{"total":72,"rows":[{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624,"area":"diffusion"},{"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":"2302.11552","title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","created":"2023-02-22","cited_by_count":220,"area":"diffusion"},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"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":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108,"area":"mllm"},{"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":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95,"area":"mllm"},{"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":"2302.03693","title":"Concept Algebra for (Score-Based) Text-Controlled Generative Models","created":"2023-02-07","cited_by_count":59,"area":"diffusion"},{"id":"2211.09786","title":"SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields","created":"2022-11-17","cited_by_count":51,"area":null},{"id":"2311.17919","title":"Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models","created":"2023-11-29","cited_by_count":46,"area":"diffusion"},{"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":"2403.17064","title":"Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions","created":"2024-03-25","cited_by_count":41,"area":"diffusion"},{"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":"2202.04178","title":"VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming","created":"2022-02-07","cited_by_count":31,"area":"lr"},{"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":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","cited_by_count":30,"area":"mllm"},{"id":"2306.01872","title":"Probabilistic Adaptation of Text-to-Video Models","created":"2023-06-02","cited_by_count":29,"area":"wm"},{"id":"2210.11522","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","created":"2022-10-20","cited_by_count":28,"area":null},{"id":"2209.06970","title":"Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models","created":"2022-09-14","cited_by_count":27,"area":"diffusion"},{"id":"2309.16115","title":"Compositional Sculpting of Iterative Generative Processes","created":"2023-09-28","cited_by_count":27,"area":"diffusion"},{"id":"2209.10326","title":"Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering","created":"2022-09-21","cited_by_count":25,"area":"lr"},{"id":"2403.09193","title":"Can We Talk Models Into Seeing the World Differently?","created":"2024-03-14","cited_by_count":23,"area":"mllm"},{"id":"2404.11615","title":"Factorized Diffusion: Perceptual Illusions by Noise Decomposition","created":"2024-04-17","cited_by_count":23,"area":"diffusion"},{"id":"2401.13171","title":"Compositional Generative Inverse Design","created":"2024-01-24","cited_by_count":20,"area":"diffusion"},{"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":"2309.04109","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","created":"2023-09-08","cited_by_count":16,"area":"diffusion"},{"id":"2502.04549","title":"Mechanisms of Projective Composition of Diffusion Models","created":"2025-02-06","cited_by_count":14,"area":"diffusion"},{"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":"2406.19298","title":"Compositional Image Decomposition with Diffusion Models","created":"2024-06-27","cited_by_count":12,"area":"diffusion"},{"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":"2503.01145","title":"CoInD: Enabling Logical Compositions in Diffusion Models","created":"2025-03-03","cited_by_count":8,"area":"diffusion"},{"id":"2503.12466","title":"Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition","created":"2025-03-16","cited_by_count":7,"area":"diffusion"},{"id":"2210.05147","title":"Markup-to-Image Diffusion Models with Scheduled Sampling","created":"2022-10-11","cited_by_count":6,"area":"diffusion"},{"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":"2405.19201","title":"Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations","created":"2024-05-29","cited_by_count":5,"area":"diffusion"},{"id":"2204.02035","title":"DT2I: Dense Text-to-Image Generation from Region Descriptions","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2402.03305","title":"Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?","created":"2024-02-05","cited_by_count":4,"area":"diffusion"},{"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":"2309.06680","title":"STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning","created":"2023-09-13","cited_by_count":3,"area":"lr"},{"id":"2410.17479","title":"Composing Diffusion Policies for Few-shot Learning of Movement Trajectories","created":"2024-10-22","cited_by_count":3,"area":"diffusion"},{"id":"2505.21780","title":"Compositional Scene Understanding through Inverse Generative Modeling","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2508.11624","title":"LoRAtorio: An intrinsic approach to LoRA Skill Composition","created":"2025-08-15","cited_by_count":3,"area":"diffusion"},{"id":"2601.22057","title":"Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion Models","created":"2026-01-29","cited_by_count":3,"area":"diffusion"},{"id":"2306.07783","title":"Compositionally Equivariant Representation Learning","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2310.17451","title":"Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings","created":"2023-10-26","cited_by_count":2,"area":"lr"},{"id":"2504.06432","title":"D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition","created":"2025-04-08","cited_by_count":2,"area":"diffusion"},{"id":"2310.09383","title":"Integrating Symbolic Reasoning into Neural Generative Models for Design Generation","created":"2023-10-13","cited_by_count":1,"area":"lr"},{"id":"2509.23605","title":"VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2602.05549","title":"Logical Guidance for the Exact Composition of Diffusion Models","created":"2026-02-05","cited_by_count":1,"area":"diffusion"},{"id":"2603.27958","title":"CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2211.03756","title":"Changes from Classical Statistics to Modern Statistics and Data Science","created":"2022-10-30","cited_by_count":0,"area":"diffusion"},{"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},{"id":"2505.18083","title":"What Do You Need for Compositional Generalization in Diffusion Planning?","created":"2025-05-23","cited_by_count":0,"area":"offlinerl"},{"id":"2512.22324","title":"DeMoGen: Towards Decompositional Human Motion Generation with Energy-Based Diffusion Models","created":"2025-12-26","cited_by_count":0,"area":"diffusion"},{"id":"2602.20839","title":"Training-Free Multi-Concept Image Editing","created":"2026-02-24","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}