AI
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Researchers from multiple institutions have developed a framework called SLAI T-Rex for efficiently ...
AI
Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models
Researchers have developed a new method for evaluating the performance of generative models in prese...
AI
Cross-Cohort Spectral-Temporal Dissociation in Frozen EEG Foundation-Model Representations
Researchers explored whether frozen representations from five EEG foundation models can decode long-...
AI
Untrainable elements determine what physical learning remembers
Researchers have identified two distinct factors that influence what physical learning rules remembe...
AI
The Epistemic Politics of AI Anthropomorphism
The paper argues that AI anthropomorphism is not just a problem of user misperce...
AI
Approximate Speculative Decoding
Researchers have introduced Approximate Speculative Decoding (ASD), a training-f...
AI
Complete, Scalable, and Robust Prioritized Planning for Multi-Robot Ordered Storage and Retrieval at Maximum Capacity
Researchers have developed a planning algorithm for multiple robots to efficient...
AI
Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol
Researchers have proposed a framework for evaluating the impact of AI-assisted v...