{"total":67,"rows":[{"id":"2205.12393","title":"Fine-tuned Language Models are Continual Learners","created":"2022-05-24","cited_by_count":156,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"area":"mllm"},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48,"area":"mllm"},{"id":"2211.10681","title":"Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning","created":"2022-11-19","cited_by_count":37,"area":null},{"id":"2309.05173","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","created":"2023-09-11","cited_by_count":35,"area":null},{"id":"2306.01669","title":"Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning","created":"2023-06-02","cited_by_count":30,"area":"mllm"},{"id":"2303.15111","title":"Learning Attention as Disentangler for Compositional Zero-shot Learning","created":"2023-03-27","cited_by_count":29,"area":null},{"id":"2305.17940","title":"Learning Conditional Attributes for Compositional Zero-Shot Learning","created":"2023-05-29","cited_by_count":28,"area":null},{"id":"2303.15230","title":"Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning","created":"2023-03-27","cited_by_count":27,"area":"mllm"},{"id":"2309.13847","title":"Tuning Multi-mode Token-level Prompt Alignment across Modalities","created":"2023-09-25","cited_by_count":26,"area":"mllm"},{"id":"2305.14428","title":"Prompting Language-Informed Distribution for Compositional Zero-Shot Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2303.01580","title":"Mixture of Soft Prompts for Controllable Data Generation","created":"2023-03-02","cited_by_count":23,"area":null},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2402.17251","title":"Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning","created":"2024-02-27","cited_by_count":20,"area":null},{"id":"2305.01239","title":"DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning","created":"2023-05-02","cited_by_count":17,"area":null},{"id":"2311.05729","title":"GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning","created":"2023-11-09","cited_by_count":16,"area":"mllm"},{"id":"2502.15969","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","created":"2025-02-21","cited_by_count":16,"area":"lr"},{"id":"2310.12690","title":"Neurosymbolic Grounding for Compositional World Models","created":"2023-10-19","cited_by_count":14,"area":"wm"},{"id":"2502.06501","title":"Learning Clustering-based Prototypes for Compositional Zero-shot Learning","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2311.07593","title":"Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification","created":"2023-11-10","cited_by_count":13,"area":"mllm"},{"id":"2211.05077","title":"Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learning","created":"2022-11-09","cited_by_count":12,"area":"mllm"},{"id":"2311.14749","title":"Compositional Zero-shot Learning via Progressive Language-based Observations","created":"2023-11-23","cited_by_count":12,"area":null},{"id":"2407.06113","title":"C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition","created":"2024-07-08","cited_by_count":9,"area":null},{"id":"2410.00398","title":"CusConcept: Customized Visual Concept Decomposition with Diffusion Models","created":"2024-10-01","cited_by_count":9,"area":"diffusion"},{"id":"2305.16681","title":"CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2306.00310","title":"Prompt Algebra for Task Composition","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2408.08703","title":"TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning","created":"2024-08-16","cited_by_count":6,"area":null},{"id":"2402.02851","title":"Enhancing Compositional Generalization via Compositional Feature Alignment","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2503.23030","title":"Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning","created":"2025-03-29","cited_by_count":4,"area":null},{"id":"2307.00097","title":"Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation","created":"2023-06-30","cited_by_count":3,"area":null},{"id":"2311.14747","title":"HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts","created":"2023-11-23","cited_by_count":3,"area":"moe"},{"id":"2509.20807","title":"Federated Domain Generalization with Domain-specific Soft Prompts Generation","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2603.16641","title":"FlowComposer: Composable Flows for Compositional Zero-Shot Learning","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2501.13859","title":"Learning Visual Proxy for Compositional Zero-Shot Learning","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2502.20292","title":"Visual Adaptive Prompting for Compositional Zero-Shot Learning","created":"2025-02-27","cited_by_count":2,"area":"mllm"},{"id":"2507.17377","title":"A Conditional Probability Framework for Compositional Zero-shot Learning","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2303.03103","title":"Towards Zero-Shot Functional Compositionality of Language Models","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2403.18525","title":"Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP","created":"2024-03-27","cited_by_count":1,"area":"mllm"},{"id":"2406.12757","title":"MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2411.12584","title":"Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2412.04083","title":"Unified Framework for Open-World Compositional Zero-shot Learning","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2501.14308","title":"Learning Primitive Relations for Compositional Zero-Shot Learning","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2502.12095","title":"Descriminative-Generative Custom Tokens for Vision-Language Models","created":"2025-02-17","cited_by_count":1,"area":"mllm"},{"id":"2505.10289","title":"MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2509.05635","title":"Few-Shot Query Intent Detection via Relation-Aware Prompt Learning","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2511.16378","title":"CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.20029","title":"$\\text{H}^2$em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2610.00064","title":"Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2303.10093","title":"Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection","created":"2023-03-17","cited_by_count":0,"area":"mllm"},{"id":"2407.10723","title":"Anticipating Future Object Compositions without Forgetting","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2501.07114","title":"Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2501.17171","title":"Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2505.11181","title":"Feasibility with Language Models for Open-World Compositional Zero-Shot Learning","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.20986","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","created":"2025-06-26","cited_by_count":0,"area":"moe"},{"id":"2508.01932","title":"Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2509.03873","title":"SalientFusion: Context-Aware Compositional Zero-Shot Food Recognition","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2512.09172","title":"Prompt-Based Continual Compositional Zero-Shot Learning","created":"2025-12-09","cited_by_count":0,"area":"mllm"},{"id":"2601.09025","title":"Universal Latent Homeomorphic Manifolds: A Framework for Cross-Domain Representation Unification","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.16211","title":"Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.23906","title":"Half-Truths Break Similarity-Based Retrieval","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.03815","title":"Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2607.05911","title":"Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2608.19871","title":"DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations","created":"2026-08-20","cited_by_count":0,"area":"mllm"},{"id":"2610.17866","title":"MicroCLIP: Connecting Text and Microscopy Images via Contrastive Language--Image Pretraining","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}