Related papers: APEX: A High-Performance Learned Index on Persiste…

The Intel Optane DC Persistent Memory (DCPM) is an attractive novel technology for building storage systems for data intensive HPC applications, as it provides lower cost per byte, low standby power and larger capacities than DRAM, with…

Humanoid locomotion has advanced rapidly with deep reinforcement learning (DRL), enabling robust feet-based traversal over uneven terrain. Yet platforms beyond leg length remain largely out of reach because current RL training paradigms…

Emerging high-performance storage technologies are opening up the possibility of designing new distributed data acquisition system architectures, in which the live acquisition of data and their processing are decoupled through a storage…

Indexes provide a method to access data in databases quickly. It can improve the response speed of subsequent queries by building a complete index in advance. However, it also leads to a huge overhead of the continuous updating during…

AI clusters today are one of the major uses of High Bandwidth Memory (HBM). However, HBM is suboptimal for AI workloads for several reasons. Analysis shows HBM is overprovisioned on write performance, but underprovisioned on density and…

Learned Image Compression (LIC) gradually became more and more famous in these years. The hyperprior-module-based LIC models have achieved remarkable rate-distortion performance. However, the memory cost of these LIC models is too large to…

Indexes are critical for efficient data retrieval and updates in modern databases. Recent advances in machine learning have led to the development of learned indexes, which model the cumulative distribution function of data to predict…

With the rapid increase in software exploits, the last few decades have seen several hardware-level features to enhance security (e.g., Intel MPX, ARM TrustZone, Intel SGX, Intel CET). Due to security, performance and/or usability issues…

Deep learning practitioners often operate on a computational and monetary budget. Thus, it is critical to design optimization algorithms that perform well under any budget. The linear learning rate schedule is considered the best…

The static nature of knowledge within Large Language Models (LLMs) makes it difficult for them to adapt to evolving information, rendering knowledge editing a critical task. However, existing methods struggle with challenges of scalability…

Processing-in-memory (PIM) reduces data movement by executing near memory, but our large-scale characterization on real PIM hardware shows that end-to-end performance is often limited by disjoint host and device address spaces that force…

This paper develops a memory-efficient approach for Sequential Pattern Mining (SPM), a fundamental topic in knowledge discovery that faces a well-known memory bottleneck for large data sets. Our methodology involves a novel hybrid trie data…

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance…

This work introduces novel training and post-training compression schemes to reduce external memory access during transformer model inference. Additionally, a new control flow mechanism, called dynamic batching, and a novel buffer…

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in…

Far-memory systems, where applications store less-active data in more energy-efficient memory media, are increasingly adopted by data centers. However, applications are bottlenecked by on-demand data fetching from far- to local-memory. We…

In-memory computing is an emerging computing paradigm that overcomes the limitations of exiting Von-Neumann computing architectures such as the memory-wall bottleneck. In such paradigm, the computations are performed directly on the data…

Processing-in-memory (PIM) has emerged as a promising solution for accelerating memory-intensive workloads as they provide high memory bandwidth to the processing units. This approach has drawn attention not only from the academic community…

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working…

Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the reward signal is hard to specify, avoiding heuristic and time-consuming reward design. However, PbRL can suffer from…