相关论文: Building Markovian Generative Architectures over P…

Large Language Models (LLMs) have demonstrated remarkable in-context learning capabilities, enabling flexible utilization of limited historical information to play pivotal roles in reasoning, problem-solving, and complex pattern recognition…

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training data required to train these architectures aggregates many…

Task-oriented dialogue systems aim to help users achieve their goals in specific domains. Recent neural dialogue systems use the entire dialogue history for abundant contextual information accumulated over multiple conversational turns.…

We investigate whether pre-training exclusively on dialogue data results in formally and functionally apt small language models. Based on this pre-trained llamalogue model, we employ a variety of fine-tuning strategies to enforce "more…

Conversational image generation requires a model to follow user instructions across multiple rounds of interaction, grounded in interleaved text and images that accumulate as chat history. While recent multimodal large language models…

Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while remaining robust to heterogeneous and evolving deployment conditions. Recent advances…

Large Language Models (LLMs) have been widely adopted to enhance Task-Oriented Dialogue Systems (TODS) by modeling complex language patterns and delivering contextually appropriate responses. However, this integration introduces significant…

Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is time to re-evaluate it.…

Large language models (LLMs) have been used for diverse tasks in natural language processing (NLP), yet remain under-explored for task-oriented dialogue systems (TODS), especially for end-to-end TODS. We present InstructTODS, a novel…

In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are…

We introduce the Markovian Pre-trained Transformer (MPT) for next-item recommendation, a transferable model fully pre-trained on synthetic Markov chains, yet capable of achieving state-of-the-art performance by fine-tuning a lightweight…

Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…

The rapid increase in the number of parameters in large language models (LLMs) has significantly increased the cost involved in fine-tuning and retraining LLMs, a necessity for keeping models up to date and improving accuracy.…

Task-oriented dialogue systems are broadly used in virtual assistants and other automated services, providing interfaces between users and machines to facilitate specific tasks. Nowadays, task-oriented dialogue systems have greatly…

This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground-truth distribution at training time, introducing error…

The emergence of instruction-tuned large language models (LLMs) has advanced the field of dialogue systems, enabling both realistic user simulations and robust multi-turn conversational agents. However, existing research often evaluates…

Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potential mismatch between required capabilities and training…

Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ…

Pretrained Foundation Models (PFMs) are regarded as the foundation for various downstream tasks with different data modalities. A PFM (e.g., BERT, ChatGPT, and GPT-4) is trained on large-scale data which provides a reasonable parameter…

We present a novel framework that integrates Large Language Models (LLMs) with automated planning and formal verification to streamline the creation and use of Markov Decision Processes (MDP). Our system leverages LLMs to extract structured…