AIBullisharXiv – CS AI · Jun 107/10
🧠Researchers introduce EPIC, a novel approach to on-device Retrieval-Augmented Generation (RAG) that prioritizes user preferences as compact personal context while operating under strict memory constraints. The method achieves dramatic efficiency gains—reducing memory usage by 2,404x and latency by 32x—while improving preference-following accuracy by 18.79 percentage points across multiple benchmarks.
AIBullisharXiv – CS AI · Jun 27/10
🧠GuidaPA is a privacy-preserving chatbot for Italian public administration that uses federated learning to train on sensitive documentation without centralizing data. The system achieves comparable performance to traditional centralized fine-tuning while keeping sensitive data distributed across agency servers, demonstrating federated learning's viability for regulated institutional deployments.
AIBullisharXiv – CS AI · May 297/10
🧠Pocket-Dentist presents an efficiency-aware benchmark for dental image analysis using compact multimodal vision-language models, demonstrating that smaller 2B-parameter models outperform larger counterparts while consuming significantly fewer computational resources. Successfully deployed on iPhone hardware, the approach enables privacy-preserving dental prescreening outside specialist centers with practical latency and memory constraints.
AIBullisharXiv – CS AI · May 297/10
🧠SURGENT is a multi-agent AI system designed to assist surgical teams throughout the perioperative workflow by combining large language models with specialized reasoning, memory management, and clinical knowledge retrieval. The system addresses critical limitations of standard LLMs—including token constraints and poor context retention—and demonstrates superior performance across five surgical tasks compared to existing medical AI frameworks.
AIBullisharXiv – CS AI · May 287/10
🧠FD-RAG introduces a federated framework for retrieval-augmented generation that enables decentralized LLM deployment across edge devices without centralizing sensitive data. The system achieves 7.8% accuracy improvements and 8.4x latency reductions by splitting lightweight memory access from expensive LLM reasoning, while aggregating anonymized knowledge across fragmented device networks.
AIBullisharXiv – CS AI · May 277/10
🧠MobileExplorer is a new framework that enables faster on-device inference for mobile GUI agents by leveraging parallel exploration of UI elements during model reasoning time. The system reduces latency by 23% while maintaining or improving task success rates, addressing privacy and network dependency concerns in mobile AI applications.
AIBullisharXiv – CS AI · May 97/10
🧠Researchers propose constant-context skill learning, a framework enabling LLM agents to learn reusable task procedures as lightweight modules rather than storing long prompts in memory. The approach reduces token usage per inference by 2-7x while maintaining or improving performance across multiple benchmark environments, addressing the privacy-capability tradeoff in agent deployment.
🧠 Llama
AIBearisharXiv – CS AI · May 77/10
🧠Researchers demonstrate that the shuffling defense mechanism used to protect Transformer model weights during secure inference can be broken through an alignment attack, allowing adversaries to recover weights with minimal cost. The attack exploits multiple shuffled activations by finding a common permutation, undermining a key security assumption in privacy-preserving machine learning.
AIBullisharXiv – CS AI · Apr 107/10
🧠Researchers introduce ConfusionPrompt, a privacy framework for large language models that decomposes user prompts into smaller sub-prompts mixed with pseudo-prompts before sending to cloud servers. The method protects user privacy while maintaining higher utility than existing perturbation-based approaches and works with existing black-box LLMs without modification.
AINeutralarXiv – CS AI · Jun 255/10
🧠EmotionAI presents a locally-run computational pipeline that analyzes speech emotion recognition without uploading sensitive audio to cloud services, combining ASR, speaker diarization, and LLM reasoning. While the system achieves 48.8% accuracy on emotion classification—above random baselines but below traditional methods—it prioritizes privacy and auditability over state-of-the-art performance, running entirely on CPU with minimal latency.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers developed an Explainable AI framework using Federated Learning to identify career-related depression and anxiety among university students while preserving privacy. The model achieved 92.08% accuracy by analyzing behavioral data and facial expressions, successfully identifying key depression indicators consistent with psychological theory.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers propose a federated learning framework that combines ARIMA, GARCH, LSTM-Attention, and XGBoost models to forecast global carbon emissions while preserving data privacy. The system enables collaborative forecasting across distributed clients without sharing raw data, achieving R² values averaging 0.73 across 14 test clients.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers propose a subspace-regularized federated learning approach for low-rank adaptation (LoRA) that addresses geometric misalignment issues when training large language models across distributed clients with heterogeneous data. The method achieves superior performance on RoBERTa-large while demonstrating near-perfect basis overlap (0.9999) across multiple models and random seeds, outperforming existing federated learning baselines.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers propose privacy-preserving group emotion recognition (GER) systems using multimodal audio-video analysis instead of individual biometric data. Two novel architectures—a cross-attention fusion model and a Variational Encoder Multi-Decoder framework—demonstrate that competitive emotion inference is achievable at the collective level without monitoring individual faces, voices, or gazes.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers introduce Alternating Token-Weighted Unlearning (ATWU), a new method for removing specific knowledge from language models while maintaining their general capabilities. The approach identifies which tokens are most relevant for forgetting by measuring conflict with model retention objectives, achieving state-of-the-art results without requiring external supervision or auxiliary models.
AINeutralarXiv – CS AI · Jun 26/10
🧠SUPREME is an open-source framework that accelerates machine unlearning evaluation by distributing computation across multiple GPUs, addressing a critical bottleneck in AI model evaluation. The framework enables reproducible testing of data removal methods at scale, which has implications for privacy-preserving AI development and regulatory compliance.
AIBullisharXiv – CS AI · Jun 16/10
🧠Researchers propose FedVPA-GP, a federated learning framework that enables privacy-preserving alignment of large language models while preserving diverse user preferences instead of averaging them into a single monolithic reward model. The approach uses a Gumbel-Softmax prior and orthogonal loss to prevent posterior collapse and successfully disentangles conflicting user intents in decentralized settings.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers introduce FedMPT, a novel federated learning method for multi-label recognition in vision-language models that addresses overfitting to spurious label correlations in decentralized settings. The approach uses causal modeling, LLM-driven condition analysis, and optimal transport mechanisms to improve model robustness when adapting to clients with heterogeneous private data.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers propose Orthogonal Projection Layer (OPL), a privacy-preserving technique for video anomaly detection systems that removes facial attributes while maintaining detection accuracy. The approach uses weak supervision to suppress identifying information without adversarial training, introducing a new framework for evaluating privacy-utility tradeoffs in surveillance applications.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce CalBench, a controlled evaluation framework for testing multi-agent LLM coordination in calendar scheduling scenarios where agents must negotiate shared commitments while protecting private information. The benchmark measures coordination quality, communication efficiency, fairness, and privacy leakage in decentralized systems where no single agent has complete information.
🏢 Meta
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce TAP (Two-Stage Adaptive Personalization), a novel federated learning framework that enables personalized fine-tuning of foundation models across clients with heterogeneous tasks and modalities. The method uses mismatched architectures to prevent cross-task interference and post-FL distillation to recover shared knowledge, advancing practical deployment of AI systems in distributed environments.
AI × CryptoBullishCrypto Briefing · May 76/10
🤖Tether has launched on-device medical AI models that reportedly outperform Google's comparable systems in benchmark testing. The development emphasizes privacy-preserving medical reasoning by enabling AI inference directly on devices rather than cloud servers, potentially reducing costs and regulatory friction in healthcare applications.
AIBullisharXiv – CS AI · Apr 106/10
🧠Researchers introduce EmoMAS, a Bayesian multi-agent framework that enables small language models to perform sophisticated negotiation by treating emotional intelligence as a strategic variable. The system coordinates game-theoretic, reinforcement learning, and psychological agents to optimize negotiation outcomes while maintaining privacy through edge deployment, demonstrating performance comparable to larger models across high-stakes domains.
AINeutralarXiv – CS AI · Apr 106/10
🧠Researchers present the first empirical study of machine unlearning in hybrid quantum-classical neural networks, adapting classical unlearning methods to quantum settings and introducing quantum-specific strategies. The study reveals that quantum models can effectively support unlearning, with performance varying based on circuit depth and entanglement structure, establishing baseline insights for privacy-preserving quantum machine learning systems.
AIBullisharXiv – CS AI · Mar 66/10
🧠Researchers introduce DP-MTV, the first framework enabling privacy-preserving multimodal in-context learning for vision-language models using differential privacy. The system allows processing hundreds of demonstrations while maintaining formal privacy guarantees, achieving competitive performance on benchmarks like VizWiz with only minimal accuracy loss.
