AI
Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments
Researchers have created two minimal simulation foundations for large language models (LLMs) and vis...
AI
Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning
Researchers have developed a method to improve the reliability of large language models (LLMs) in sc...
AI
The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
Researchers have proposed a method to audit prefix invariance in sequence models. Prefix invariance ...
AI
AraDetox: A Multi-Dialect Arabic Detoxification Dataset
Researchers have created a new dataset called AraDetox for cleaning up harmful language in Arabic so...
AI
Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text
Researchers propose a new framework to improve the performance of spoken languag...
AI
Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling
Researchers have discovered a vulnerability in the way some AI systems handle sa...
AI
Deep Learning-Based Multi-User Communication Design for Dense IoT Networks: Interference-Aware Finite-Blocklength Communication and Preliminary MIMO Extensions
Researchers have developed a deep learning-based communication system for dense ...
AI
What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation
Researchers have developed a benchmark to evaluate the quality of research ideas...