相关论文: Towards Adaptive Context Management for Intelligen…

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a…

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe…

We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and images. CEMTM builds on fine-tuned large vision language…

While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanism offers a flexible solution for managing long contexts, utilizing…

We present MCQA, a learning-based algorithm for multimodal question answering. MCQA explicitly fuses and aligns the multimodal input (i.e. text, audio, and video), which forms the context for the query (question and answer). Our approach…

Large language models (LLMs) have started to play a vital role in modelling speech and text. To explore the best use of context and multiple systems' outputs for post-ASR speech emotion prediction, we study LLM prompting on a recent task…

Long-term conversational agents require effective memory management to handle dialogue histories that exceed the context window of large language models (LLMs). Existing methods based on fact extraction or summarization reduce redundancy…

Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding,…

Emotion recognition has a wide range of applications in human-computer interaction, marketing, healthcare, and other fields. In recent years, the development of deep learning technology has provided new methods for emotion recognition.…

Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting…

Recent advances in autoregressive (AR) models have demonstrated their potential to rival diffusion models in image synthesis. However, for complex spatially-conditioned generation, current AR approaches rely on fine-tuning the pre-trained…

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications. However, their performance often degrades in context-specific scenarios, such as…

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning…

Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…

Medical AI, including clinical language models, vision-language models, and multimodal health record models, already summarizes notes, answers questions, and supports decisions. Their adaptation to new populations, specialties, or care…

Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed…

Simulation is an invaluable tool for developing and evaluating controllers for self-driving cars. Current simulation frameworks are driven by highly-specialist domain specific languages, and so a natural language interface would greatly…

Large Language Models (LLMs) based on Transformers excel at text processing, but their reliance on prompts for specialized behavior introduces computational overhead. We propose a modification to a Transformer architecture that eliminates…

Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However,…