FLOPs vs Real Work: The Importance of Replication in AI Efficiency Assessment
arXiv:2608.14550v1 Announce Type: new
Abstract: AI efficiency has recently taken the spotlight in both academy and industry due to massive model scales, high energy demands, and environmental costs. While reporting Floating Point Operations (FLOPs) is a traditional approach for assessing computatio...
Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation
arXiv:2608.14594v1 Announce Type: new
Abstract: Projected Gradient Descent (PGD) is widely used to evaluate adversarial robustness, typically via final adversarial accuracy, which does not capture model behaviour throughout the attack. Recent work proposes trajectory-level diagnostics, such as loss...
Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
arXiv:2608.13596v1 Announce Type: new
Abstract: Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales. We study an underexplored cross-scale setting: improving a small recipient language model with a stronger donor despite substantial arc...
arXiv:2608.13590v1 Announce Type: new
Abstract: XGBoost is a very popular and powerful method for prediction. It iteratively fits simple decision trees to the residuals of the previous step. An efficient and scalable implementation is available. The standard loss function for XGBoost is the quadrat...
Which Site, and When: A Free-Satellite-Data Test of Himalayan Glacial Lake Bursts, Landslides, and Ice Floods
arXiv:2608.12422v1 Announce Type: new
Abstract: Two free satellite signals carry real information about glacial-lake outburst risk in the Nepal Himalaya: radar interferometry sees a moraine dam slowly sagging, and satellite weather marks the weeks when a primed lake is under stress. A companion fea...
MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
arXiv:2608.12435v1 Announce Type: new
Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic computation complexity during training and a key--value cache that grows line...
Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts
arXiv:2608.11212v1 Announce Type: new
Abstract: Top-k Mixture-of-Experts (MoE) routing is discontinuous, so a deployment-motivated numerical disturbance -- simulated 4-bit KV-cache quantization read by a protected BF16 gate -- pushes tokens across decision boundaries and flips which experts fire. T...
Terminal Symmetry as a Decision Resource: Statewise Refinement for Anytime Verified Construction
arXiv:2608.11318v1 Announce Type: new
Abstract: Many sequential construction tasks exhibit exact symmetry at completion while their execution remains directed and history-dependent. We develop a decision-resource view of terminal symmetry: process evidence supplies directionality, terminal correspo...
arXiv:2608.11256v1 Announce Type: new
Abstract: Institutions use commercial AI detectors for academic integrity, yet detectors cannot distinguish AI editing from full LLM drafts and may treat both as misconduct. In a controlled study of published English abstracts (four domains; 2013 to 2015 vs. 20...
In this article, you will learn the conceptual and practical differences between retrieval and memory in agentic AI systems, and how to combine both effectively....
Towards Sustainable Artificial Intelligence: A Comprehensive Review and Comparative Analysis of Deep Learning Models' Carbon Footprint
arXiv:2608.09998v1 Announce Type: new
Abstract: Artificial Intelligence (AI) and Machine Learning (ML) have become powerful tools for supporting and automating complex human tasks. Despite their benefits, growing attention has been directed toward their environmental implications, primarily due to ...
Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification
arXiv:2608.10007v1 Announce Type: new
Abstract: The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL), treat all training samples uniformly, which limits their robustness and effectiveness when applied...
arXiv:2608.09997v1 Announce Type: new
Abstract: Transformers have had a profound impact on the world of language processing and computer vision. As efforts to answer the million-dollar question of ``How does a Transformer learn?" have been increasing, existing interpretability studies primarily ana...
MIDAS: Mutual Information Disentanglement with Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis
arXiv:2608.09986v1 Announce Type: new
Abstract: Most existing multimodal sentiment analysis approaches assume access to complete multimodal inputs. However, real-world applications frequently encounter incomplete or corrupted modalities, posing a critical challenge. Although several methods have be...
Flow-by-Flow:Content-Judgment Bypass for Governing AI Output in High-Loss Domains
arXiv:2608.07474v1 Announce Type: new
Abstract: Prior work showed that human-in-the-loop oversight becomes structurally untenable in high-loss domains when AI output velocity V exceeds human cognitive capacity C_max. The operative constraint, however, is not V alone but V x L, where L denotes per-i...
Towards an Argumentative Foundation for Evaluative AI
arXiv:2608.07473v1 Announce Type: new
Abstract: Evaluative AI (EAI) has been recently proposed as a way to support human decision-making, not by producing a single recommendation, but by presenting competing hypotheses together with evidence for and against each. In this position paper, we advocate...
Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
arXiv:2608.07630v1 Announce Type: new
Abstract: We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources : aleatoric uncertainty, or locally scarce data. Our approach leverage...
Prompt Caching vs. Fine-Tuning: A Cost and Latency Decision Framework
In this article, you will learn how prompt caching and fine-tuning differ as strategies for reducing cost and latency in agentic AI systems, and how...
From Continuous Predictors to Clinical Thresholds: Early Evidence on Performance Trade-offs of Guideline-Based Categorisation for Ischaemic Stroke Outcome Prediction
arXiv:2608.05203v1 Announce Type: new
Abstract: Machine learning models achieve strong predictive accuracy for 90-day outcome prediction in acute ischaemic stroke, yet clinical adoption is limited by the misalignment of model explanations with clinicians' reasoning. Motivated by a clinician user st...
Monte Carlo Tree Search for Table-to-Multimodal Report Generation
arXiv:2608.04071v1 Announce Type: new
Abstract: Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligence. Existing methods suffer from fixed linear pipelines and isolated sub...
C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning
arXiv:2608.04013v1 Announce Type: new
Abstract: Recent advances in Multimodal Emotion Recognition in Conversations (MERC) highlight its reliance on complete multimodal inputs. However, real-world data often suffer from missing modalities due to transmission errors or user behavior, severely degradi...
Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation
arXiv:2608.04028v1 Announce Type: new
Abstract: Echo-state networks enable efficient temporal learning by fixing the recurrent dynamics and training only a linear readout. However, conventional reservoirs typically accommodate signal mixing, memory retention, and stability within a single random re...
A Long-Run Persistence Theory for AI Systems under the Redundancy-Adjusted Artificial Age Score (AAS)
arXiv:2608.04012v1 Announce Type: new
Abstract: Artificial intelligence systems are increasingly expected to operate over repeated cycles of interaction, adaptation, and update rather than through isolated one-shot outputs. This raises a fundamental theoretical question: can an AI system persist in...