4 citations · 14 across the 38 of their papers we have counts for
46 papers
RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models
Ritika Allada, Pinar Yanardag
Recent advances in text-to-image (T2I) models have revolutionized the field of image generation and editing. However, identifying semantics that a T2I model can successfully edit i…
From Zero to Hero: Training-Free Custom Concept Spawning in World Models
Kiymet Akdemir, Pinar Yanardag
Autoregressive world models have emerged as a powerful paradigm for interactive video generation, allowing users to navigate dynamically generated environments through actions. The…
DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
Hidir Yesiltepe, Koutilya PNVR, Gaurav Pathak +4
Recent progress in video diffusion models has enabled remarkable generative fidelity, yet leveraging these priors for restoration remains limited by the strong coupling between con…
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral +4
Long-rollout causal video diffusion has converged on a fixed-size sliding-window KV cache, with recent progress innovating within this layout by changing which tokens occupy the wi…
AdaState: Self-Evolving Anchors for Streaming Video Generation
Yusuf Dalva, Pinar Yanardag
Autoregressive video diffusion models generate streaming video by producing frames sequentially, conditioning each chunk on previously generated content. These models are structura…
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
Tuna Han Salih Meral, Kaan Oktay, Hidir Yesiltepe +2
Latent flow matching for image generation usually transports Gaussian noise to variational autoencoder latents along linear paths. Both endpoints, however, concentrate in thin sphe…
Canvas-to-Image: Compositional Image Generation with Multimodal Controls
Yusuf Dalva, Guocheng Gordon Qian, Maya Goldenberg +5
While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when us…
Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization
Tahira Kazimi, Connor Dunlop, Pinar Yanardag
While recent text-to-video (T2V) diffusion models have achieved impressive quality and prompt alignment, they often produce low-diversity outputs when sampling multiple videos from…
Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization
Connor Dunlop, Matthew Zheng, Kavana Venkatesh +1
Text-to-image (T2I) diffusion models have made remarkable strides in generating and editing high-fidelity images from text. Yet, these models remain fundamentally generic, failing…
Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
Hidir Yesiltepe, Tuna Han Salih Meral, Adil Kaan Akan +2
Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding…
LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Models
Mert Sonmezer, Matthew Zheng, Pinar Yanardag
Low-rank Adaptation (LoRA) models have revolutionized the personalization of pre-trained diffusion models by enabling fine-tuning through low-rank, factorized weight matrices speci…
Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models
Kiymet Akdemir, Jing Shi, Kushal Kafle +2
Text-to-image diffusion models have demonstrated significant capabilities to generate diverse and detailed visuals in various domains, and story visualization is emerging as a part…
Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models
Kiymet Akdemir, Tahira Kazimi, Pinar Yanardag
Story visualization has become a popular task where visual scenes are generated to depict a narrative across multiple panels. A central challenge in this setting is maintaining vis…
Dynamic View Synthesis as an Inverse Problem
Hidir Yesiltepe, Pinar Yanardag
In this work, we address dynamic view synthesis from monocular videos as an inverse problem in a training-free setting. By redesigning the noise initialization phase of a pre-train…
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers
Yusuf Dalva, Hidir Yesiltepe, Pinar Yanardag
We introduce LoRAShop, the first framework for multi-concept image editing with LoRA models. LoRAShop builds on a key observation about the feature interaction patterns inside Flux…
CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation
Kavana Venkatesh, Connor Dunlop, Pinar Yanardag
Creativity in AI imagery remains a fundamental challenge, requiring not only the generation of visually compelling content but also the capacity to add novel, expressive, and artis…
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Alec Helbling, Tuna Han Salih Meral, Ben Hoover +2
Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel metho…
Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models
Tahira Kazimi, Ritika Allada, Pinar Yanardag
Classifiers are important components in many computer vision tasks, serving as the foundational backbone of a wide variety of models employed across diverse applications. However,…
FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers
Yusuf Dalva, Kavana Venkatesh, Pinar Yanardag
Rectified flow models have emerged as a dominant approach in image generation, showcasing impressive capabilities in high-quality image synthesis. However, despite their effectiven…
MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance
Hidir Yesiltepe, Tuna Han Salih Meral, Connor Dunlop +1
In this work, we propose the first motion transfer approach in diffusion transformer through Mixture of Score Guidance (MSG), a theoretically-grounded framework for motion transfer…
MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models
Tuna Han Salih Meral, Hidir Yesiltepe, Connor Dunlop +1
Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these…
LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors
Yusuf Dalva, Yijun Li, Qing Liu +4
Large-scale diffusion models have achieved remarkable success in generating high-quality images from textual descriptions, gaining popularity across various applications. However,…
PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
Muntasir Wahed, Kiet A. Nguyen, Adheesh Sunil Juvekar +6
Despite significant advancements in Large Vision-Language Models (LVLMs)' capabilities, existing pixel-grounding models operate in single-image settings, limiting their ability to…
LoRACLR: Contrastive Adaptation for Customization of Diffusion Models
Enis Simsar, Thomas Hofmann, Federico Tombari +1
Recent advances in text-to-image customization have enabled high-fidelity, context-rich generation of personalized images, allowing specific concepts to appear in a variety of scen…