AIAttnStudio

归档研究领域研究标签

找不到相关结果。

Federico

AI Research Lab

Hello, I'm Federico.

关于实验室 / About

公告

欢迎来到Federico的个人博客

分类

Large Language Models

Computer Vision

标签

3D VAE 3DGS 3D匹配 3D生成 3D网格生成 3D重建 4-bit Acting ActionMesh Activation Quantization AdaLN Adapter Advantage Estimation Agent Agent Architecture AI Agent AI绘画 Alignment Alignment Tax Attention Attention Mechanism AutoGPT AWQ Beam Search BERT Best-of-N Bradley-Terry Cache Eviction Chain-of-Thought Chat Template Civitai Claude CLIP CM CogVideoX Communication Consistency Distillation Consistency Models Constitutional AI Context Extension Context Length Extension Continuous Batching ControlNet ControlNet-XS CoT CroCo CUDA Graphs Curriculum Learning CVPR 2024 CVPR 2026 Dark Knowledge Data Construction Data Deduplication Data Engineering Data Filtering Data Parallelism Data Quality Data Scaling Dataset Curation DDIM DDPM DeepSeek DeepSeek-R1 DeepSeek-R1-Zero DeepSpeed Diffusion Diffusion Transformer Direct Preference Optimization Distillation Distributed Training Distribution Shift DiT DoRA DPO DreamBooth Dreambooth DUSt3R ECCV 2024 EDM ELBO Fast Reciprocal Matching Feature Distillation FlashAttention Flow Matching FLUX FSDP Function Calling GAE GAN对比 Gaussian Splatting GGUF Goodhart's Law GPT GPT-4V GPTQ GPU Cluster GPU Optimization Gradient Synchronization Group Relative Policy Optimization GRPO Guanaco Ho Hugging Face Hunyuan3D HunyuanDiT Inference Scaling Law Inference-Time Compute InstantMesh Instruction Following Instruction Tuning INT4 INT8 IPO Jamba JSON Schema KL Divergence Knowledge Distillation KTO KV Cache LangGraph Language Model Large Reconstruction Model Latent Video Diffusion LCM LDM Lipman Llama LLaMA llama.cpp LLaVA LLaVA-1.5 LLaVA-1.6 LLM LLM Agent LLM Alignment LLM Distillation LLM Fine-Tuning LLM Inference LLM Reasoning LLM Safety LLM Scaling LLM Training Long Context LongRoPE LoRA Low-Rank Adaptation LRM LVDM LyCORIS Mamba Mamba-2 Markdown MASt3R Math Reasoning MDX Megatron-LM Memory Memory Management Memory Optimization Mesh MeshFlow MeshVAE Metric Pointmap MiniLLM Mixed Precision Mixtral MLP MMDiT Model Alignment Model Compression Model Merging Model Optimization Model Parallelism MoE Multi-Agent Multimodal NeRF NF4 NTK ODE One-2-3-45 Open-Sora OpenAI OpenLRM OpenVLA Optimal Transport ORPO Overoptimization PagedAttention Parameter-Efficient Parameter-Efficient Fine-Tuning PBR材质 PEFT Physical AI Pipeline Parallelism Planning Pointmap Policy Gradient Position Encoding Position Interpolation Post-Training PPO Pre-training Pre-training Data Preference Alignment Preference Data Preference Learning Prefix Caching Prefix Tuning PRM Process Reward Model Prompt Engineering Prompt Tuning Proximal Policy Optimization QLoRA Quantization Qwen-VL Radford ReAct Reasoning Reasoning Models Rectified Flow Reinforced Fine-Tuning Reinforcement Learning Relative Position Response Distillation Reward Hacking Reward Model Reward Modeling RLAIF RLHF RoPE RoPE Scaling Rotary Embeddings Rotary Position Embedding RT-2 S4 Scaffold-GS Scaling Laws Score Matching SD3 SDXL LoRA SD微调 Self-Consistency Sequence Parallelism Serving SFT SFT Data SimPO SLAT Song Song ChunLIU Sora SSM Stable Diffusion Stable Diffusion 3 Stable Diffusion XL Stable Diffusion微调 Supervised Fine-Tuning T2I-Adapter Temporal 3D Diffusion Tensor Parallelism Test-Time Scaling Text-to-Image Textual Inversion TokenMerge Tool Use Training Objective Transfer Learning Transformer Tree of Thoughts TRELLIS TripoSG TRPO Trust Region TTCT TTST UNet VAE VecSet Vicuna Video Diffusion Video DiT Video-to-4D VideoLDM Vision Transformer ViT VLA vLLM VLM Wan2.1 Weight Decomposition Weight Quantization YaRN Yarn Zero-shot π₀ 一步生成三维重建交叉注意力位姿估计体渲染体积渲染具身智能前馈生成加速推理动作分块动画网格生成单图像3D 单图像3D重建去噪扩散变分推断可微渲染图像分类图像理解图像生成图像识别多格式输出多模态多模态助手多模态控制多模态推理多目立体大语言模型姿态控制对比学习局部特征常微分方程开源 VLM 循环神经网络微软思维链感知压缩扩散模型扩散模型加速扩散模型蒸馏拓扑一致指令微调推理文本到图像文本编码器文章示例新视角合成无监督标定时序一致性时空建模机器人学习机器人操控条件扩散条件生成概率流模仿学习模型扩展模态对齐深度估计深度图控制深度学习混元3D 混合专家模型潜在扩散模型点云条件生成状态空间模型生成式 AI 生成式AI 确定性采样视觉定位视觉指令微调视觉理解视觉生成视觉语言动作模型视觉语言模型视觉语言预训练视角自适应视频压缩视频生成神经渲染神经辐射场稀疏激活稠密匹配纹理合成线性注意力结构化潜在表示结构化高斯腾讯自注意力艺术家风格计算机图形学计算机视觉语义压缩语言模型轨迹视图辐射场边缘检测连续潜在空间逆向过程选择性扫描选择性状态空间锚点长序列建模隐式模型零样本分类零样本迁移非马尔可夫高斯泼溅

Large Language Models32 Generative AI14 3D Vision5 Computer Vision2 Deep Learning2 Embodied AI1 文章示例1

搜索

搜索

请输入搜索关键词。

站点统计

57文章

7分类

404标签

日

一

二

三

四

五

六

文章目录

当前页面没有目录

Federico

AI Research Lab

Hello, I'm Federico.

关于实验室 / About

公告

欢迎来到Federico的个人博客

分类

Large Language Models

Computer Vision

标签

3D VAE 3DGS 3D匹配 3D生成 3D网格生成 3D重建 4-bit Acting ActionMesh Activation Quantization AdaLN Adapter Advantage Estimation Agent Agent Architecture AI Agent AI绘画 Alignment Alignment Tax Attention Attention Mechanism AutoGPT AWQ Beam Search BERT Best-of-N Bradley-Terry Cache Eviction Chain-of-Thought Chat Template Civitai Claude CLIP CM CogVideoX Communication Consistency Distillation Consistency Models Constitutional AI Context Extension Context Length Extension Continuous Batching ControlNet ControlNet-XS CoT CroCo CUDA Graphs Curriculum Learning CVPR 2024 CVPR 2026 Dark Knowledge Data Construction Data Deduplication Data Engineering Data Filtering Data Parallelism Data Quality Data Scaling Dataset Curation DDIM DDPM DeepSeek DeepSeek-R1 DeepSeek-R1-Zero DeepSpeed Diffusion Diffusion Transformer Direct Preference Optimization Distillation Distributed Training Distribution Shift DiT DoRA DPO DreamBooth Dreambooth DUSt3R ECCV 2024 EDM ELBO Fast Reciprocal Matching Feature Distillation FlashAttention Flow Matching FLUX FSDP Function Calling GAE GAN对比 Gaussian Splatting GGUF Goodhart's Law GPT GPT-4V GPTQ GPU Cluster GPU Optimization Gradient Synchronization Group Relative Policy Optimization GRPO Guanaco Ho Hugging Face Hunyuan3D HunyuanDiT Inference Scaling Law Inference-Time Compute InstantMesh Instruction Following Instruction Tuning INT4 INT8 IPO Jamba JSON Schema KL Divergence Knowledge Distillation KTO KV Cache LangGraph Language Model Large Reconstruction Model Latent Video Diffusion LCM LDM Lipman Llama LLaMA llama.cpp LLaVA LLaVA-1.5 LLaVA-1.6 LLM LLM Agent LLM Alignment LLM Distillation LLM Fine-Tuning LLM Inference LLM Reasoning LLM Safety LLM Scaling LLM Training Long Context LongRoPE LoRA Low-Rank Adaptation LRM LVDM LyCORIS Mamba Mamba-2 Markdown MASt3R Math Reasoning MDX Megatron-LM Memory Memory Management Memory Optimization Mesh MeshFlow MeshVAE Metric Pointmap MiniLLM Mixed Precision Mixtral MLP MMDiT Model Alignment Model Compression Model Merging Model Optimization Model Parallelism MoE Multi-Agent Multimodal NeRF NF4 NTK ODE One-2-3-45 Open-Sora OpenAI OpenLRM OpenVLA Optimal Transport ORPO Overoptimization PagedAttention Parameter-Efficient Parameter-Efficient Fine-Tuning PBR材质 PEFT Physical AI Pipeline Parallelism Planning Pointmap Policy Gradient Position Encoding Position Interpolation Post-Training PPO Pre-training Pre-training Data Preference Alignment Preference Data Preference Learning Prefix Caching Prefix Tuning PRM Process Reward Model Prompt Engineering Prompt Tuning Proximal Policy Optimization QLoRA Quantization Qwen-VL Radford ReAct Reasoning Reasoning Models Rectified Flow Reinforced Fine-Tuning Reinforcement Learning Relative Position Response Distillation Reward Hacking Reward Model Reward Modeling RLAIF RLHF RoPE RoPE Scaling Rotary Embeddings Rotary Position Embedding RT-2 S4 Scaffold-GS Scaling Laws Score Matching SD3 SDXL LoRA SD微调 Self-Consistency Sequence Parallelism Serving SFT SFT Data SimPO SLAT Song Song ChunLIU Sora SSM Stable Diffusion Stable Diffusion 3 Stable Diffusion XL Stable Diffusion微调 Supervised Fine-Tuning T2I-Adapter Temporal 3D Diffusion Tensor Parallelism Test-Time Scaling Text-to-Image Textual Inversion TokenMerge Tool Use Training Objective Transfer Learning Transformer Tree of Thoughts TRELLIS TripoSG TRPO Trust Region TTCT TTST UNet VAE VecSet Vicuna Video Diffusion Video DiT Video-to-4D VideoLDM Vision Transformer ViT VLA vLLM VLM Wan2.1 Weight Decomposition Weight Quantization YaRN Yarn Zero-shot π₀ 一步生成三维重建交叉注意力位姿估计体渲染体积渲染具身智能前馈生成加速推理动作分块动画网格生成单图像3D 单图像3D重建去噪扩散变分推断可微渲染图像分类图像理解图像生成图像识别多格式输出多模态多模态助手多模态控制多模态推理多目立体大语言模型姿态控制对比学习局部特征常微分方程开源 VLM 循环神经网络微软思维链感知压缩扩散模型扩散模型加速扩散模型蒸馏拓扑一致指令微调推理文本到图像文本编码器文章示例新视角合成无监督标定时序一致性时空建模机器人学习机器人操控条件扩散条件生成概率流模仿学习模型扩展模态对齐深度估计深度图控制深度学习混元3D 混合专家模型潜在扩散模型点云条件生成状态空间模型生成式 AI 生成式AI 确定性采样视觉定位视觉指令微调视觉理解视觉生成视觉语言动作模型视觉语言模型视觉语言预训练视角自适应视频压缩视频生成神经渲染神经辐射场稀疏激活稠密匹配纹理合成线性注意力结构化潜在表示结构化高斯腾讯自注意力艺术家风格计算机图形学计算机视觉语义压缩语言模型轨迹视图辐射场边缘检测连续潜在空间逆向过程选择性扫描选择性状态空间锚点长序列建模隐式模型零样本分类零样本迁移非马尔可夫高斯泼溅

站点统计

57文章

7分类

404标签

© 2026 Federico·隐私政策·服务条款·RSS·Sitemap

Powered byAstro&Federico

当前页面没有目录