Computer Science
Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving efficient mechanisms, like linear attention, improve both…
Artificial intelligence (AI) is shifting scientific discovery from task-specific workflows towards autonomous systems that organize exploration with experimental and human feedback in open-ended candidate spaces. Evolutionary computation…
Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a general-purpose model in computer vision? In this paper, we…
Developers' choices about what data a system collects, how it is used and shared, and what defaults govern user choices directly shape users' privacy experiences. Yet, developers often make problematic privacy-related design decisions…
Image-generation AI systems increasingly support creative work by producing multiple design variations for users to evaluate and select. In such human-AI co-creation workflows, selection becomes a critical stage where human judgment guides…
This letter develops a radio access network (RAN) framework for mixed discrete-continuous optimization problems that arise in user-centric cell=free massive multiple-antenna networks. The novel framework exploits the structural…
Agent skills extend LLM agents with reusable procedures, tools, and domain-specific workflows, but their safety depends on resolving dependencies among interacting instructions. We introduce SkillLogic, a framework for analyzing logical…
We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing. Unlike classical contextual bandits…
Exposed documents such as emails, chat threads, tickets, and incident notes routinely leak credentials, but during incident response a leaked secret is only half the story. Responders also need to identify the ``door'' the secret opens: the…
Wearable sensing systems in high-stakes institutional contexts translate behavioral data into consequential judgments, yet wearers have little access to how those judgments are made. We present a qualitative study of 24 individuals who…
Safety-critical perception systems must reliably detect rare object classes within small label spaces, a setting that long-tailed detection methods, designed for hundreds of classes with dense annotation, fundamentally do not address.…
In quantum programs, Bugs4Q is a widely used benchmark containing real quantum defects. However, its evaluation assumes that benchmark labels remain valid and that generated fixes execute in the target environment. We evaluate two Bugs4Q…
Large language model (LLM)-based audio-visual speech recognition (LLM-AVSR) has recently demonstrated strong robustness in adverse acoustic environments by leveraging complementary audio and visual information. Existing approaches typically…
Recent advances in generative modeling have made generated tabular data a practical solution for privacy-sensitive data sharing, where watermarking enables ownership verification. However, existing watermarking methods fundamentally fail…
In large-scale computing systems, jobs often demand heterogeneous server allocations: large jobs that occupy a substantial fraction of the servers are of high importance and are thus latency-sensitive, while small jobs fill in the remaining…
Accurate noise classification is essential for operating near-term quantum processors, yet existing approaches, such as quantum process tomography, scale exponentially with system size, limiting their practicality for routine calibration.…
In this paper we develop the framework of using a parametrized mapping $[\sigma(1), \sigma(2), \cdots, \sigma(n)] \mapsto \sigma(1)z + \sigma(2)z^2 + \cdots \sigma(n)z^n$ to perform runtime analysis on Shellsort. In particular, we show that…
Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties. These models often encode domain-specific knowledge into their graph encoding modules, which increases their parameter…
As large language models (LLMs) scale, their memory and computation demands have grown substantially, making weight-only quantization a widely adopted technique for reducing model size with minimal accuracy loss. However, on current GPUs,…
Efficient inference in Large Language Models (LLMs) requires deciding where computation can be reduced while preserving model quality. We study this problem through multilayer perceptron (MLP) activation sparsification and token-level…