{"total":21,"rows":[{"id":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2410.14729","title":"Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2505.17425","title":"Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2503.09399","title":"ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2510.20627","title":"H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2512.17953","title":"Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2502.12413","title":"DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2510.00618","title":"Robust Context-Aware Object Recognition","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2601.00993","title":"WildIng: A Wildlife Image Invariant Representation Model for Geographical Domain Shift","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2607.03165","title":"Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.13783","title":"Doomed to Re-Annotate, Forever: The ImageNet Story","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2404.10141","title":"ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2405.14030","title":"Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2411.15933","title":"Bringing the Context Back into Object Recognition, Robustly","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2504.00429","title":"Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2511.05325","title":"Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2602.20068","title":"The Invisible Gorilla Effect in Out-of-distribution Detection","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.06095","title":"Metonymy in vision models undermines attention-based interpretability","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.13660","title":"The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.05424","title":"Invisible Shortcuts: Why Vision Encoders Know Your Camera","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.01090","title":"Modelpedia: A Catalog of Model Findings for the Meta-Science of AI","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}