Related papers: Ira: Efficient Transaction Replay for Distributed …

Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instruction conflicts. IH is key to defending against jailbreaks,…

We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for auditing privacy risks…

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by…

In class-incremental learning (CIL), effective incremental learning strategies are essential to mitigate task confusion and catastrophic forgetting, especially as the number of tasks $t$ increases. Current exemplar replay strategies impose…

Smart Contracts and transactions allow users to implement elaborate constructions on cryptocurrency blockchains like Bitcoin and Ethereum. Many of these constructions, including operational payment channels and atomic swaps, use a building…

In this paper we present the initial design of Minerva consensus protocol for Truechain and other technical details. Currently, it is widely believed in the blockchain community that a public chain cannot simultaneously achieve high…

Real-time understanding of continuous video streams is essential for intelligent agents operating in high-stakes environments, including autonomous vehicles, surveillance drones, and disaster response robots. Yet, most existing video…

Blockchains are meant to be persistent: posted transactions are immutable and cannot be changed. When a theft takes place, there are limited options for reversing the disputed transaction, and this has led to significant losses in the…

Interference alignment (IA) is a joint-transmission technique that achieves the capacity of the interference channel for high signal-to-noise ratios (SNRs). Most prior work on IA is based on the impractical assumption that perfect and…

Currently, Gasper, the implemented consensus protocol of Ethereum, takes between 64 and 95 slots to finalize blocks. Because of that, a significant portion of the chain is susceptible to reorgs. The possibility to capture MEV (Maximum…

As capacity and complexity of on-chip cache memory hierarchy increases, the service cost to the critical loads from Last Level Cache (LLC), which are frequently repeated, has become a major concern. The processor may stall for a…

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…

Memory security and reliability are two of the major design concerns in cloud computing systems. State-of-the-art memory security-reliability co-designs (e.g. Synergy) have achieved a good balance on performance, confidentiality, integrity,…

Aligning LLMs with user preferences is crucial for real-world use but often requires costly fine-tuning or expensive inference, forcing trade-offs between alignment quality and computational cost. Existing inference-time methods typically…

DRAM is the building block of modern main memory systems. DRAM cells must be periodically refreshed to prevent data loss. Refresh operations degrade system performance by interfering with memory accesses. As DRAM chip density increases with…

Transformers achieve state-of-the-art performance for natural language processing tasks by pre-training on large-scale text corpora. They are extremely compute-intensive and have very high sample complexity. Memory replay is a mechanism…

Improving reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this by performing multiple latent iterations to refine each token…

In large language models built upon the Transformer architecture, recent studies have shown that inter-head interaction can enhance attention performance. Motivated by this, we propose Multi-head Explicit Attention (MEA), a simple yet…

Set reconciliation, where two parties hold fixed-length bit strings and run a protocol to learn the strings they are missing from each other, is a fundamental task in many distributed systems. We present Rateless Invertible Bloom Lookup…

This paper examines the impact of reducing Ethereum slot time on decentralized exchange activity, with a focus on CEX-DEX arbitrage behavior. We develop a trading model where the agent's DEX transaction is not guaranteed to land, and the…