Scaling Transformer Energy-based Models For High Quality Image Synthesis
Paper • 2610.31889 • Published • 1
🦆 locked-in brother.
Edgar Moreau
Ethgar
AI & ML interests
Autonomous UAVs, Embodied AI, World models, application over research.
Recent Activity
published a Space 2 days ago
MacroSwan/clear-the-playroom updated a Space 2 days ago
MacroSwan/clear-the-playroom liked a Space 2 days ago
huggingface/paperswithcodeOrganizations
upvoted 20
papers 13 days ago
SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model
Paper • 2610.28480 • Published • 5
Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
Paper • 2610.12470 • Published • 3
RoboJEPA: Scaling Robotic Latent World Models
Paper • 2610.10515 • Published • 7
Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object
Paper • 2610.07355 • Published • 1
H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
Paper • 2610.06805 • Published • 3
Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation
Paper • 2609.38172 • Published • 2
λ-JEPA Spectral Anti-Collapse Regularization for Self-Supervised Learning
Paper • 2609.35288 • Published • 1
Pro-Bench: Prompt-Robust Open-Vocabulary Visual Grounding Across Real-World Heterogeneous Environments
Paper • 2609.27076 • Published • 1
The JEPA Predictor: A Transferable Operator for Occluded Feature Completion
Paper • 2607.16274 • Published • 1
SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
Paper • 2606.23444 • Published • 1
Asymmetric physics enables efficient learning in quadrupedal robot swarms
Paper • 2606.23153 • Published • 1
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 235
MolmoPoint: Better Pointing for VLMs with Grounding Tokens
Paper • 2603.28069 • Published • 9
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Paper • 2603.14482 • Published • 40
Detect Anything in Real Time: From Single-Prompt Segmentation to Multi-Class Detection
Paper • 2603.11441 • Published • 2
EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding
Paper • 2603.04254 • Published • 2
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
Paper • 2602.10098 • Published • 25
ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction
Paper • 2601.06997 • Published • 1
EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3
Paper • 2511.15833 • Published • 4