AI
CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models
Researchers propose CacheSpec, an optimization framework that uses reusable program caches to reduce...
AI
Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain
Researchers have created a benchmark called Telco-GAIA to evaluate the performance of artificial int...
AI
CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning
Researchers have developed CMI-Mem, a lightweight memory manager for agent systems that uses reinfor...
AI
RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation
Researchers have developed RSMeM, a system that enhances the performance of remote sensing agents by...
AI
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
Researchers have developed a method called Margin Calibration to improve the rob...
AI
A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models
Researchers have compared five different methods to defend against 'vision-langu...
AI
Nova: An End-to-End MLIR Compiler for Deep Learning
Researchers have developed an automated compiler called Nova that can optimize t...
AI
Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language
Researchers have developed a domain-specific language (ADSL-PDE) to improve the ...