE), a post-hoc uncertainty estimation framework for fine-tuned large language models (LLMs) based on Mixture-of-Experts architectures. Our method applies a structured Laplace approximation…

Multimodal emotion recognition in conversation (MERC) and multimodal emotion-cause pair extraction (MECPE) have recently garnered significant attention. Emotions are the expression of affect or feelings; responses to specific events, or…

Clinical event sequences in Electronic Health Records (EHRs) record detailed information about the patient condition and patient care as they occur in time. Recent years have witnessed increased interest of machine learning community in…

There remain two critical challenges that hinder the development of ERC. Firstly, there is a lack of exploration into mining deeper insights from the data itself for conversational emotion tasks. Secondly, the systems exhibit vulnerability…

Emotion Recognition in Conversations (ERC) has gained increasing attention for developing empathetic machines. Recently, many approaches have been devoted to perceiving conversational context by deep learning models. However, these…

Emotion is intrinsic to humans and consequently emotion understanding is a key part of human-like artificial intelligence (AI). Emotion recognition in conversation (ERC) is becoming increasingly popular as a new research frontier in natural…

Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the…

Inferring emotion status from users' queries plays an important role to enhance the capacity in voice dialogues applications. Even though several related works obtained satisfactory results, the performance can still be further improved. In…

The advancement of transformer neural networks has significantly elevated the capabilities of sentence similarity models, but they still struggle with highly discriminative tasks and may produce sub-optimal representations of important…

Automatic emotion recognition plays a key role in computer-human interaction as it has the potential to enrich the next-generation artificial intelligence with emotional intelligence. It finds applications in customer and/or representative…

Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in…

Emotion recognition in conversations (ERC) is vital to the advancements of conversational AI and its applications. Therefore, the development of an automated ERC model using the concepts of machine learning (ML) would be beneficial.…

Creating agents that can both appropriately respond to conversations and understand complex human linguistic tendencies and social cues has been a long standing challenge in the NLP community. A recent pillar of research revolves around…

Mixture of Experts (MoE) is a popular framework for modeling heterogeneity in data for regression, classification, and clustering. For regression and cluster analyses of continuous data, MoE usually use normal experts following the Gaussian…

We introduce a Mixture of Raytraced Experts, a stacked Mixture of Experts (MoE) architecture which can dynamically select sequences of experts, producing computational graphs of variable width and depth. Existing MoE architectures generally…

Emotion recognition in conversation (ERC) has attracted much attention in recent years for its necessity in widespread applications. Existing ERC methods mostly model the self and inter-speaker context separately, posing a major issue for…

Multimodal Emotion Recognition in Conversation (MERC) aims to predict speakers' emotions by integrating textual, acoustic, and visual cues. Existing approaches either struggle to capture complex cross-modal interactions or experience…

Multimodal emotion recognition in conversations (MERC) requires integrating multimodal signals while being robust to noise and modeling contextual reasoning. Existing approaches often emphasize fusion but overlook uncertainty in noisy…