InferScale: GPU-Native KV Injection for Personalized LLM Serving
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscri…
Field Codes for Distributed Coupling Samplers and Certified Empirical Transport
Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
Object Detection for Autonomous Driving in Chinese Rural Scenes: An Experimental Study on…
CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge …
Evaluating Regional Bias in LLMs From Abstract Stereotype to Concrete Social Decision-Mak…
A new benchmark for evaluating patient-facing health AI agents
How enabling two settings tripled our scores on the ARC-AGI-3 benchmark
GPT-5.6 vs. Claude Fable 5 for Physical AI, which performs best?
OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment
Feature Bagging Provides Stability
Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Languag…
Surrogate assisted diversity estimation in neural ensemble search
Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Me…
Actions Have Consequences: Detecting Outcome Performativity using Intervention Testing
Human diversity fuels collective creativity that large language models cannot simulate or…
What happens when you put AI to work deciphering lost languages?
OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth …
StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction
ToxScreen: Detecting Whether an LLM Has Been Poisoned
Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models
Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility
AI as Friction for Reflection Support in Ideation
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Commu…
FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning
PRISM-Net: Patient-specific reference-guided inter-breast symmetry matching for three-cla…
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
MediaWiki Code2Code Search: Neural Retrieval for the Semantic Discovery of Open-Source So…