CMU — CS Research

Computer science research from Carnegie Mellon University, including AI, robotics, language technologies, and software engineering.

Sample of the collection (25 of 4,876 items)

• Quantifying the Statistical Effect of Rubric Modifications on Human-Autorater Agreement Carnegie Mellon University Autoraters, also referred to as LLM-as-judges, are increasingly used for evaluation and automated content moderation. However, there is…
• LLM-based Multimodal Feedback Produces Equivalent Learning and Better Student Perceptions than Educator Feedback Carnegie Mellon University Providing timely, targeted, and multimodal feedback helps students quickly correct errors, build deep understanding and stay motivated,…
• Learning Latent Representations to Bridge Coarse-Grained and Atomistic Resolutions in Polymer Simulations Sandia National Laboratories We present a machine-learning-based framework for learning reduced-order representations of polymer chain conformations across…
• LLM-Based Post-ASR Error Correction for Disordered Speech Carnegie Mellon University Automatic speech recognition (ASR) systems achieve near-human accuracy on typical speech, but performance on disordered speech remains…
• Research on Architecture Design and Optimization of Cloud-Edge Collaborative Emergency Communication System for Low-Latency Response Carnegie Mellon University In terms of the base station destruction, link disconnection and resource contention in the disaster environment of the traditional…
• Evaluation of Agents under Simulated AI Marketplace Dynamics To Eun Kim et al. Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large language models, and…
• HiFiGaze: Improving Eye Tracking Accuracy Using Screen Content Knowledge Carnegie Mellon University We present a new and accurate approach for gaze estimation on consumer computing devices. We take advantage of continued strides in the…
• Inclusive Mobile Learning: How Technology-Enabled Language Choice Supports Multilingual Students Carnegie Mellon University Most learners worldwide are multilingual, yet implementing multilingual education remains challenging in practice. EdTech offers an…
• EdTech for Last Mile Learners in the Global South: Navigating Technological and Motivational Learning Insights with Radios and Mobile Phones Carnegie Mellon University Educational technology (EdTech) solutions have shown promise for disseminating educational opportunities to last-mile learners,…
• Does Visual Token Pruning Improve Calibration? An Empirical Study on Confidence in MLLMs Carnegie Mellon University Visual token pruning is a widely used strategy for efficient inference in multimodal large language models (MLLMs), but existing work…
• When Friction Helps: Transaction Confirmation Improves Decision Quality in Blockchain Interactions Carnegie Mellon University In blockchain applications, transaction confirmation is often treated as usability friction to be minimized or removed. However,…
• Hybrid Game Control Envelope Synthesis Carnegie Mellon University Control problems for embedded systems like cars and trains can be modeled by two-player hybrid games. Control envelopes, which are…
• Language Preferences and Practices in Multilingual EdTech: Flexible Primary Language Use with Secondary Language Support Carnegie Mellon University The benefits of learning in one's mother tongue are well documented, yet colonial languages dominate education, marginalizing local…
• Efficient Mesh Reconstruction and Texturing of Oracle Bones Carnegie Mellon University The high-fidelity 3D digitization of small, detailed cultural heritage objects, such as Oracle Bones, presents significant challenges…
• MitoChontrol: Adaptive mitochondrial filtering for robust single-cell RNA sequencing quality control University of Pittsburgh Mitochondrial transcript abundance is a standard quality control metric in single-cell RNA sequencing, but fixed percentage thresholds…
• Toward Robust AI Agents: A Closed-Loop Task Planning–Execution–Feedback Framework for Open Scenarios Carnegie Mellon University Background: In open environments, AI agents often suffer from insufficient robustness and verifiability, primarily due to target drift,…
• NILO: Nested Iterative Optimization for Video Bitrate Ladder Construction Carnegie Mellon University In video-on-demand services, each video title is deployed as a bitrate ladder—a set of pre-encoded representations with increasing…
• Understanding Fabrication Variability in Core‐Shell Soft Biomaterials Using Stochastic Artificial Intelligence University of Aveiro Approaches for the fabrication of biomaterials are currently numerous, with a wide diversity of available material precursors,…
• Global optimization tailored for graphics processing units: Complete and rigorous search for large-scale nonlinear minimization Carnegie Mellon University This paper introduces a numerical method to enclose the global minimum of a nonlinear function subject to simple bounds on the…
• World2Rules: A Neuro-Symbolic Framework for Learning World-Governing Safety Rules for Aviation Carnegie Mellon University Many real-world safety-critical systems are governed by explicit rules that define unsafe world configurations and constrain agent…
• Evidence-based management in practice: measuring the use of four core sources of evidence University of Malta Purpose This purpose of this empirical study is to develop and validate the Evidence-Based Management Source Utilisation Scale…
• Cross sections measurement of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> <mml:msup> <mml:mi>e</mml:mi> <mml:mo>+</mml:mo> </mml:msup> <mml:msup> <mml:mi>e</mml:mi> <mml:mo>−</mml:mo> </mml:msup> <mml:mo stretchy="false">→</mml:mo> <mml:mi mathvariant="normal">Ξ</mml:mi> <mml:mo stretchy="false">(</mml:mo> <mml:mn>1530</mml:mn> <mml:msup> <mml:mo stretchy="false">)</mml:mo> <mml:mn>0</mml:mn> </mml:msup> <mml:msup> <mml:mover accent="true"> <mml:mi mathvariant="normal">Ξ</mml:mi> <mml:mo stretchy="false">¯</mml:mo> </mml:mover> <mml:mn>0</mml:mn> </mml:msup> <mml:mo>+</mml:mo> <mml:mi mathvariant="normal">c</mml:mi> <mml:mo>.</mml:mo> <mml:mi mathvariant="normal">c</mml:mi> <mml:mo>.</mml:mo> </mml:math> and search for <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> <mml:mrow> <mml:mi>ψ</mml:mi> <mml:mo stretchy="false">(</mml:mo> <mml:mn>3770</mml:mn> <mml:mo stretchy="false">)</mml:mo> <mml:mo stretchy="false">→</mml:mo> <mml:mi mathvariant="normal">Ξ</mml:mi> <mml:mo stretchy="false">(</mml:mo> <mml:mn>1530</mml:mn> <mml:msup> <mml:mrow> <mml:mo stretchy="false">)</mml:mo> </mml:mrow> <mml:mrow> <mml:mn>0</mml:mn> </mml:mrow> </mml:msup> <mml:msup> <mml:mrow> <mml:mover accent="true"> <mml:mrow> <mml:mi mathvariant="normal">Ξ</mml:mi> </mml:mrow> <mml:mrow> <mml:mo stretchy="false">¯</mml:mo> </mml:mrow> </mml:mover> </mml:mrow> <mml:mrow> <mml:mn>0</mml:mn> </mml:mrow> </mml:msup> <mml:mo>+</mml:mo> <mml:mi mathvariant="normal">c</mml:mi> <mml:mo>.</mml:mo> <mml:mi mathvariant="normal">c</mml:mi> <mml:mo>.</mml:mo> </mml:mrow> </mml:math> Anonymous et al. Using <a:math xmlns:a="http://www.w3.org/1998/Math/MathML" display="inline"> <a:msup> <a:mi>e</a:mi> <a:mo>+</a:mo> </a:msup> <a:msup>…
• EEG Foundation Model Improves Online Directional Motor Imagery Brain-computer Interface Control Carnegie Mellon University Brain-Computer interfaces (BCIs) offer a link between neural signals and external computation, enabling control of devices for the…
• Integration of Optimization and Discrete-Event Simulation in Supply Logistics of Carbon Dioxide Capture and Storage Decision Sciences (United States) In this paper, we describe five solution strategies for scheduling CO2 shipments in a carbon capture and storage (CCS) maritime supply…
• Comparing Developer and LLM Biases in Code Evaluation Carnegie Mellon University As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture…

Query this set from any AI agent

Agents: a markdown version of this page is at https://publicmcp.org/library/cmu.md.