Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems
Federated continual learning approach for autonomous mobile fleets with layer-wise forgetting protection.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Federated continual learning approach for autonomous mobile fleets with layer-wise forgetting protection.
Unsubstantiated social media commentary about transhumanism.
AAC: differentiable landmark compressor for ALT shortest-path heuristics with admissibility-by-construction.
RespondeoQA: first bilingual Latin-English QA benchmark with 7,800 pairs from pedagogical sources.
F²LP-AP: training-free label propagation for semi-supervised node classification on heterophilous graphs.
Simulation-Based Inference with neural posterior estimation for industrial equipment degradation monitoring; domain-specific application without novel AI methods.
Near-Future Policy Optimization improves RLVR convergence by balancing off-policy trajectory quality and distribution proximity for LLM post-training.
Dynamic pricing framework for LLM-augmented freight negotiation using adaptive concession strategies under real-time rate updates.
Interval POMDP shielding method for autonomous systems with learned perception, using confidence intervals to block unsafe actions under sensor uncertainty.
Prompt optimization for LLM-as-a-Judge evaluation on legal QA; tests transfer across Qwen3-32B and DeepSeek-V3 judges on LEXam benchmark.
Supplement Generation Training trains smaller LLMs to generate adaptive task-specific prompts for larger models, reducing post-training costs.
Likelihood factorization for hierarchical SBI reduces simulator costs by training neural surrogates per-site instead of multi-site sampling.
Anthropic suspended ~110 users at agricultural tech company without warning; users report lack of transparency in account enforcement.
COMPASS framework uses adaptive semantic sampling with language-specific PEFT adapters to mitigate negative cross-lingual interference in multilingual LLMs.
ONOTE benchmark for omnimodal music notation processing across auditory, visual, symbolic domains; addresses Western notation bias and LLM judge hallucinations.
Textual Parameter Graph Optimization (TPGO) enables multi-agent systems to self-improve via structural parameter evolution, moving beyond flat prompt tuning.
Framework for auditing whether AI-synthesized summaries of public consultation faithfully represent source populations using optimal transport and causal inference.
GFlowNet-based approach for model adaptation in digital twins of evolving natural systems with partial observations and mechanistic simulators.
QuanForge mutation testing framework for Quantum Neural Networks addressing stochastic factors and quantum measurement randomness.
Auto-ART: structured literature synthesis of adversarial robustness field (2020-2026) plus open-source framework with 50+ attacks, 28 defenses, and Robustness Diagnostic Index.
Uber exhausts 2026 AI budget by April due to rising Claude Code inference costs.
StormNet applies graph neural networks to bias-correct storm surge forecasts from ADCIRC models.
MGDA-Decoupled balances multiple alignment objectives in DPO-based LLM training via geometry-aware optimization.
Empirical study of 40+ transformer compression experiments on GPT-2 and Mistral 7B reveals variance-importance decoupling.
Systematic fairness evaluation across six LLMs on intersectional demographic biases using benchmark datasets.
Feature whitening improves interpretability of linear neuroimaging models for brain biomarker discovery.
User subjective impressions of GPT Image 2 output quality combining GTA 6 and Cyberpunk 2077 aesthetics.
Framework for high-consequence decision-making augmented by machine intelligence and agentic metadata stewardship.
ORPHEAS is a specialized bilingual Greek-English embedding model for cross-lingual RAG applications.