Related papers: Region-based memory management for Mercury program…

Large Language Models (LLMs) have made extraordinary progress in the field of Artificial Intelligence and have demonstrated remarkable capabilities across a large variety of tasks and domains. However, as we venture closer to creating…

A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes…

Mutual exclusion (ME) is a commonly used technique to handle conflicts in concurrent systems. With recent advancements in non-volatile memory technology, there is an increased focus on the problem of recoverable mutual exclusion (RME), a…

The extensive memory footprint of language model (LM) fine-tuning poses a challenge for both researchers and practitioners. LMs use an embedding matrix to represent extensive vocabularies, forming a substantial proportion of the model…

Processing-In-Memory (PIM) is a novel approach that augments existing DRAM memory chips with lightweight logic. By allowing to offload computations to the PIM system, this architecture allows for circumventing the data-bottleneck problem…

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 However, as data evolve their knowledge quickly becomes outdated.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…

It is well known that physical phenomena may be of great help in computing some difficult problems efficiently. A typical example is prime factorization that may be solved in polynomial time by exploiting quantum entanglement on a quantum…

Many modern workloads such as neural network inference and graph processing are fundamentally memory-bound. For such workloads, data movement between memory and CPU cores imposes a significant overhead in terms of both latency and energy. A…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

The concepts of unitary evolution matrices and associative memory have boosted the field of Recurrent Neural Networks (RNN) to state-of-the-art performance in a variety of sequential tasks. However, RNN still have a limited capacity to…

Memory systems have been designed to leverage past experiences in Large Language Model (LLM) agents. However, many deployed memory systems primarily optimize compression and storage, with comparatively less emphasis on explicit, closed-loop…

Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is…

Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled powerful semantic and multimodal reasoning capabilities, creating new opportunities to enhance sample efficiency, high-level planning, and…

Large language models (LLMs) substantially enhance developer productivity in repository-level code generation through interactive collaboration. However, as interactions progress, repository context must be continuously preserved and…

Fine-tuning large language models (LLMs) with backpropagation\textemdash even for a subset of parameters such as LoRA\textemdash can be much more memory-consuming than inference and is often deemed impractical for resource-constrained…

Personalized large language models (LLMs) rely on memory retrieval to incorporate user-specific histories, preferences, and contexts. Existing approaches either overload the LLM by feeding all the user's past memory into the prompt, which…

Continual fine-tuning of large language models (LLMs) is becoming increasingly crucial as these models are deployed in dynamic environments where tasks and data distributions evolve over time. While strong adaptability enables rapid…

Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…

Dynamic programming (DP) is a fundamental method in operations research, but formulating DP models has traditionally required expert knowledge of both the problem context and DP techniques. Large Language Models (LLMs) offer the potential…

Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve…