AI
Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems
Researchers have developed a new type of neural network surrogate that can solve complex electromagn...
AI
Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets
Researchers have proposed a new evaluation protocol for black-box jailbreak attacks called Fair-ASR....
AI
Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-Based Reinforcement Learning
Researchers have developed a new method for prioritizing experiences in reinforcement learning, part...
AI
PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX
Researchers have introduced PTXBench, a benchmark that evaluates and adapts large language models (L...
AI
Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design
Researchers have developed a new framework called MCTH (Monte Carlo Tree Halluci...
AI
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation
Researchers have introduced SemComp-Bench, a benchmark for evaluating the perfor...
AI
Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Task
Researchers have developed a method to reduce the energy consumption of large la...
AI
Explainable AI-Powered Framework for Video-Based Skill Assessment in Cataract Surgery
Researchers have developed an AI-powered framework for assessing surgical skills...