相关论文: From Exposure to Internalization: Dual-Stream Cali…

Self-Consistency mitigates hallucinations in Large Language Models (LLMs) by sampling multiple reasoning paths,but it lacks a systematic approach to determine the optimal number of samples or select the most faithful rationale. To address…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations.…

Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confidence scores that necessitate calibration. While current…

Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to…

The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Learners sharing similar implicit cognitive states often display comparable observable problem-solving performances. Leveraging collaborative connections among such similar learners proves valuable in comprehending human learning. Motivated…

Deep sequence recognition (DSR) models receive increasing attention due to their superior application to various applications. Most DSR models use merely the target sequences as supervision without considering other related sequences,…

The dual-stream transformer architecture-based joint audio-video generation method has become the dominant paradigm in current research. By incorporating pre-trained video diffusion models and audio diffusion models, along with a…

Sequential recommendation seeks to model the evolution of user interests by capturing temporal user intent and item-level transition patterns. Transformer-based recommenders demonstrate a strong capacity for learning long-range and…

Voice conversion is an increasingly popular technology, and the growing number of real-time applications requires models with streaming conversion capabilities. Unlike typical (non-streaming) voice conversion, which can leverage the entire…

Cognitive Language Processing (CLP), situated at the intersection of Natural Language Processing (NLP) and cognitive science, plays a progressively pivotal role in the domains of artificial intelligence, cognitive intelligence, and brain…

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systematic biases from…

Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from…

The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning. In the high-stakes domain of healthcare, correct answers alone are insufficient;…

Deep neural networks have demonstrated remarkable advancements in various fields using large, well-annotated datasets. However, real-world data often exhibit long-tailed distributions and label noise, significantly degrading generalization…

Clustering high-dimensional spatiotemporal data using an unsupervised approach is a challenging problem for many data-driven applications. Existing state-of-the-art methods for unsupervised clustering use different similarity and distance…

We propose and study a realistic Continual Learning (CL) setting where learning algorithms are granted a restricted computational budget per time step while training. We apply this setting to large-scale semi-supervised Continual Learning…