4:53 [ICLR 2026] SiNGER: A Clearer Voice Distills Vision Transformers Further AIRLab 102 views - 2 weeks ago
19:24 How to build a large model from a small model. Learning to Grow Pretrained Models for Efficient T... AIRLab 175 views - 3 weeks ago
18:36 I roughly got it. Your nature. Toward Material-Agnostic System Identification from Videos AIRLab 75 views - 4 weeks ago
12:56 Since when did you think the camera is the center of the world? TAPIP3D: Tracking Any Point in Pe... AIRLab 664 views - 1 month ago
14:57 로봇없는 로봇팀 Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware AIRLab 135 views - 1 month ago
14:40 Today's topic is ViT Distillation. However, accompanied by Singular Nullspace. SiNGER: Clearer Vo... AIRLab 156 views - 1 month ago
18:50 The Moment When Internet Photos Become Robot Data Robot Learning from Any Images AIRLab 188 views - 1 month ago
25:44 I like the future predictions that videos make🤙🏻👍🏻 Cosmos Policy: Fine-Tuning Video Models for Vi... AIRLab 164 views - 1 month ago
26:08 One page won't do. Space is a 'flow' 🎥 Thinking in Space: How MLLMs See, Remember, and Recall Spaces AIRLab 149 views - 1 month ago
39:37 What does AI understand about the world? The Platonic Representation Hypothesis AIRLab 201 views - 1 month ago
19:03 Uh... who are you? Is it me? Why are your movements the same? 🤨 PhysTwin AIRLab 117 views - 1 month ago
15:19 Wow, I'll think about it before I go to bed since I've been doing a lot of fluid restoration toda... AIRLab 140 views - 1 month ago
17:00 We don't need your demo Human 🤖 GraspVLA: a Grasping Foundation Model on Billion-scale Synthetic ... AIRLab 214 views - 3 months ago
22:15 The alignment between the camera and the lidar is very tight.^^ General, Target-less, and Automat... AIRLab 125 views - 3 months ago
15:31 Can't predict the future? Then use a video generation model. VideoVLA: Video Generators Can Be Ge... AIRLab 180 views - 3 months ago
16:47 Robot version of Seeing is believing 👀⚖️⤴️⤵️🔃↩️↪️🔄 One Demo is Worth a Thousand Trajectories AIRLab 172 views - 3 months ago
13:23 Back, stronger than ever! RoboTwin 2.0: A Robotic Data Generator and Benchmark with Domain Random... AIRLab 129 views - 3 months ago
13:59 Cooking Report~ Cooking Report~ 3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS AIRLab 130 views - 3 months ago
15:43 VLM is like this... What's in the Image? A Deep-Dive into the Vision of Vision Language Models AIRLab 701 views - 4 months ago
12:48 날 따라 해봐요 이렇게~ TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos AIRLab 136 views - 4 months ago
22:02 Q: "이 픽셀 여기 맞나요?" VLM: "아니.. 더 뒤다..!!" DepthLM: Metric Depth From Vision Language Models AIRLab 199 views - 4 months ago
9:33 🏳️Send token 1, don't send 2, send 3🏴 MoR-ViT: Efficient Vision Transformer with Mixture-of-Recur... AIRLab 143 views - 4 months ago
15:45 🤖삐빅. 인간 시대의 끝이 도래했다..🤖 RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning AIRLab 164 views - 4 months ago
22:22 타겟이 없는곳에서 이정도의 정합성을? HiGS-Calib: Hierarchical 3DGS based Targetless LiDAR-Camera Calibration AIRLab 137 views - 4 months ago
24:05 시뮬레이터에서 폐관수련..? X-SIM: Cross-Embodiment Learning via Real-to-Sim-to-Real AIRLab 205 views - 5 months ago
25:17 OpenVLA 너 더 좋아질 수 있어! Fine-Tuning Vision-Language-Action Models:Optimizing Speed and Success AIRLab 611 views - 5 months ago
20:04 뎁스 카메라 여러개 쓰는데 간섭이 문제인가요? 제가 딱 해결해 드림. DRIM: Depth Restoration With Interference Mitigation AIRLab 131 views - 5 months ago
18:16 사진? 완벽히 이해했어!(이해 못했음) Is a Picture Worth a Thousand Words? Spatial Reasoning in VLM AIRLab 146 views - 5 months ago
18:48 카메라와 라이다를 Gaussian splatting과 함께 드셔보세요 Robust LiDAR-Camera Calibration With 2D Gaussian Splatting AIRLab 277 views - 5 months ago
24:53 보인다 보여~👀 Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models AIRLab 109 views - 5 months ago
23:15 The Giant DINO is Coming... DINOv3: Self-Supervised Learning for Vision at Unprecedented Scale AIRLab 662 views - 6 months ago
23:22 안보인다는건 핑계야! DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models AIRLab 171 views - 6 months ago
20:28 Diffusion? "느려..." CARP: Visuomotor Policy Learning via Coarse-to-Fine AutoRegressive Prediction AIRLab 142 views - 6 months ago
17:00 뭐라고? 로봇 데이터가 복사가 된다고?! 🖨️🖨️🖨️ Constraint-Preserving Data Generation for Visuomotor Policy Learning AIRLab 165 views - 6 months ago
28:05 텍스트로 로봇을 제어한다고? CLIP-RT: Learning Robotic Policies from Natural Language Supervision AIRLab 239 views - 7 months ago
23:11 I have a Robot~🦾 I have a twin~🪞 Uh! RoboTwin:Dual-Arm Robot Benchmark with Generative Digital Twins AIRLab 117 views - 7 months ago
21:33 Why Is Spatial Reasoning Hard for VLMs An Attention Mechanism Perspective on Focus Areas (ICML 2025) AIRLab 190 views - 7 months ago
20:16 자, 잘 봐. 이게 화살표라는거야↗️↙️↘️⬇️↙️. 이대로만 하면 돼💫 Robotic Visual Instruction (CVPR 2025) AIRLab 124 views - 7 months ago
15:48 그럴듯함을 넘어 물리 법칙까지 정확하게 PhysFlow:Multi-modal Foundation and Video Diffusion for 4D Physical Simulation AIRLab 158 views - 7 months ago
17:58 오일러!🤜 라그랑지안!🤛 크로스!!!🤝 ELPINN: Eulerian Lagrangian Physics-Informed Neural Network AIRLab 133 views - 7 months ago
22:51 네가 그렇게 잘해? 어디 이것도 잘하나 보자 🔎️🧐️ GENMANIP: LLM-driven Simulation for Instruction-Following Manipulation AIRLab 93 views - 7 months ago
16:59 VLM : 방금 왼쪽 오른쪽 구분하는 상상함🤣🤣 Perspective-Aware Reasoning in VLM via Mental Imagery Simulation AIRLab 184 views - 8 months ago
17:33 준비됐지, 팔?💪 물론이지, 다리.🦵 Visual Whole-Body Control for Legged Loco-Manipulation (CoRL 2024) AIRLab 147 views - 8 months ago
24:09 로봇 매니퓰레이션을 VLM으로 뚝딱 🦾 OmniManip: General Robotic Manipulation via Object Primitives as Constraints AIRLab 237 views - 8 months ago
16:53 뭘 해야 하는지는 알겠는데 어떻게 해야 할지 모르겠다고? 잘 봐, 알려줄게👀 UAD: Unsupervised Affordance Distillation (ICRA2025) AIRLab 142 views - 8 months ago
21:47 물리 법칙 무시하는 AI는 LLM이 처리했으니 안심하라고👍PhyT2V: LLM-Guided Physics-Based Video Generation (CVPR 2025) AIRLab 158 views - 8 months ago
15:38 Normalization에 대해서 생각해본 적 있어? 🤔🤔 Transformers without Normalization (CVPR 2025) AIRLab 236 views - 9 months ago
17:25 하나로 모든 걸 할 수 있는 최강자 등장💪 (두둥탁) . VGGT:Visual Geometry Grounded Transformer (CVPR 2025) AIRLab 785 views - 9 months ago
18:44 이젠 로봇 관절마저 렌더링 해버림 ㄷㄷ 🩻🩻 Differentiable Robot Rendering (CoRL 2024 Oral) AIRLab 451 views - 9 months ago
21:28 상상하라, 그러면 이해할 것이다 V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction & Planning AIRLab 659 views - 9 months ago
19:48 Absolute Zero: Reinforced Self-play Reasoning with Zero Data (arXiv 2025) AIRLab 316 views - 10 months ago
31:33 이제 densification이 필요가 없어⚡Eliminating Densification for Efficient Convergence of 3DGS (arXiv 2025) AIRLab 161 views - 10 months ago
19:35 파운데이션 모델이 다 해주는 참 좋은 세상🤖💪 Autonomous Improvement of Instruction Following Skills via FMs (CoRL 2024) AIRLab 161 views - 10 months ago
17:53 Attention은 됐고 우리는 FFN 대통합한다💥💥FFN Fusion Rethinking Sequential Computation in LLMs(arXiv 2025) AIRLab 256 views - 10 months ago
17:52 너네끼리 뭉쳐버릴려고?😠 Towards a Density Preserving Objective Function for Learning on Point Sets(ECCV 2024) AIRLab 111 views - 10 months ago
26:57 이게 그냥 섞는게 아니야‼️Sim&Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation(RSS 2025) AIRLab 234 views - 10 months ago
17:58 지름길로 쉽게 쉽게 가보자고 😉😉One Step Diffusion via Shortcut Model(ICLR 2025) AIRLab 475 views - 10 months ago
26:02 눈 두 개 있는 파운데이션 모델 등장. (두둥) 👁️👁️FoundationStereo: Zero-Shot Stereo Matching(CVPR 2025) AIRLab 383 views - 11 months ago
21:01 싱글샷→풀가구 실화냐🪑SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects(ICLR 2025) AIRLab 409 views - 11 months ago