相关论文: CitySpec with Shield: A Secure Intelligent Assista…
Safe landing is essential in robotics applications, from industrial settings to space exploration. As artificial intelligence advances, we have developed PEACE (Prompt Engineering Automation for CLIPSeg Enhancement), a system that…
Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from real user questions and expected answers. This study proposes…
Urban embodied AI agents, ranging from delivery robots to quadrupeds, are increasingly populating our cities, navigating chaotic streets to provide last-mile connectivity. Training such agents requires diverse, high-fidelity urban…
Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic…
Users increasingly create, manage and share digital resources, including sensitive data, via cloud platforms and APIs. Platforms encode the rules governing access to these resources, referred to as \textit{security policies}, using…
Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assistants. This paper introduces IntentGrasp, a comprehensive benchmark for evaluating the…
This paper presents the details of our system designed for the Task 1 of Multimodal Information Based Speech Processing (MISP) Challenge 2021. The purpose of Task 1 is to leverage both audio and video information to improve the…
For highly regulated industries such as banking and healthcare, one of the major hindrances to the adoption of cloud computing is compliance with regulatory standards. This is a complex problem due to many regulatory and technical…
We introduce STREET, a unified multi-task and multi-domain natural language reasoning and explanation benchmark. Unlike most existing question-answering (QA) datasets, we expect models to not only answer questions, but also produce…
The problem of synthetic speech detection has enjoyed considerable attention, with recent methods achieving low error rates across several established benchmarks. However, to what extent can low error rates on academic benchmarks translate…
Edge-based automatic speech recognition (ASR) technologies are increasingly prevalent in the development of intelligent and personalized assistants. However, resource-constrained ASR models face significant challenges in adaptivity,…
Large language models (LLMs) promise to accelerate UI design, yet current tools struggle with two fundamentals: externalizing designers' intent and controlling iterative change. We introduce SPEC, a structured, parameterized, hierarchical…
Humans often have to read multiple documents to address their information needs. However, most existing reading comprehension (RC) tasks only focus on questions for which the contexts provide all the information required to answer them,…
Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and response sequences grow longer. Speculative decoding (SD) offers…
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots. However, different policies…
Recent years have witnessed a boom in self-supervised learning (SSL) in various areas including speech processing. Speech based SSL models present promising performance in a range of speech related tasks. However, the training of SSL models…
While real world challenges typically define visual categories with language words or phrases, most visual classification methods define categories with numerical indices. However, the language specification of the classes provides an…
AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rests on a fundamental paradox: as language models are trained on human-written corpora, the…
We present Tempest, a synthesis tool to automatically create correct-by-construction reactive systems and shields from qualitative or quantitative specifications in probabilistic environments. A shield is a special type of reactive system…
As smart bands make life more convenient and provide a positive lifestyle, many people are now using them. Since smart bands deal with private information, security design and implementation for smart band system become necessary. To make a…