AI Research 技术调研
Search
搜索
暗色模式
亮色模式
探索
标签: jepa
此标签下有28条笔记。
2026年7月16日
世界模型技术演进调研（2017 → 2026）· 主汇总
world-model
model-based-rl
video-generation
jepa
driving-world-model
game-world-model
physical-ai
survey
2026年7月16日
A Path Towards Autonomous Machine Intelligence
world-model
jepa
energy-based-model
self-supervised-learning
cognitive-architecture
vicreg
hierarchical-planning
position-paper
lecun
2026年7月16日
A-JEPA: Joint-Embedding Predictive Architecture Can Listen
jepa
audio
self-supervised
representation-learning
spectrogram
masking
curriculum-learning
vision-transformer
2026年7月16日
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (I-JEPA)
jepa
self-supervised
world-model
vision-transformer
latent-prediction
non-generative
masking
representation-learning
2026年7月16日
MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features
jepa
self-supervised
world-model
optical-flow
multi-task-learning
vicreg
convnext
video
motion-features
2026年7月16日
Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking
jepa
self-supervised
fmri
brain-foundation-model
neuroimaging
positional-encoding
medical-ai
spatiotemporal-masking
2026年7月16日
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
world-model
jepa
dinov2
latent-dynamics
model-predictive-control
zero-shot-planning
offline
patch-features
non-reconstructive
lecun
2026年7月16日
Learning and Leveraging World Models in Visual Representation Learning
jepa
world-model
self-supervised-learning
vision-transformer
equivariant-representation
predictor-finetuning
latent-prediction
representation-learning
2026年7月16日
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud
jepa
self-supervised
point-cloud
3d-vision
latent-prediction
non-generative
masking
representation-learning
transformer
2026年7月16日
S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention
jepa
eeg
self-supervised
bci
brain-computer-interface
spatial-masking
transfer-learning
signal-processing
2026年7月16日
Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation
jepa
world-model
self-supervised
music
audio
representation-learning
stem-separation
non-generative
retrieval
ismir
2026年7月16日
T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data
jepa
self-supervised
tabular-data
latent-prediction
non-contrastive
representation-learning
transformer
masking
regularization-token
2026年7月16日
Understanding World or Predicting Future? A Comprehensive Survey of World Models
world-model
survey
taxonomy
video-generation
embodied-ai
autonomous-driving
robotics
social-simulacra
sora
jepa
2026年7月16日
Revisiting Feature Prediction for Learning Visual Representations from Video (V-JEPA)
jepa
world-model
self-supervised
video-representation
latent-prediction
non-generative
masking
vision-transformer
frozen-evaluation
lecun
样本
2026年7月16日
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
jepa
world-model
intuitive-physics
violation-of-expectation
self-supervised
latent-prediction
video-representation
multimodal-llm-baseline
lecun
2026年7月16日
JEPA-Reasoner: Decoupling Latent Reasoning from Token Generation
jepa
latent-reasoning
coconut
gsm8k
decoupled-architecture
talker-model
error-containment
ema-target-encoder
cosine-similarity-loss
2026年7月16日
JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
jepa
speech-tokenizer
self-supervised-learning
finite-scalar-quantization
density-adaptive-attention
hifi-gan
conformer
neural-audio-codec
representation-learning
2026年7月16日
JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
jepa
text-to-image
cross-attention
flow-matching
masked-prediction
imagenet
multimodal-fusion
clip
mar
non-generative-lineage
2026年7月16日
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
jepa
ssl
self-supervised
isotropic-gaussian
sigreg
epps-pulley
lecun
balestriero
collapse-free
2026年7月16日
LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
jepa
llm-finetuning
llm-pretraining
embedding-space-objective
next-token-prediction
contrastive-representation-learning
custom-attention-mask
loss-dropout
lora
yann-lecun
2026年7月16日
Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
jepa
world-model
offline-rl
planning
mpc
latent-dynamics
goal-conditioned
trajectory-stitching
lecun
vicreg
2026年7月16日
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
world-model
jepa
self-supervised
video
action-conditioned
zero-shot-planning
robot-manipulation
predictive-embedding
non-generative
2026年7月16日
JEPA-VLA: Video Predictive Embedding is Needed for VLA Models
jepa
vla
world-model
v-jepa-2
visual-representation
policy-prior
gated-cross-attention
libero
robotwin
cortexbench
2026年7月16日
When Does LeJEPA Learn a World Model?
jepa
lejepa
identifiability
world-model-theory
hermite-polynomials
sigreg
gaussian-regularization
lean4-formal-verification
representation-learning
sturm-liouville
2026年7月16日
JEPA 谱系：I-JEPA · V-JEPA · V-JEPA 2 · DINO-WM · 非生成预测式世界模型
jepa
world-model
self-supervised
latent-prediction
non-generative
i-jepa
v-jepa
dino-wm
deep-dive
2026年7月16日
世界模型架构演进（RSSM · Transformer/AR · 扩散 · JEPA · 因果 tokenizer · 动作条件）
world-model
architecture
rssm
transformer
diffusion
jepa
tokenizer
action-conditioning
2026年7月16日
世界模型五大范式对比（RL-WM · 生成视频 · 交互/游戏 · 驾驶 · JEPA）
world-model
paradigms
rl-world-model
dreamer
muzero
video-generation
world-simulator
game-world-model
driving-world-model
jepa
survey
2026年7月16日
世界模型训练方法（想象力 RL · 扩散/流 · next-token · JEPA 回归 · 蒸馏）
world-model
training
imagination-rl
dreamer
muzero
diffusion
flow-matching
diffusion-forcing
autoregressive
jepa
distillation