#cross-domain News & Analysis

7 articles tagged with #cross-domain. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

7 articles

AIBullisharXiv – CS AI · Mar 46/102

🧠

SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training

Researchers developed SAE-based Transferability Score (STS), a new metric using sparse autoencoders to predict how well fine-tuned large language models will perform across different domains without requiring actual training. The method achieves correlation coefficients above 0.7 with actual performance changes and provides interpretable insights into model adaptation.

AINeutralarXiv – CS AI · Mar 116/10

🧠

EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering

Researchers introduce EgoCross, a new benchmark to evaluate multimodal AI models on egocentric video understanding across diverse domains like surgery, extreme sports, and industrial settings. The study reveals that current AI models, including specialized egocentric models, struggle with cross-domain generalization beyond common daily activities.

AINeutralarXiv – CS AI · Mar 27/1017

🧠

Exploring Robust Intrusion Detection: A Benchmark Study of Feature Transferability in IoT Botnet Attack Detection

Researchers conducted a benchmark study on IoT botnet intrusion detection systems, finding that models trained on one network domain suffer significant performance degradation when applied to different environments. The study evaluated three feature sets across four IoT datasets and provided guidelines for improving cross-domain robustness through better feature engineering and algorithm selection.

AIBullisharXiv – CS AI · Feb 276/105

🧠

Generative Data Transformation: From Mixed to Unified Data

Researchers propose TAESAR, a new data-centric framework for improving recommendation models by transforming mixed-domain data into unified target-domain sequences. The approach uses contrastive decoding to address domain gaps and data sparsity issues, outperforming traditional model-centric solutions while generalizing across various sequential models.

AINeutralarXiv – CS AI · Feb 274/105

🧠

CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection

Researchers introduce CGSA, a new framework for source-free domain adaptive object detection that integrates Object-Centric Learning into DETR-based detectors. The approach uses Hierarchical Slot Awareness and Class-Guided Slot Contrast modules to improve cross-domain object detection without retaining source data, demonstrating superior performance on multiple datasets.

AINeutralarXiv – CS AI · Mar 34/105

🧠

From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing

Researchers developed TAR-FAS, a new AI framework that uses external visual tools to improve face anti-spoofing detection across different domains. The system employs a Chain-of-Thought approach with visual tools to detect subtle spoofing patterns that traditional methods miss, achieving state-of-the-art performance.

AINeutralarXiv – CS AI · Mar 24/105

🧠

Bridging Dynamics Gaps via Diffusion Schr\"odinger Bridge for Cross-Domain Reinforcement Learning

Researchers propose BDGxRL, a novel framework using Diffusion Schrödinger Bridge to enable reinforcement learning agents to transfer policies across different domains without direct target environment access. The method aligns source domain transitions with target dynamics through offline demonstrations and introduces reward modulation for consistent learning.