Home

• DeiT: Training data-efficient image transformers & distillation through attention — vision, transformers, distillation — 2026-05-31
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows — vision, transformers — 2026-05-31
• π_0: A Vision-Language-Action Flow Model for General Robot Control — vision, robotics — 2026-06-01
• Segment Anything — vision, instance-segmentation — 2026-06-02
• DETRs Beat YOLOs on Real-time Object Detection — vision, object-detection, transformers — 2026-06-03
• FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects — vision, 6dof-pose-estimation — 2026-06-04
• NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis — vision, neural-rendering — 2026-06-05
• Masked Autoencoders Are Scalable Vision Learners — masked-image-modeling, auto-encoders, self-supervised-learning, transformers, representation-learning — 2026-06-06
• On the Spectral Bias of Neural Networks — optimization, robustness, representation-learning, data-representation — 2026-06-08
• RF-DETR: Neural Architecture Search for Real-Time Detection Transformers — object-detection, instance-segmentation, neural-architecture-search, transformers — 2026-06-09
• Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision — 3d-reconstruction, implicit-representations, neural-rendering, multi-view-stereo, depth-estimation — 2026-06-10
• Deep Marching Cubes: Learning Explicit Surface Representations — 3d-reconstruction, data-representation, optimization — 2026-06-11
• Occupancy Networks: Learning 3D Reconstruction in Function Space — 3d-reconstruction, implicit-representations, data-representation — 2026-06-12
• Fast Inference from Transformers via Speculative Decoding — speculative-decoding, transformers, language — 2026-06-13
• Learning Transferable Visual Models From Natural Language Supervision — vlm, contrastive-learning, zero-shot, representation-learning, open-vocabulary — 2026-06-14
• YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection — object-detection, instance-segmentation, keypoint-detection, optimization, robotics — 2026-06-15
• Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics — 4d-reconstruction, implicit-representations, flow-maps, motion-estimation, temporal-coherence — 2026-06-16
• SketchVLM: Vision language models can annotate images to explain thoughts and guide users — vlm, visual-question-answering, grounding — 2026-06-17
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control — robotics, vlm, transformers, language, grounding — 2026-06-18
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels — jepa, world-simulation, representation-learning, self-supervised-learning, robotics — 2026-06-19
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning — transformers, optimization — 2026-06-22
• FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision — transformers, optimization, language — 2026-06-23
• Emerging Properties in Self-Supervised Vision Transformers — self-supervised-learning, transformers, representation-learning, distillation — 2026-06-24
• Perception Encoder: The best visual embeddings are not at the output of the network — contrastive-learning, representation-learning, vlm, distillation, object-detection — 2026-06-25
• Neural Ordinary Differential Equations — optimization, normalizing-flows, auto-encoders, representation-learning — 2026-06-26
• SAM 2: Segment Anything in Images and Videos — instance-segmentation, object-tracking, visual-tracking, transformers, temporal-coherence — 2026-06-30
• SAM 3: Segment Anything with Concepts — open-vocabulary, instance-segmentation, object-detection, object-tracking, semantic-segmentation — 2026-07-01
• Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision — 3d-reconstruction, implicit-representations, neural-rendering, multi-view-stereo — 2026-07-02