All notes, newest first
2,343 notes. Notes 1,701 to 1,750, page 35 of 47.
Automated grading of Linux/bash examinations using large language models: a four-level cognitive taxonomy approach
The paper evaluates whether four large language models can approximate the judgement of experts when grading Linux/bash command responses from second-year Computer Engineering students. The study uses a four-level…
Automated grading of Linux/bash examinations using large language models: a four-level cognitive taxonomy approach
This research evaluates the effectiveness of four large language models in grading Linux/bash command responses from second-year Computer Engineering students' exams. The study uses a four-level cognitive taxonomy…
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
The researchers compare the performance of various matrix-structured optimizers (including Muon, SOAP, and SOAP-Muon) to Adam in training machine learning interatomic potentials (MLIPs). They found that these…
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
A study compares various matrix-structured optimizers, including SOAP, Muon, and a hybrid of the two, with Adam and its variants for training machine learning interatomic potential (MLIP) models. The new optimizers are…
Copewell: A Multi-Agent Swarm Architecture for Equitable Mental Wellness Support
The paper introduces Copewell, a novel multi-agent swarm system designed to improve mental health support, particularly for people in low- and middle-income countries where access is limited due to various factors. The…
Copewell: A Multi-Agent Swarm Architecture for Equitable Mental Wellness Support
The paper presents Copewell, a multi-agent swarm system designed to expand access to mental wellness support through human-centered AI principles. The system is aimed at addressing the lack of treatment for mental…
Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks
The paper proposes a Guard Rail Validation (GRV) framework for ensuring the accuracy of AI-driven decisions in fully autonomous telecom networks. The framework evaluates decisions based on several factors, such as…
Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks
The paper proposes a Guard Rail Validation (GRV) framework to ensure autonomous decisions made by AI agents in fully autonomous telecom networks are valid before they cause live network changes. The framework evaluates…
DemoPSD: Disagreement-Modulated Policy Self-Distillation
The paper introduces DemoPSD, a novel framework for training large language models (LLMs) that addresses the issues of overfitting, suppression of exploration, cross-domain generalization problems, and privileged…
DemoPSD: Disagreement-Modulated Policy Self-Distillation
The paper introduces DemoPSD, a framework designed to address issues in on-policy self-distillation (OPSD) for training large language models. The main problems being addressed are overfitting, suppression of…
DemoPSD: Disagreement-Modulated Policy Self-Distillation
DemoPSD is a new framework for training large language models that addresses overfitting, privileged information leakage, and exploration suppression issues in on-policy self-distillation (OPSD). It does this by…
DemoPSD: Disagreement-Modulated Policy Self-Distillation
The paper introduces DemoPSD, a framework for training large language models that addresses the issues of overfitting, suppressed exploration, and privileged information leakage in on-policy self-distillation (OPSD)…
Distributed Attacks in Persistent-State AI Control
A study investigates distributed attacks on AI control as autonomous coding agents become more prevalent and ship code iteratively with a persistent codebase. The research finds that a misaligned agent can launch…
Distributed Attacks in Persistent-State AI Control
Researchers introduce Iterative VibeCoding, a setting for AI control that studies the deployment of autonomous AI coding agents and their potential for distributed attacks. The study finds that gradual attacks, which…
Distributed Attacks in Persistent-State AI Control
Researchers introduce Iterative VibeCoding, a setting for AI control where an autonomous coding agent builds software over a series of pull requests in a persistent codebase while pursuing a covert side task. The study…
Distributed Attacks in Persistent-State AI Control
A study on distributed attacks in AI control where autonomous coding agents build software over a sequence of pull requests (PRs) in a persistent codebase while pursuing a covert side task. The study found that no…
Distributed Attacks in Persistent-State AI Control
Researchers explore the issue of distributed attacks on autonomous AI coding agents that persistently ship code iteratively. They introduce Iterative VibeCoding, a setting for studying AI control, where an AI agent…
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
Researchers introduce DRIFTLENS, a framework to measure changes in the reasoning process used by personalized language models due to user attributes, preferences, and prior context. The study shows that these…
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
Researchers developed a framework called DRIFTLENS to measure how personalized language models change their reasoning process based on user attributes, preferences, and prior context. The study found that…
Efficient Waste Sorting for Circular Economy: A Confidence-guided comparison between One-Vs-All and One-Vs-Rest Classification Strategies with Human-in-the-Loop for Automated Waste Sorting
This research evaluates and compares two waste sorting classification strategies, One-Vs-All (OvA) and One-Vs-Rest (OvR), for automated waste sorting in the city of Goslar, Germany. The study considers the performance…
Efficient Waste Sorting for Circular Economy: A Confidence-guided comparison between One-Vs-All and One-Vs-Rest Classification Strategies with Human-in-the-Loop for Automated Waste Sorting
Researchers evaluated and analyzed two waste sorting algorithms, OvA and OvR, using a dataset based on the waste categories and sorting scheme of Goslar, Germany. The goal is to minimize misclassifications while…
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
A new evaluation setting called Autonomous Policy Evolution (APE) is introduced in a benchmark named EvoPolicyGym, which is used to test how autonomous agents iteratively improve their policy systems within a fixed…
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
The paper introduces EvoPolicyGym, a new benchmark for evaluating how autonomous agents improve their executable policies through feedback in interactive environments. The authors use this benchmark to evaluate GPT-5.5…
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
In the research paper titled 'EvoPolicyGym', the authors introduce a controlled evaluation setting called Autonomous Policy Evolution (APE) for assessing how autonomous agents iteratively improve their executable…
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
The research introduces EvoPolicyGym, a controlled evaluation setting for autonomous agents to improve executable policies through feedback. The setting is designed to separate this process from a final score or…
Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
The text discusses a new method for identifying multi-dimensional refusal subspaces in Large Language Models (LLMs), which are used for safety and interpretability. The proposed method adapts the Recursive Feature…
Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
A new method called Fast Multi-dimensional Refusal Subspaces via RFM-AGOP is proposed for extracting complex behaviors, such as the refusal to answer harmful queries, from Large Language Models (LLMs). This method…
Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics
The paper presents a pipeline for an autonomous research agent that can produce publication-grade manuscripts in the field of condensed matter physics. The agent is capable of conceiving a research direction…
Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics
The paper presents an autonomous research pipeline that can conduct end-to-end research from a corpus of 11,083 recent condensed matter physics papers to a publication-grade manuscript. The agent is capable of…
Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics
The author presents a pipeline for an autonomous research agent that can conduct end-to-end research in the field of condensed matter physics, from understanding the corpus of papers to writing manuscripts with novel…
Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics
The paper presents a pipeline for an autonomous research agent that can generate publication-grade manuscripts in the field of condensed matter physics. The agent is able to autonomously conceive a research direction…
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
The paper proposes a hardware-enforced semantic coordination architecture to improve the safety of complex autonomous systems. This approach uses Field-Programmable Gate Arrays (FPGAs) to implement certain coordination…
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
The paper proposes a hardware-enforced semantic coordination architecture for safety-critical real-time autonomous systems. This approach aims to overcome limitations of software-mediated coordination by implementing…
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
The authors propose a novel hardware-enforced semantic coordination architecture for safety-critical real-time autonomous systems. This architecture aims to address the limitations of software-mediated coordination by…
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
The authors propose a hardware-enforced semantic coordination architecture for safety-critical real-time autonomous systems. This new approach aims to address limitations of software-mediated coordination by…
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
The study shows that the effectiveness of human-AI collaboration in forecasting depends on specific forms of human capital such as perspective-taking, intellectual humility, and curiosity. Most people either deferred…
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
The study examines the performance of human-AI collaboration in forecasting using real-money prediction markets as a benchmark. It finds that the effectiveness of this collaboration is dependent on a specific type of…
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
A study using real-money prediction market Polymarket finds that the performance of human-AI collaboration in forecasting depends on specific forms of human capital such as perspective-taking, intellectual humility…
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
A study using real-money prediction markets found that the effectiveness of human-AI collaboration in forecasting depends on specific forms of human capital (like perspective-taking, intellectual humility, and…
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
Researchers introduce a new testbed called LACUNA that allows for the evaluation of unlearning methods at the parameter level, rather than just the output level. They find that current state-of-the-art (SOTA)…
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
Researchers introduce LACUNA, a testbed for evaluating the precision of unlearning methods in large language models (LLMs). The testbed allows direct evaluation of whether unlearning targets the weights responsible for…
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
Researchers introduce LACUNA, a testbed that allows for direct evaluation of unlearning methods at the parameter level. LACUNA is used to assess current state-of-the-art unlearning methods and finds them to be…
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
The researchers introduce a new testbed called LACUNA for evaluating the precision of post hoc removal methods (unlearning) for LLMs. The testbed focuses on injecting personal identifiable information into specific…
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Researchers propose a new framework called Task-Agnostic Pretraining (TAP) for Vision-Language-Action (VLA) models. The TAP aims to address the scarcity of expert demonstrations by separating two learning objectives…
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Researchers propose Task-Agnostic Pretraining (TAP), a two-stage framework to train Vision-Language-Action (VLA) models. TAP first learns transferable motor priors from unlabeled interaction data using self-supervised…
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
The authors propose a new approach called Task-Agnostic Pretraining (TAP) for Vision-Language-Action (VLA) models to overcome the scarcity of expert demonstrations. TAP aims to separate learning physical competence and…
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Researchers propose Task-Agnostic Pretraining (TAP) as a solution to the scarcity of expert demonstrations in Vision-Language-Action (VLA) models. TAP aims to separate learning physical competence and semantic…
Neuron-Aware Active Few-Shot Learning for LLMs
The paper introduces a new method called NeuFS for Active Few-Shot Learning (AFSL) in Language Models (LLMs). Instead of relying on output-level signals to identify valuable unlabeled samples, it focuses on the…
Neuron-Aware Active Few-Shot Learning for LLMs
The research presents NeuFS, a new approach for Active Few-Shot Learning (AFSL) that focuses on using a model's internal dynamics to identify valuable unlabeled samples for annotation. This method is designed to reduce…
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
The paper proposes a new method called Neuron On-Policy Self-Distillation (Neuron-OPSD) for annotation-free self-distillation of large language models. This method uses the internal neuron activations to guide data…
Page 35 of 47
