4
Reassessing Muon for Matrix Factorization
This paper provides a theoretical analysis of the Muon optimizer to clarify the mechanisms behind its performance advantages in large-scale deep learning.
4
From Language to Navigation Goals: A Vision-Language Approach for Semantic Navigation of Mobile Robots Using RGB-D Perception
A new framework enables mobile robots to interpret natural language commands for autonomous navigation using RGB-D perception.
4
Set-shifting Behavioral Test for Harnessed Agents
A new benchmark based on cognitive psychology tests has been developed to evaluate how AI agents adapt when the reliability of their tools changes during operation.
4
Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of an Agentic AI Tutoring System
A study evaluates the scalability and classroom performance of an AI tutoring agent that integrates retrieval-augmented generation with structured knowledge models.
4
Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science
This paper proposes a framework for networked intelligence that uses shared context graphs to facilitate collaboration among multiple AI agents in scientific research.
4
Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography
A study evaluating deep learning models for echocardiography analysis reveals that current attribution methods often fail to verify temporal faithfulness in medical imaging predictions.
4
When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech
The study evaluates the impact of audio separation preprocessing on zero-shot automatic speech recognition performance, finding that cleaner audio does not always improve transcription accuracy.
4
Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning
A new decoupled training strategy for transfer learning aims to reduce computational and energy costs by optimizing classifier heads separately from feature extraction layers.
4
The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models
The paper provides a theoretical framework linking Joint-Embedding Predictive Architectures to active inference principles through variational free energy.
4
ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
The proposed ScanFocus framework addresses computational efficiency and precision in spatio-temporal video grounding through a coarse-to-fine processing approach.
4
ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level
The ExTernD method introduces a post-training factorization technique for large language models that utilizes expanded-rank ternary decomposition to improve quantization efficiency and accuracy.
4
STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting
The authors introduce STKAN, a spatio-temporal forecasting architecture that leverages Kolmogorov-Arnold Networks to better model complex traffic data.
4
How Far Can Root Cause Analysis Go on Real-World Telemetry Data?
A study evaluating root cause analysis in microservice failures reveals that current AI and classical methods struggle to effectively process large-scale, multimodal telemetry data.
4
GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning
The GHR-VLM framework combines grounded reasoning with vision-language models to enable zero-shot video analytics for transit systems without requiring task-specific training data.
4
The Hitchhiker's Guide to Monoculture
An analysis of Kaggle contest submissions examines whether the use of AI coding assistants is leading to increased homogenization of software development outputs.
4
Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
A new defense mechanism called Traffic-Aware Randomized Smoothing has been proposed to improve the robustness of LLM-based network intrusion detection systems against traffic manipulation.
4
Faithful Autoformalization of Natural Language Assertions
The authors introduced Monty, a framework designed to improve the accuracy of autoformalization by converting natural language specifications into executable software assertions.
4
MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentation
MedDiffuseMix provides a saliency-guided diffusion framework to augment medical imaging data while preserving critical diagnostic features.
4
FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents
FixItFlow is an automated system that leverages large language models to generate technical troubleshooting guides from historical cloud incident data.
4
A Self-Evolving Agent for Longitudinal Personal Health Management
HealthClaw is a proposed self-evolving agent architecture designed to provide longitudinal health management by maintaining private memory of user routines and medical history.
4
Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild
Researchers have proposed a training-free approach for detecting human-object interactions in the wild by leveraging the capabilities of multimodal large language models.
4
MASPRM: Multi-Agent System Process Reward Model
The Multi-Agent System Process Reward Model provides a method to evaluate and optimize message sequences between agents during inference-time search.
4
When Bots Join the Team: Bot Adoption and the Institutional Fabric of Open-Source Software Projects
Researchers analyzed nearly 3,000 GitHub projects to understand how the integration of automated bots as active participants influences the organizational structure of open-source software teams.
4
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
The authors present a method for integrating compiler feedback directly into the autoregressive decoding process to improve the quality of AI-generated code.