2903 articles tagged with #ai. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
AIBullisharXiv โ CS AI ยท Mar 36/106
๐ง Researchers introduce MetaState, a recurrent augmentation for discrete diffusion language models (dLLMs) that adds persistent working memory to improve text generation quality. The system addresses the 'Information Island' problem where intermediate representations are discarded between denoising steps, achieving improved accuracy on LLaDA-8B and Dream-7B models with minimal parameter overhead.
AIBullisharXiv โ CS AI ยท Mar 36/109
๐ง Researchers introduce In-Context Policy Optimization (ICPO), a new method that allows AI models to improve their responses during inference through multi-round self-reflection without parameter updates. The practical ME-ICPO algorithm demonstrates competitive performance on mathematical reasoning tasks while maintaining affordable inference costs.
AIBullisharXiv โ CS AI ยท Mar 36/108
๐ง Researchers introduce GRAD-Former, a novel AI framework for detecting changes in satellite imagery that outperforms existing methods while using fewer computational resources. The system uses gated attention mechanisms and differential transformers to more efficiently identify semantic differences in very high-resolution satellite images.
AIBullisharXiv โ CS AI ยท Mar 36/107
๐ง Researchers propose TC-SSA, a token compression framework that enables large vision-language models to process gigapixel pathology images by reducing visual tokens to 1.7% of original size while maintaining diagnostic accuracy. The method achieves 78.34% overall accuracy on SlideBench and demonstrates strong performance across multiple cancer classification tasks.
AIBullisharXiv โ CS AI ยท Mar 36/108
๐ง Researchers introduce SkeleGuide, a new AI framework that uses explicit skeletal reasoning to generate more realistic human images in existing scenes. The system addresses common issues like distorted limbs and unnatural poses by incorporating structural priors based on human skeletal structure.
AIBullisharXiv โ CS AI ยท Mar 37/107
๐ง ATLAS is a new AI-driven framework that uses large language models to automate System-on-Chip (SoC) security verification by converting threat models into formal verification properties. The system successfully detected 39 out of 48 security weaknesses in benchmark tests and generated correct security properties for 33 of those vulnerabilities.
AIBullisharXiv โ CS AI ยท Mar 37/108
๐ง Researchers introduce FastCode, a new framework for AI-assisted software engineering that improves code understanding and reasoning efficiency. The system uses structural scouting to navigate codebases without full-text ingestion, significantly reducing computational costs while maintaining accuracy across multiple benchmarks.
AIBullisharXiv โ CS AI ยท Mar 36/106
๐ง Researchers developed TARSE, a new AI system for clinical decision-making that retrieves relevant medical skills and experiences from curated libraries to improve reasoning accuracy. The system performs test-time adaptation to align language models with clinically valid logic, showing improvements over existing medical AI baselines in question-answering benchmarks.
AINeutralarXiv โ CS AI ยท Mar 37/107
๐ง Researchers introduced EraseAnything++, a new framework for removing unwanted concepts from advanced AI image and video generation models like Stable Diffusion v3 and Flux. The method uses multi-objective optimization to balance concept removal while preserving overall generative quality, showing superior performance compared to existing approaches.
AIBullisharXiv โ CS AI ยท Mar 36/107
๐ง Researchers developed ThreatFormer-IDS, a Transformer-based intrusion detection system that achieves robust cybersecurity monitoring for IoT and industrial networks. The system demonstrates superior performance in detecting zero-day attacks while providing explainable threat attribution, achieving 99.4% AUC-ROC on benchmark tests.
AIBullisharXiv โ CS AI ยท Mar 36/107
๐ง Researchers developed a spatiotemporal diffusion autoencoder using CT brain images to predict stroke outcomes and evolution. The AI model achieved best-in-class performance for predicting next-day severity and functional outcomes using a dataset of 5,824 CT images from 3,573 patients across two medical centers.
AIBullisharXiv โ CS AI ยท Mar 37/107
๐ง Researchers propose Talaria, a new confidential inference framework that protects client data privacy when using cloud-hosted Large Language Models. The system partitions LLM operations between client-controlled environments and cloud GPUs, reducing token reconstruction attacks from 97.5% to 1.34% accuracy while maintaining model performance.
AINeutralarXiv โ CS AI ยท Mar 36/106
๐ง Researchers documented their experience training Summer-22B, a video foundation model developed from scratch using 50 million clips. The report details engineering challenges, dataset curation methods, and architectural decisions, emphasizing that dataset engineering consumed the majority of development effort.
AINeutralarXiv โ CS AI ยท Mar 36/108
๐ง Researchers introduce GMP, a new benchmark highlighting critical challenges in AI content moderation systems when dealing with co-occurring policy violations and dynamic platform rules. The study reveals that current large language models struggle with consistent moderation when policies are unstable or context-dependent, leading to either over-censorship or allowing harmful content.
AIBullisharXiv โ CS AI ยท Mar 37/106
๐ง Researchers introduce MultiPUFFIN, a multimodal AI foundation model that predicts molecular properties for drug discovery and materials science. The model combines multiple data types and thermodynamic principles to achieve superior performance while using 2000x fewer training molecules than existing models like ChemBERTa-2.
AIBullisharXiv โ CS AI ยท Mar 36/106
๐ง Researchers created OpenRad, a curated repository containing approximately 1,700 open-access AI models for radiology. The platform aggregates scattered radiology AI research into a standardized, searchable database that includes model weights, interactive applications, and spans all imaging modalities and radiology subspecialties.
AIBullisharXiv โ CS AI ยท Mar 37/107
๐ง Researchers propose MIST-RL, a reinforcement learning framework that improves AI code generation by creating more efficient test suites. The method achieves 28.5% higher fault detection while using 19.3% fewer test cases, demonstrating significant improvements in AI code verification efficiency.
AIBullisharXiv โ CS AI ยท Mar 36/107
๐ง Researchers developed BioProAgent, a neuro-symbolic AI framework that combines large language models with deterministic constraints to enable reliable scientific planning in wet-lab environments. The system achieves 95.6% physical compliance compared to 21.0% for existing methods by using finite state machines to prevent costly experimental failures.
AIBullisharXiv โ CS AI ยท Mar 36/109
๐ง Researchers introduced AWE, a memory-augmented multi-agent framework for autonomous web penetration testing that outperforms existing tools on injection vulnerabilities. AWE achieved 87% XSS success and 66.7% blind SQL injection success on benchmark tests, demonstrating superior accuracy and efficiency compared to general-purpose AI penetration testing tools.
AINeutralarXiv โ CS AI ยท Mar 35/103
๐ง Researchers developed behavioral generative agents powered by large language models to simulate consumer decision-making in energy operations. The study found these AI agents can model heterogeneous customer behavior and provide insights into rare events like blackouts, offering a scalable tool for energy policy analysis.
AIBullisharXiv โ CS AI ยท Mar 36/1011
๐ง Researchers developed FreeGNN, a continual source-free graph neural network framework for renewable energy forecasting that adapts to new sites without requiring source data or target labels. The system uses a teacher-student strategy with memory replay and achieved strong performance across three real-world datasets including GEFCom2012, Solar PV, and Wind SCADA.
AIBullisharXiv โ CS AI ยท Mar 36/1010
๐ง DoorDash developed an AI system that uses multiple data sources to better understand ambiguous search queries by combining catalog data with web search results. The system achieved significant accuracy improvements over traditional methods and is now deployed across 95% of DoorDash's daily search traffic.
AIBullisharXiv โ CS AI ยท Mar 36/106
๐ง Researchers developed SpecularNet, a lightweight AI framework for detecting phishing websites that operates without external databases or cloud services. The system achieves 93.9% F1 score while reducing inference time from several seconds to 20 milliseconds per webpage, making it practical for real-world deployment.
AIBullisharXiv โ CS AI ยท Mar 36/104
๐ง Researchers developed AIRMap, a deep-learning framework that generates radio maps for wireless network simulation over 100x faster than traditional ray tracing methods. The AI model achieves under 4 dB RMSE accuracy in 4 ms per inference and significantly outperforms traditional simulators when calibrated with field measurements.
$NEAR
AIBullisharXiv โ CS AI ยท Mar 36/103
๐ง Researchers developed a hybrid AI approach combining tensor decomposition with neural networks to improve MIMO channel estimation for 6G wireless systems under pilot signal limitations. The method achieves significant performance improvements over traditional approaches, with up to 13.11 dB better accuracy in specific scenarios.
