Related papers: PSM: Policy Synchronised Deterministic Memory

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

Context: Concurrent objects with asynchronous messaging are an increasingly popular way to structure highly available, high performance, large-scale software systems. To ensure data-consistency and support synchronization between objects…

Multi-turn dialogues and context-intensive tasks challenge Large Language Models (LLMs) to integrate long histories without sacrificing generation quality. Although prefix LLMs can better exploit historical context via bidirectional…

We present four high performance hybrid sorting methods developed for various parallel platforms: shared memory multiprocessors, distributed multiprocessors, and clusters taking advantage of existence of both shared and distributed memory.…

Persistent Memory (PM) is a new storage technology thatbrings high performance, byte addressability, and persistency for a lesser cost than DRAM. Due to cache volatility and store reordering, developers must use explicit instructions (e.g.:…

Current AI agent architectures suffer from ephemeral memory limitations, preventing effective collaboration and knowledge sharing across sessions and agent boundaries. We introduce SAMEP (Secure Agent Memory Exchange Protocol), a novel…

Abstract. Matching logic cannot handle concurrency. We introduce concurrent matching logic (CML) to reason about fault-free partial correctness of shared-memory concurrent programs. We also present a soundness proof for concurrent matching…

Phase-change memory (PCM) devices have multiple banks to serve memory requests in parallel. Unfortunately, if two requests go to the same bank, they have to be served one after another, leading to lower system performance. We observe that a…

Linear constraints are the linear counterpart of Haskell's class constraints. Linearly typed parameters allow the programmer to control resources such as file handles and manually managed memory as linear arguments. Indeed, a linear type…

Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large language models (LLMs), places significant pressure on memory systems due to frequent memory…

The synthesis problem for partially observable Markov decision processes (POMDPs) is to compute a policy that satisfies a given specification. Such policies have to take the full execution history of a POMDP into account, rendering the…

Coherent causal memory (CCM) is causal memory in which prefixes of an execution can be mapped to global memory states in a consistent way. While CCM requires conflicting pairs of writes to be globally ordered, it allows writes to remain…

Memoryless and finite-memory policies offer a practical alternative for solving partially observable Markov decision processes (POMDPs), as they operate directly in the output space rather than in the high-dimensional belief space. However,…

We study large-scale distributed cooperative systems that use optimistic replication. We represent a system as a graph of actions (operations) connected by edges that reify semantic constraints between actions. Constraint types include…

Executing smart contracts is a compute and storage-intensive task, which currently dominates modern blockchain's performance. Given that computers are becoming increasingly multicore, concurrency is an attractive approach to improve…

The abilities to perceive, learn, and use generalities, similarities, classes, i.e., semantic memory (SM), is central to cognition. Machine learning (ML), neural network, and AI research has been primarily driven by tasks requiring such…

Context-aware recommender systems (CARSs) apply sensing and analysis of user context in order to provide personalized services. Adding context to a recommendation model is challenging, since the addition of context may increases both the…

The memory model for RISC-V, a newly developed open source ISA, has not been finalized yet and thus, offers an opportunity to evaluate existing memory models. We believe RISC-V should not adopt the memory models of POWER or ARM, because…

Data replication is crucial in modern distributed systems as a means to provide high availability. Many techniques have been proposed to utilize replicas to improve a system's performance, often requiring expensive coordination or…

Providing Large Language Models with relevant contextual knowledge at inference time has been shown to greatly improve the quality of their generations. This is often achieved by prepending informative passages of text, or 'contexts',…