Stephan Alaniz

38 papers A* 8Journal 25Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Explaining CLIP Zero-shot Predictions Through Concepts. CoRR Onat Özdemir, Anders Christensen, Stephan Alaniz, Zeynep Akata, Emre Akbas
2026	J	`jnl`	FINER: MLLMs Hallucinate under Fine-grained Negative Queries. CoRR Rui Xiao, Sanghwan Kim, Yongqin Xian, Zeynep Akata, Stephan Alaniz
2025	J	`jnl`	A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models. CoRR Leander Girrbach, Stephan Alaniz, Genevieve Smith, Zeynep Akata
2025	A*	`conf`	COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training. CVPR Sanghwan Kim, Rui Xiao, Mariana-Iuliana Georgescu, Stephan Alaniz, Zeynep Akata
2025	J	`jnl`	Concept-Guided Interpretability via Neural Chunking. CoRR Shuchen Wu, Stephan Alaniz, Shyamgopal Karthik, Peter S. Dayan, Eric Schulz, Zeynep Akata
2025	J	`jnl`	Discovering Chunks in Neural Embeddings for Interpretability. CoRR Shuchen Wu, Stephan Alaniz, Eric Schulz, Zeynep Akata
2025	A*	`conf`	FLAIR: VLM with Fine-grained Language-informed Image Representations. CVPR Rui Xiao, Sanghwan Kim, Mariana-Iuliana Georgescu, Zeynep Akata, Stephan Alaniz
2025	J	`jnl`	Feasibility with Language Models for Open-World Compositional Zero-Shot Learning. CoRR Jae Myung Kim, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
2025	J	`jnl`	LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance. CoRR Jae Myung Kim, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
2025	J	`jnl`	Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models. CoRR Leander Girrbach, Stephan Alaniz, Genevieve Smith, Trevor Darrell, Zeynep Akata
2025	A*	`conf`	Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs). ICLR Leander Girrbach, Stephan Alaniz, Yiran Huang, Trevor Darrell, Zeynep Akata
2025	J	`jnl`	SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions. CoRR Jessica Bader, Leander Girrbach, Stephan Alaniz, Zeynep Akata
2025	J	`jnl`	Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs. CoRR Sanghwan Kim, Rui Xiao, Stephan Alaniz, Yongqin Xian, Zeynep Akata
2024	J	`jnl`	COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training. CoRR Sanghwan Kim, Rui Xiao, Mariana-Iuliana Georgescu, Stephan Alaniz, Zeynep Akata
2024	—	`conf`	DataDream: Few-Shot Guided Dataset Generation. ECCV (71) Jae Myung Kim, Jessica Bader, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
2024	J	`jnl`	DataDream: Few-shot Guided Dataset Generation. CoRR Jae Myung Kim, Jessica Bader, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
2024	J	`jnl`	FLAIR: VLM with Fine-grained Language-informed Image Representations. CoRR Rui Xiao, Sanghwan Kim, Mariana-Iuliana Georgescu, Zeynep Akata, Stephan Alaniz
2024	J	`jnl`	Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs). CoRR Leander Girrbach, Yiran Huang, Stephan Alaniz, Trevor Darrell, Zeynep Akata
2023	—	`conf`	DeViL: Decoding Vision features into Language. DAGM Meghal Dani, Isabel Rio-Torto, Stephan Alaniz, Zeynep Akata
2023	J	`jnl`	DeViL: Decoding Vision features into Language. CoRR Meghal Dani, Isabel Rio-Torto, Stephan Alaniz, Zeynep Akata
2023	J	`jnl`	How should the advent of large language models affect the practice of science? CoRR Marcel Binz, Stephan Alaniz, Adina Roskies, Balazs Aczel, Carl T. Bergstrom, Colin Allen, Daniel Schad, Dirk U. Wulff, Jevin D. West, Qiong Zhang, Richard M. Shiffrin, Samuel J. Gershman, Ven Popov, Emily M. Bender, Marco Marelli, Matthew M. Botvinick, Zeynep Akata, Eric Schulz
2023	A*	`conf`	In-Context Impersonation Reveals Large Language Models' Strengths and Biases. NeurIPS Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, Zeynep Akata
2023	J	`jnl`	In-Context Impersonation Reveals Large Language Models' Strengths and Biases. CoRR Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, Zeynep Akata
2023	A*	`conf`	Iterative Superquadric Recomposition of 3D Objects from Multiple Views. ICCV Stephan Alaniz, Massimiliano Mancini, Zeynep Akata
2023	J	`jnl`	Iterative Superquadric Recomposition of 3D Objects from Multiple Views. CoRR Stephan Alaniz, Massimiliano Mancini, Zeynep Akata
2023	A*	`conf`	PDiscoNet: Semantically consistent part discovery for fine-grained recognition. ICCV Robert van der Klis, Stephan Alaniz, Massimiliano Mancini, Cássio Fraga Dantas, Dino Ienco, Zeynep Akata, Diego Marcos
2023	J	`jnl`	PDiscoNet: Semantically consistent part discovery for fine-grained recognition. CoRR Robert van der Klis, Stephan Alaniz, Massimiliano Mancini, Cássio F. Dantas, Dino Ienco, Zeynep Akata, Diego Marcos
2022	—	`conf`	Abstracting Sketches Through Simple Primitives. ECCV (29) Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos, Zeynep Akata
2022	J	`jnl`	Abstracting Sketches through Simple Primitives. CoRR Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos, Zeynep Akata
2022	—	`conf`	Compositional Mixture Representations for Vision and Text. CVPR Workshops Stephan Alaniz, Marco Federici, Zeynep Akata
2022	J	`jnl`	Compositional Mixture Representations for Vision and Text. CoRR Stephan Alaniz, Marco Federici, Zeynep Akata
2022	—	`—`	Explainability in Deep Learning by Means of Communication. Stephan Alaniz
2022	J	`jnl`	Semantic Image Synthesis with Semantically Coupled VQ-Model. CoRR Stephan Alaniz, Thomas Hummel, Zeynep Akata
2021	A*	`conf`	Learning Decision Trees Recurrently Through Communication. CVPR Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata
2019	A*	`conf`	Modeling Conceptual Understanding in Image Reference Games. NeurIPS Rodolfo Corona, Stephan Alaniz, Zeynep Akata
2019	J	`jnl`	Modeling Conceptual Understanding in Image Reference Games. CoRR Rodolfo Corona, Stephan Alaniz, Zeynep Akata
2019	J	`jnl`	XOC: Explainable Observer-Classifier for Explainable Binary Decisions. CoRR Stephan Alaniz, Zeynep Akata
2018	J	`jnl`	Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft. CoRR Stephan Alaniz