We propose SymPlex, a reinforcement learning framework for discovering analytical symbolic solutions to partial differential equations (PDEs) without access to ...
Multimodal Large Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual token num...
Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reason...
A key challenge in autoregressive image generation is to efficiently sample independent locations in parallel, while still modeling mutual dependencies with ser...
Imbalanced node classification in graph neural networks (GNNs) happens when some labels are much more common than others, which causes the model to learn unfair...
Recently, there have been significant research interests in training large language models (LLMs) with reinforcement learning (RL) on real-world tasks, such as ...
Modern distributed optimization methods mostly rely on traditional synchronous approaches, despite substantial recent progress in asynchronous optimization. We ...
Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to ...
Prompt injection attacks manipulate webpage content to cause web agents to execute attacker-specified tasks instead of the user's intended ones. Existing method...
Long-context inference with Large Language Models (LLMs) is costly due to quadratic attention and growing key-value caches, motivating context compression. In t...
The development of programming languages involves complex theoretical and practical challenges, particularly when addressing modularity and reusability through ...
Human vision is foveated, with variable resolution peaking at the center of a large field of view; this reflects an efficient trade-off for active sensing, allo...
Deep Learning (DL) libraries like TensorFlow and Pytorch simplify machine learning (ML) model development but are prone to bugs due to their complex design. Bug...
Large Language Models (LLMs) have recently attracted wide interest for tackling software engineering tasks. In contrast to code generation, refactoring demands ...
We analyze the Accelerated Noisy Power Method, an algorithm for Principal Component Analysis in the setting where only inexact matrix-vector products are availa...
Equilibrium Propagation (EP) is a physics-inspired learning algorithm that uses stationary states of a dynamical system both for inference and learning. In its ...
AI-enabled systems are subjected to various types of runtime uncertainties, ranging from dynamic workloads, resource requirements, model drift, etc. These uncer...
Context: Code coverage is widely used as a software quality assurance measure. However, its effect, and specifically the advisable dose, are disputed in both th...
Test-driven development (TDD) has been adopted to improve Large Language Model (LLM)-based code generation by using tests as executable specifications. However,...
Flaky tests yield different results when executed multiple times for the same version of the source code. Thus, they provide an ambiguous signal about the quali...
Asynchronous pipeline parallelism maximizes hardware utilization by eliminating the pipeline bubbles inherent in synchronous execution, offering a path toward e...
Mixture of Experts (MoE) architectures significantly enhance the capacity of LLMs without proportional increases in computation, but at the cost of a vast param...
Agreement is a foundational problem in distributed computing that have been studied extensively for over four decades. Recently, Meir, Mirault, Peleg and Robins...
Blockchain validators can reduce block processing time by exploiting multi-core CPUs, but deterministic execution must preserve a given total order while respec...
