相关论文: Holographic Knowledge Manifolds: A Novel Pipeline …

Hidden Markov models (HMM) are commonly used in generation tasks and have demonstrated strong capabilities in neuro-symbolic applications for the Markov property. These applications leverage the strengths of neural networks and symbolic…

Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…

Large language models (LLMs) encode knowledge in parametric weights, making it costly to update or extend without retraining. Retrieval-augmented generation (RAG) mitigates this limitation by appending retrieved text to the input, but…

Large language models (LLMs) have shown promise as parametric knowledge bases, but often underperform on question answering (QA) tasks due to hallucinations and uncertainty. While prior work attributes these failures to knowledge gaps in…

Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However, their direct application is fundamentally limited by a…

Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explosion of visual tokens, which often leads to Out-of-Memory…

The application of Transformer-based large models has achieved numerous success in recent years. However, the exponential growth in the parameters of large models introduces formidable memory challenge for edge deployment. Prior works to…

Hidden Markov Model (HMM) is often regarded as the dynamical model of choice in many fields and applications. It is also at the heart of most state-of-the-art speech recognition systems since the 70's. However, from Gaussian mixture models…

Large Language Models (LLMs) have become a mainstay for many everyday applications. However, as data evolve their knowledge quickly becomes outdated. Continual learning aims to update LLMs with new information without erasing previously…

The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory hierarchy of the human brain, we reduce this cost by…

Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision, language, and video understanding tasks, scaling them to long-form speech remains a critical bottleneck due to the explosive growth of…

Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing…

Generative large language models (LLMs) have revolutionized multiple domains. Modern LLMs predominantly rely on an autoregressive decoding strategy, which generates output tokens sequentially and employs a key-value cache (KV cache) to…

Backpropagation provides a generalized configuration for overcoming catastrophic forgetting. Optimizers such as SGD and Adam are commonly used for weight updates in continual learning and continual pre-training. However, access to gradient…

As transistor-based memory technologies like dynamic random access memory (DRAM) approach their scalability limits, the need to explore alternative storage solutions becomes increasingly urgent. Phase-change memory (PCM) has gained…

Time series forecasting is a critical and challenging task in practical application. Recent advancements in pre-trained foundation models for time series forecasting have gained significant interest. However, current methods often overlook…

Hierarchical Temporal Memory (HTM) is a biomimetic machine learning algorithm imbibing the structural and algorithmic properties of the neocortex. Two main functional components of HTM that enable spatio-temporal processing are the spatial…

We introduce HAMLET, a holistic and automated framework for evaluating the long-context comprehension of large language models (LLMs). HAMLET structures source texts into a three-level key-fact hierarchy at root-, branch-, and leaf-levels,…

Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic…