{"total":34,"rows":[{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513,"area":null},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"area":null},{"id":"2402.16843","title":"Multi-LoRA Composition for Image Generation","created":"2024-02-26","cited_by_count":80,"area":null},{"id":"2408.14339","title":"ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty","created":"2024-08-26","cited_by_count":61,"area":null},{"id":"2211.09786","title":"SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields","created":"2022-11-17","cited_by_count":51,"area":null},{"id":"2406.08656","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","created":"2024-06-12","cited_by_count":43,"area":null},{"id":"2309.00966","title":"Compositional Diffusion-Based Continuous Constraint Solvers","created":"2023-09-02","cited_by_count":40,"area":null},{"id":"2306.05357","title":"Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models","created":"2023-06-08","cited_by_count":36,"area":null},{"id":"2304.14391","title":"Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement","created":"2023-04-27","cited_by_count":30,"area":null},{"id":"2210.11522","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","created":"2022-10-20","cited_by_count":28,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2409.19808","title":"Can Models Learn Skill Composition from Examples?","created":"2024-09-29","cited_by_count":17,"area":null},{"id":"2410.06303","title":"Compositional Risk Minimization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2509.23468","title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","created":"2025-09-27","cited_by_count":13,"area":null},{"id":"2206.14538","title":"vMFNet: Compositionality Meets Domain-generalised Segmentation","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2207.07568","title":"Reasoning about Actions over Visual and Linguistic Modalities: A Survey","created":"2022-07-15","cited_by_count":10,"area":null},{"id":"2502.05606","title":"FreeBlend: Advancing Concept Blending with Staged Feedback-Driven Interpolation Diffusion","created":"2025-02-08","cited_by_count":8,"area":null},{"id":"2507.23784","title":"SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2310.14466","title":"Inferring Relational Potentials in Interacting Systems","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2401.08472","title":"Instilling Multi-round Thinking to Text-guided Image Generation","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2401.11631","title":"Text-to-Image Cross-Modal Generation: A Systematic Review","created":"2024-01-21","cited_by_count":5,"area":null},{"id":"2204.02035","title":"DT2I: Dense Text-to-Image Generation from Region Descriptions","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2404.01296","title":"MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2510.01944","title":"Uniform-in-time convergence bounds for Persistent Contrastive Divergence algorithms","created":"2025-10-02","cited_by_count":4,"area":null},{"id":"2309.03483","title":"DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2505.21780","title":"Compositional Scene Understanding through Inverse Generative Modeling","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2306.07783","title":"Compositionally Equivariant Representation Learning","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2509.23605","title":"VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2310.06562","title":"Compositional Representation Learning for Brain Tumour Segmentation","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2503.04687","title":"Compositional World Knowledge leads to High Utility Synthetic data","created":"2025-03-06","cited_by_count":0,"area":null}],"next_cursor":null}