Related papers: Just-In-Time Piecewise-Linear Semantics for ReLU-t…

Recently, large language models (LLMs) have been successfully applied to many fields, showing outstanding comprehension and reasoning capabilities. Despite their great potential, LLMs usually require dedicated pre-training and fine-tuning…

LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model. While existing…

Recent work has shown that Just-In-Time (JIT) compilation can introduce timing side-channels to constant-time programs, which would otherwise be a principled and effective means to counter timing attacks. In this paper, we propose a novel…

In many recent works, multi-layer perceptions (MLPs) have been shown to be suitable for modeling complex spatially-varying functions including images and 3D scenes. Although the MLPs are able to represent complex scenes with unprecedented…

Linear temporal logic (LTL) is a specification language for finite sequences (called traces) widely used in program verification, motion planning in robotics, process mining, and many other areas. We consider the problem of learning LTL…

This paper presents Merlin, a new framework for managing resources in software-defined networks. With Merlin, administrators express high-level policies using programs in a declarative language. The language includes logical predicates to…

Split learning (SL) is a collaborative learning framework, which can train an artificial intelligence (AI) model between a device and an edge server by splitting the AI model into a device-side model and a server-side model at a cut layer.…

Just-in-Time software defect prediction (JIT-SDP) plays a critical role in prioritizing risky code changes during code review and continuous integration. However, existing datasets often suffer from noisy labels and low precision in…

An approach to construct explicit integral representations for two-layer ReLU networks is presented, which provides relatively simple representations for any multivariate polynomial. Quantitative bounds are provided for a particular,…

This paper describes a C++ library that compiles neural network models at runtime into machine code that performs inference. This approach in general promises to achieve the best performance possible since it is able to integrate statically…

Large Language Models (LLMs) demonstrate substantial accuracy gains when augmented with reasoning modes such as chain-of-thought and inference-time scaling. However, reasoning also incurs significant costs in inference latency and token…

We introduce sliced ReLU attention, a new attention mechanism that departs structurally from both softmax and its approximation alternatives. Instead of applying a nonlinearity to pairwise dot products, we operate on one-dimensional…

Deploying neural networks on microcontrollers is constrained by kilobytes of flash and SRAM, where 1x1 pointwise (PW) mixers often dominate memory even after INT8 quantization across vision, audio, and wearable sensing. We present…

Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional encoder-decoder policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT…

In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we propose linearity-based compression as a novel way to…

This paper presents \tdl, a typed feature-based representation language and inference system. Type definitions in \tdl\ consist of type and feature constraints over the boolean connectives. \tdl\ supports open- and closed-world reasoning…

The rapid development in the performance of large language models (LLMs) is accompanied by the escalation of model size, leading to the increasing cost of model training and inference. Previous research has discovered that certain layers in…

Two new logics for verification of hyperproperties are proposed. Hyperproperties characterize security policies, such as noninterference, as a property of sets of computation paths. Standard temporal logics such as LTL, CTL, and CTL* can…

Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and…

The rapid adoption of large language models (LLMs) presents new challenges for existing network architectures due to significant peak traffic and high communication uncertainty. Traditional wireless networks struggle to support efficiently,…