Forecast2Anomaly (F2A): Adapting Multivariate Time Series Foundation Models for Anomaly Prediction
"预训练模型" 相关文章
Epistemic Uncertainty for Generated Image Detection
Aligning Brain Signals with Multimodal Speech and Vision Embeddings
字节Seed团队发布循环语言模型Ouro，在预训练阶段直接「思考」，Bengio组参与
ICCV25 Highlight｜格灵深瞳RICE模型狂刷榜单，让AI「看懂」图片的每个细节
A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
PLAN: Proactive Low-Rank Allocation for Continual Learning
Steering Autoregressive Music Generation with Recursive Feature Machines
LENS: Large Pre-trained Transformer for Exploring Financial Time Series Regularities
Extracting alignment data in open models
马普所&谷歌等提出AnyUp：无需再训练的通用特征上采样，推理即用，效果SOTA！
北大等提出MaskDCPT：通用图像修复预训练新范式，PSNR提升3.77dB
马普所&谷歌等提出AnyUp：无需再训练的通用特征上采样，推理即用，效果SOTA！
Coupled Diffusion Sampling for Training-Free Multi-View Image Editing
Exploratory Causal Inference in SAEnce
No ML Team? See How This Startup Built a Powerful AI Copilot in Weeks!
Dr.LLM: Dynamic Layer Routing in LLMs
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion
