What happens when an LLM never sees material beyond fifth grade?
Explorar
Noticias de IA
21010 elementos — filtrados, clasificados y sin duplicados
AI in drug discovery – what it is, where we stand and the path forward
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization
Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimize…
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Comp…
Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based P…
Falsehood and Impossibility Are Different Directions in an AI's Representation of Language
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…
TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
Novel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data
Into the ORBIT for Time Series: Training Regimes for Foundation Models
Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger La…
Physics-informed distribution of relaxation times estimation and latent-space condition m…
InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers
UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with…
TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Reg…
LOB-ID: Evaluating Synthetic Market Data by Inception Distances
LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
Training AI Scientists to Replicate Research
Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and anal…
Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Net…
Deliberate Practice: Learning Robot Skills under a Budget
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical D…
Algebraic Decomposition Theory for Transformer Length Generalization
ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models