AI
Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving
Researchers have proposed an open-vocabulary, energy-based sparse framework called Lagrange for gene...
AI
Scaling Laws for Task-Specific LLM Distillation
Researchers have developed empirical scaling laws for compressing large language models (LLMs) in sp...
AI
The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
A recent arXiv paper argues that autonomous AI systems should have three key features to safely pres...
AI
PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs
Researchers from Hong Kong Polytechnic University have developed PolyUQuest, a web retrieval-augment...
AI
Evidence-Aware MapReduce for Forkable Compute
Researchers have developed an 'evidence-aware MapReduce' system, which allows fo...
AI
OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets
Researchers have developed a system called OriginBlame that tracks the origin of...
AI
CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models
Researchers propose CacheSpec, an optimization framework that uses reusable prog...
AI
Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain
Researchers have created a benchmark called Telco-GAIA to evaluate the performan...