HuggingFace
SLAM in Low-Light Environments: Project Report
Simultaneous localization and mapping (SLAM) is one of the fundamental problems in robotics, as it enables autonomous...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation
Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and...
HuggingFace
Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
Real-time EEG classification on edge devices is bottlenecked by the floating-point arithmetic of conventional neural ...
HuggingFace
ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models
Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independentl...
arXiv
The Ethics of Autonomous AI Agents for Offensive Security
LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling -- dete...
arXiv
The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models
Large-scale pretrained language models such as T5 and BERT have demonstrated strong capabilities for generating struc...
arXiv
PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires...
arXiv
Self-supervision drives representational convergence in medical foundation models more than clinical supervision
Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scal...
arXiv
Sound Probabilistic Safety Bounds for Large Language Models
We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) gener...
arXiv
Courteous Anticipation: Improving Long-Lived Task Planning in Persistent Shared Environments
We consider a task planning scenario in which robots sharing a persistent environment are assigned tasks one at a tim...
arXiv
Don't Trust the Label: License Laundering in AI Supply Chains
AI artifacts move through a multi-platform supply chain, spanning datasets and models on Hugging Face and application...
arXiv
Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout
RGB-D semantic segmentation has achieved remarkable progress, yet most models assume that RGB and depth are always av...