arXiv
VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents
Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecu...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models
Vision language models (VLMs) have made remarkable progress in visual reasoning during the last decade. Most evaluati...
arXiv
Scalable Visual Pretraining for Language Intelligence
The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpor...
arXiv
PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesis
Current electroencephalography (EEG)-based dream detection relies on power spectral density (PSD) and statistical mom...
HuggingFace
Scalable Visual Pretraining for Language Intelligence
The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpor...
HuggingFace
A Sovereign, Open-Source Foundation Model for German and English
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation mod...
HuggingFace
Video Generation Models are General-Purpose Vision Learners
Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. Wh...
HuggingFace
Self-Guided Test-Time Training for Long-Context LLMs
Long-context processing has become increasingly important for large language models (LLMs), but simply extending the ...
HuggingFace
Trust Region Policy Distillation
Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Di...
HuggingFace
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to...
HuggingFace
PanoWorld: Real-World Panoramic Generation
In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotati...
HuggingFace
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining lea...