相关论文: Remembrance: The Unbearable Sentience of Being Dig…
A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this…
Trends like digital transformation even intensify the already overwhelming mass of information knowledge workers face in their daily life. To counter this, we have been investigating knowledge work and information management support…
Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external storage require complex management and incur storage overhead,…
Deletion is a fundamental database operation, yet modern systems often fail to provide the privacy guarantee that users expect from it. A deleted value may disappear from query results and even from physical storage, yet remain inferable…
Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future.…
To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, the simple combination of memory data and new-task samples…
Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years. Indeed, Deep Neural Networks are now the golden standard in domains as various as computer vision, natural language…
Computer systems have evolved over the years starting from sizable, single-user, slow, and expensive machines to multi-user, fast, cheaper, and small-sized machines. The use of multi-user computer networks has given rise to a new paradigm…
High dimensional data can have a surprising property: pairs of data points may be easily separated from each other, or even from arbitrary subsets, with high probability using just simple linear classifiers. However, this is more of a rule…
Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…
Autonomous agents operating in dynamic and safety-critical environments require decision-making frameworks that are both computationally efficient and physically grounded. However, many existing approaches rely on end-to-end learning, which…
The development of critical systems is becoming more and more complex. The overall tendency is that development costs raise. In order to cut cost of development, companies are forced to build systems from proven components and larger new…
I will propose the notion that the universe is digital, not as a claim about what the universe is made of but rather about the way it unfolds. Central to the argument will be the concepts of symmetry breaking and algorithmic probability,…
Organizations use data lakes to store and analyze sensitive data. But hackers may compromise data lake storage to bypass access controls and access sensitive data. To address this, we propose Membrane, a system that (1) cryptographically…
The demand for high-density data storage with ultrafast accessibility motivates the search for new memory implementations. Ideally such storage devices should be robust to input error and to unreliability of individual elements; furthermore…
The rapid advancements in memory systems, CPU technology, and emerging technologies herald a transformative potential in computing, promising to revolutionize memory hierarchies. Innovations in DDR memory are delivering unprecedented…
Leonard Shelby, the protagonist of Memento, uses mementos in the form of tattoos and pictures to handle his amnesia. Similar to Leonard, contemporary quantum computers suffer from "quantum amnesia": the inability to store quantum registers…
We introduce the notion of universal memcomputing machines (UMMs): a class of brain-inspired general-purpose computing machines based on systems with memory, whereby processing and storing of information occur on the same physical location.…
As data-intensive applications increasingly strain conventional computing systems, processing-in-memory (PIM) has emerged as a promising paradigm to alleviate the memory wall by minimizing data transfer between memory and processing units.…
World models enable agents to plan within imagined environments by predicting future states conditioned on past observations and actions. However, their ability to plan over long horizons is limited by the effective memory span of the…