TrustMI: Causally controlling how assistants trust their users
Research
Research News
New papers, breakthroughs and academic AI research
Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII
Research
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Research
Introducing Code-Switched Contexts to Cognitively-Inspired Bilingual Model Training
Research
Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing
Research
Shared Stopping Decisions Change Answers in HQQ Cache Quantization
Research
Probabilistic Race and Ethnicity Prediction Using Group-Specific Name Lists
Research
ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory
Research
LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration
Research
PCLM: Small-target localization with frozen CLIP via prototype contrast and local magnification
Research
Repeated-Measure Leakage, Distribution Shift, and Reliability under Partial Observation in Patient World Models
Research
DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression
Research