ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Algebraic Decomposition Theory for Transformer Length Generalization
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical D…
Deliberate Practice: Learning Robot Skills under a Budget
Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Net…
Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and anal…
Training AI Scientists to Replicate Research
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
A Compositional Theory of Curvature in Probabilistic Circuits
Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security …
LipCache: A Local Inference Proxy with Certified Caching for Edge Image Classification Se…
LOB-ID: Evaluating Synthetic Market Data by Inception Distances
TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
Generative data assimilation highlights fronts as key regulators of ocean energy cascade
CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without C…
Google is making private AI practical with homomorphic encryption
Kog is going deeper to squeeze more inference out of GPUs
Samsung health AI models analyse wearable biosignal data
Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based F…
India Less Exposed to AI Job Risks Than Others, Goldman Says
Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy
QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruc…
Deep Vision in Smart Manufacturing: MODERN Framework for Intelligent Quality Monitoring a…
Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Confli…
Fashion Outfit Generation via Unified Sequential Composition Models
How AI text watermarking works
How Organizations Use AI: Evidence from ChatGPT [pdf]
Anthropic set AI agents loose on the same task. They started a turf war.