CS
Cordelia Schmid
cs.CVcs.LGcs.AIcs.ROcs.CLstat.MLcs.SDAlgorithmsArtificial Intelligencecs.MM
On Valency
published · living versionsW_8w9zqdes·v1 · currentpublished
DiPLO: Self-distilled Diffusion Planning for Loco-manipulation
with Shafeef Omar, Sebastian Sanokowski, Elham Daneshmand, Dian Yu +2
1 version
W_6fnz9f6b·v1published
Preprints & journals
244 papers in the corpus · 2005–2026DexOAK: Object-Aware Kinematic Retargeting2610.26762v1 · Federica Spinola, Robert Katzschmann, Cordelia Schmid2026 · 0 citationsarXivon Valency
DiPLO: Self-distilled Diffusion Planning for Loco-manipulation2610.24847v1 · Shafeef Omar, Sebastian Sanokowski, Elham Daneshmand et al.2026 · 0 citationsarXivon Valency
Soft Teacher Forcing2610.17189v1 · Mohammad Fahes, Cordelia Schmid, Anurag Arnab2026 · 0 citationsarXiv
BrickBench: Evaluating Agentic Brick Design2610.12452v1 · Peter Kulits, Yiqing Xu, R. Kenny Jones et al.2026 · 0 citationsarXiv
Agents Are Systems, Not Models: Rethinking Agentic Evaluation2610.01618v1 · Luis Wiedmann, Leander Girrbach, Cordelia Schmid et al.2026 · 0 citationsarXiv
What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior2609.24576v1 · D'ebora Oliveira Makowski, Samiran Gode, Abhijeet Nayak et al.2026 · 0 citationsarXiv
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection2609.19143v1 · Sara Pieri, Evangelos Kazakos, Shizhe Chen et al.2026 · 0 citationsarXiv
Spatially Aware World Action Model via Geometric Latent Diffusion2609.02531v1 · Javier Alejandro Lopetegui Gonzalez, Paul Pacaud, Cordelia Schmid2026 · 0 citationsarXiv
LOCI: A Locator-Critic with Refinement Loop2608.30959v1 · Walid Bousselham, Mathilde Caron, Arsha Nagrani et al.2026 · 0 citationsarXiv
Pano3D: Unified 3D Reconstruction and Panoptic Segmentation2606.14307v2 · Victor Barberteguy, Ahmet Iscen, Mathilde Caron et al.2026 · 0 citationsEuropean Conference on Computer Vision (ECCV) 2026
PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction2605.21414v1 · Shizhe Chen, Paul Pacaud, Cordelia Schmid2026 · 0 citationsarXiv
Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding2605.15342v1 · Arsha Nagrani, Jasper Uijilings, Shyamal Buch et al.2026 · 0 citationsarXiv
BrickNet: Graph-Backed Generative Brick Assembly2604.22984v1 · Peter Kulits, Cordelia Schmid2026 · 0 citationsarXiv
HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching2604.10836v1 · Zerui Chen, Rolandos Alexandros Potamias, Shizhe Chen et al.2026 · 0 citationsarXiv
MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning2601.10649v2 · Darshan Singh, Arsha Nagrani, Kawshik Manikantan et al.2026 · 0 citationsarXiv
Guardian: Detecting Robotic Planning and Execution Errors with Vision-Language Models2512.01946v5 · Paul Pacaud, Ricardo Garcia, Shizhe Chen et al.2025 · 0 citationsarXiv
FOM-Nav: Frontier-Object Maps for Object Goal Navigation2512.01009v1 · Thomas Chabal, Shizhe Chen, Jean Ponce et al.2025 · 0 citationsarXiv
VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation2510.23497v3 · Walid Bousselham, Hilde Kuehne, Cordelia Schmid2025 · 0 citationsarXiv
CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects2510.14904v4 · Gabriel Fiastre, Antoine Yang, Cordelia Schmid2025 · 0 citationsarXiv
RECODE: Reasoning Through Code Generation for Visual Question Answering2510.13756v2 · Junhong Shen, Mu Cai, Bo Hu et al.2025 · 0 citationsarXiv
What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives2510.03075v4 · Karim Farid, Rajat Sahay, Yumna Ali Alnaggar et al.2025 · 0 citationsarXiv
MetricNet: Recovering Metric Scale in Generative Navigation Policies2509.13965v2 · Abhijeet Nayak, D'ebora Oliveira Makowski, Samiran Gode et al.2025 · 0 citationsarXiv
CAViAR: Critic-Augmented Video Agentic Reasoning2509.07680v1 · Sachit Menon, Ahmet Iscen, Arsha Nagrani et al.2025 · 0 citationsarXiv
VoCap: Video Object Captioning and Segmentation from Any Prompt2508.21809v1 · Jasper Uijlings, Xingyi Zhou, Xiuye Gu et al.2025 · 0 citationsarXiv
OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models2507.19262v1 · Monika Wysocza'nska, Shyamal Buch, Anurag Arnab et al.2025 · 0 citationsarXiv
Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames2507.02001v1 · Anurag Arnab, Ahmet Iscen, Mathilde Caron et al.2025 · 6 citationsarXiv
Gondola: Grounded Vision Language Planning for Robotic Manipulation2506.11261v2 · Shizhe Chen, Ricardo Garcia, Paul Pacaud et al.2025 · 0 citationsarXiv
ComposeAnything: Composite Object Priors for Text-to-Image Generation2505.24086v1 · Zeeshan Khan, Shizhe Chen, Cordelia Schmid2025 · 0 citationsarXiv
Continual Learning in Vision-Language Models via Aligned Model Merging2506.03189v1 · Ghada Sokar, Gintare Karolina Dziugaite, Anurag Arnab et al.2025 · 0 citationsarXiv
Feasibility with Language Models for Open-World Compositional Zero-Shot Learning2505.11181v1 · Jae Myung Kim, Stephan Alaniz, Cordelia Schmid et al.2025 · 0 citationsarXiv
LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance2505.11703v1 · Jae Myung Kim, Stephan Alaniz, Cordelia Schmid et al.2025 · 0 citationsarXiv
MINERVA: Evaluating Complex Video Reasoning2505.00681v1 · Arsha Nagrani, Sachit Menon, Ahmet Iscen et al.2025 · 7 citationsarXiv
Memory-Modular Classification: Learning to Generalize with Memory Replacement2504.06021v1 · Dahyun Kang, Ahmet Iscen, Eunchan Jo et al.2025 · 0 citationsarXiv
Learning to Answer Visual Questions From Web Videos.35533174 · Yang, Antoine, Miech, Antoine, Sivic, Josef et al.2025 · 26 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(5):3202-3218
InteractVLM: 3D Interaction Reasoning from 2D Foundational Models2504.05303v1 · Sai Kumar Dwivedi, Dimitrije Anti'c, Shashank Tripathi et al.2025 · 4 citationsarXiv
Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs2504.00072v1 · Lucas Ventura, Antoine Yang, Cordelia Schmid et al.2025 · 3 citationsarXiv
HORT: Monocular Hand-held Objects Reconstruction with Transformers2503.21313v2 · Zerui Chen, Rolandos Alexandros Potamias, Shizhe Chen et al.2025 · 4 citationsarXiv
Online 3D Scene Reconstruction Using Neural Object Priors2503.18897v1 · Thomas Chabal, Shizhe Chen, Jean Ponce et al.2025 · 2 citationsarXiv
Large-scale Pre-training for Grounded Video Caption Generation2503.10781v3 · Evangelos Kazakos, Cordelia Schmid, Josef Sivic2025 · 0 citationsarXiv
What Are You Doing? A Closer Look at Controllable Human Video Generation2503.04666v2 · Emanuele Bugliarello, Anurag Arnab, Roni Paiss et al.2025 · 1 citationarXiv
FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement2503.04919v1 · Ian Huang, Yanan Bao, Karen Truong et al.2025 · 7 citationsarXiv
Prediction-Powered Causal Inferences2502.06343v3 · Riccardo Cadei, Ilker Demirel, Piersilvio De Bartolomeis et al.2025 · 0 citationsarXiv
Neptune: The Long Orbit to Benchmarking Long Video Understanding2412.09582v2 · Arsha Nagrani, Mingda Zhang, Ramin Mehran et al.2024 · 0 citationsarXiv
Visual Lexicon: Rich Image Features in Language Space2412.06774v1 · XuDong Wang, Xingyi Zhou, Alireza Fathi et al.2024 · 1 citationarXiv
Language-Guided Image Tokenization for Generation2412.05796v2 · Kaiwen Zha, Lijun Yu, Alireza Fathi et al.2024 · 3 citationsarXiv
FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigation2411.09524v3 · Samiran Gode, Abhijeet Nayak, D'ebora N.P. Oliveira et al.2024 · 1 citationarXiv
Grounded Video Caption Generation2411.07584v1 · Evangelos Kazakos, Cordelia Schmid, Josef Sivic2024 · 1 citationarXiv
CoVR-2: Automatic Data Construction for Composed Video Retrieval.39302778 · Ventura, Lucas, Yang, Antoine, Schmid, Cordelia et al.2024 · 18 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):11409-11421
Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach2410.23676v1 · Mathilde Caron, Alireza Fathi, Cordelia Schmid et al.2024 · 1 citationarXiv
Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy2410.01345v2 · Ricardo Garcia, Shizhe Chen, Cordelia Schmid2024 · 14 citationsarXiv
Career total: 882 works. 244 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.