Analysing Environmental Efficiency in AI for X-Ray Diagnosis
arXiv:2511.07436v1 Announce Type: new Abstract: The integration of AI tools into medical applications has aimed to improve the efficiency of…
Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks
arXiv:2511.06696v1 Announce Type: cross Abstract: Pretrained equivariant graph neural networks based on spherical harmonics offer efficient and accurate alternatives to…
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
arXiv:2511.05459v2 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage,…
Evidence-Bound Autonomous Research (EviBound): A Governance Framework for Eliminating False Claims
arXiv:2511.05524v1 Announce Type: new Abstract: LLM-based autonomous research agents report false claims: tasks marked “complete” despite missing artifacts, contradictory metrics,…
Rethinking Metrics and Diffusion Architecture for 3D Point Cloud Generation
arXiv:2511.05308v2 Announce Type: replace-cross Abstract: As 3D point clouds become a cornerstone of modern technology, the need for sophisticated generative…
ML-EcoLyzer: Quantifying the Environmental Cost of Machine Learning Inference Across Frameworks and Hardware
arXiv:2511.06694v1 Announce Type: cross Abstract: Machine learning inference occurs at a massive scale, yet its environmental impact remains poorly quantified,…
Improving Diagnostic Performance on Small and Imbalanced Datasets Using Class-Based Input Image Composition
arXiv:2511.03891v2 Announce Type: replace-cross Abstract: Small, imbalanced datasets and poor input image quality can lead to high false predictions rates…
TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework
arXiv:2511.05385v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models’ (LLMs) reliability. For flexibility,…
AI Assisted AR Assembly: Object Recognition and Computer Vision for Augmented Reality Assisted Assembly
arXiv:2511.05394v1 Announce Type: cross Abstract: We present an AI-assisted Augmented Reality assembly workflow that uses deep learning-based object recognition to…
On the Brittleness of CLIP Text Encoders
arXiv:2511.04247v2 Announce Type: replace-cross Abstract: Multimodal co-embedding models, especially CLIP, have advanced the state of the art in zero-shot classification…