AI
Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
Researchers have developed a new method for discovering ensemble zero-cost proxies in neural archite...
AI
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
A new framework called EDGE is proposed to improve reinforcement learning in complex tasks. Existing...
AI
Bulbul: A Dataset for Dialectal Arabic Speech Recognition
A new dataset called Bulbul has been created to help improve speech recognition in dialectal Arabic....
AI
NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus
Researchers have developed a new method called NoTB to assess the correctness of register-transfer-l...
AI
Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments
Researchers from the University of Technology Sydney have proposed a new method ...
AI
Barycentric Fused Gromov-Wasserstein Balancing for Causal Inference under Multiple Treatments
Researchers have developed a new deep learning framework called CIHSI-Net for es...
AI
Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets
Researchers propose a system called WebVisus to help scientists explore large-sc...
AI
CRS-Bench: A Reference-Relative Reliability Benchmark for Medical Image Encoders
Researchers have developed a benchmark called CRS-Bench to evaluate the performa...