Curating the frontier of Artificial Intelligence

An Infectious Disease Spread Simulation Based on Large Language Model Decision Making

在传染病爆发期间对个人决策进行建模对于理解行为动态和为有效的公共信息提供信息至关重要...

Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective pub...

Rethinking Infrastructure Inspection as Image Difference Classification: A Traffic Sign Case Study

数字孪生(DTs) 允许道路基础设施检查, 数字化，尽管这受到有限注释数据的阻碍。这项工作利用了...

Digital twins (DTs) allow the digitalization of road infrastructure inspection, though this is hindered by limited annotated data. This work exploits ...

Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration

LLM 代理的最新进展实现了复杂的认知能力,，例如多步推理, 规划, 和工具使用,，这越来越多地...

Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly pos...

Risk Assessment of Autonomous Driving: Integrating Technical Failures, Ethical Dilemmas, and Policy Frameworks

自动驾驶技术有潜力减少每年因人为失误造成的大量道路交通事故,，但它也带来了...

Autonomous driving technology has the potential to reduce the large number of road traffic accidents caused by human error each year, but it also brin...

Unsupervised Skill Discovery for Agentic Data Analysis

推理时技能增强提供了一种轻量级的方法来改进数据分析代理，通过注入可重用的程序知识而无需更新...

Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updati...

The crucial human component in computing and AI

研讨会包括由 SERC 最新种子资助获得者就空气污染预测和负责任的计算机访问等主题进行的研究演讲。

The symposium included research talks by SERC’s latest seed grant recipients on topics such as air pollution forecasting and responsible computer visi...

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

LLM 智能体越来越多地部署在需要对长期交互历史进行持续推理的长期任务上。大规模地意识到这一点......

LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale ...

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents

随着生成长度的不断增长，稀疏注意力对于服务大型语言模型 (LLMs) 变得越来越重要。然而, 部署...

Sparse attention is becoming increasingly important for serving large language models (LLMs) as generation lengths continue to grow. However, deployin...

Benchmark Everything Everywhere All at Once

基准通过提供标准化和明确的绩效衡量标准，是评估和推进 LLM 和 MLLM 的基础。然而,他们的...

Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance. However, their ...

Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement

我们引入了 Goedel-Architect, ，这是一个在 Lean 4 中以蓝图生成和细化为中心的形式定理证明的代理框架。一张蓝图...

We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint ...