Transformer

技术

Transformer，基于自注意力机制的深度学习架构，广泛作为 GPT 等大语言模型和视觉模型的底层基础

479 次提及342 个连接最近出现: 2026-06-29

关系图谱

关系 (372)

使用技术 (284)

Transcribe LongCat-Next InfoTok STEM Qwen3 ResPose KV Cache Attention Mechanism Kimi Moonshot GLM-5 Hand2World 小牛电动 o3 MSA VHTformer UniPR CLIP LongCat-AudioDiT Uni-1 ProMoE Lingshu-Cell MAI-Transcribe-1 VITA-QinYu 具身智能 DeepSeek R1 emojiGPT MAGE SEMF SentiAvatar PhysGM 多模态理解 RAAP OmniLottie 腾讯 LeVERB MoT-2B Google DeepMind Gemini 2.5 Qwen2.5 Llama 3.2 Qwen3-14B HiVG Sora RT-1 Transformer CARE Transformer LPM 1.0 T(R,O) Grasp DeepSeek V3 JoyAI-Image-Edit Ultrasound-CLIP AutoSOTA StarVLA softmax 视频生成 LLaMA 3 Morpheus-1 Mythos BioMD Claude FreeLOC ERNIE-Image LingBot-Map Genie 3 ElevenLabs DiT360 AC²-VLA GPT-2 GPT-4 DeepSeek V3 文心一言 4.0 π0.7 RAM框架 StreamingVLA GPT2-XL BERT-large MoE Cosmos Attention Mechanism 新烛时代 QuatRoPE OpenMythos Claude Sonnet 4.6 Ouroboros Claude Mythos BioSeq2Seq TokenRig HedgeMamba Pythia-1B AtomVLA Being-H0.7 GPT Image 2 o1 美团 KV Cache LitePT OmniHuman-1 DeepSeek V4 RT-2 Gato Octo PMDformer Agent 阿里巴巴 GPT-4o Learning Mechanics Neural Scaling Laws Wan 2.1-14B 神经缩放律深度求索 DeepSeek CoastGPT HappyHorse HiDream-O1-Image MiniCPM-o 4.5 大模型权重 UniConverter LangFlow MiMo LDA-1B SenseNova U1 Nemotron 3 Nano Omni JiT MotuBrain AX8850N VEGA-3D LLM Uni-1.1 Claude Opus 4.6 RecBERT Oxygen Vision 视觉语言导航 TranscriptFormer LLaVA-NeXT 文心 5.1 Opus 4.6 FFN Dropout softmax RT-1 Radar 大模型 TML-Interaction-Small ICAD-LLM ChatGPT GRN 2B VGGT HTD NitroGen ReasonBrain C-JEPA PoliFormer Anthropic Mini Phoenix MotionMAR TMT VQ-VAE Gemini 2.0 DAG CLIP 模型 HappyHorse 1.0 SANA-WM VGGT-Ω ViT³ GPT-3 FuXi-Alpha FuXi-Beta HSTU Nemotron GridS GemDepth Together AI Meta AI Whisper HiDream系列大模型 Crysformer PettiChat IBM Bob VeRL-Omni DiffusersFSDP Megatron Uni-Hand ChatGPT VTLA Meki CamFormer SparsePrime Bonsai Image 4B WavFlow LegoACE GPIC BitNet b1.58 Ouro 1.4B Jet-Nemotron 2B Agnes-2.0-Flash MPA Cosmos 3 G0.5 UniMedVL WeatherMesh 6 PVA-Net LingBot-VA 混元优化器大模型 Atlas MoCos 神经基础模型 Gemma 4 12B NVIDIA Cosmos 3 Qwen3-VL WALL-WM Dreamer V3 V-JEPA 2 Stem稀疏注意力 PhysX-Anything Stem ResNet Grok Imagine 0.9 SAM 3D Body 隐式思维链 LLaVA-v1.5-7B D4RT MiniMax M3 Qwen3-Coder-30B-A3B Qwen3.5-35B-A3B δ-mem TranSG SAM 3D UniCM WLA-0 Supervised Memory Training BatteryMFormer UiT PromptStereo Recursive Superintelligence GuidedVLA 《Happy-LLM：从零开始构建大模型》HRM-Text AlphaFold OpenAI Recursive RAG S²AM3D Baton Qwen2.5-VL Monet-7B Fast-WAM GLM-5.2 Magpie 1.0 Gemini 3 OpenRath CogVideoX1.5-5B Wan2.1-1.3B WorldScape Policy NVIDIA DreamZero MiniT2I G0.5 模型 PromptDepth Kairos 开悟世界模型月之暗面字节跳动 AstraBrain-WBC 0.5 Humanoid-GPT Gemma 4 谷歌 Gemini MultiMoE Magi-1 DepthVLM Aether AI NEO-ov Aether AI Gemini 2.5 Pro TransPrune Chinchilla Gopher Visics Engram Wan-Streamer REViT Mirendi FTP-1 Wan Streamer v0.1 DSpark Nemotron 3 Ultra FLAG LoopWM MOSS-TTS

应用于 (53)

关系图谱

关系 (372)

使用技术 (284)

应用于 (53)

竞争 (12)

基于 (10)

使用 (7)

创建 (5)

发布 (1)

相关文章 (479)