1 citations · 3 across the 15 of their papers we have counts for
16 papers
Can Circuit Alignment Predict OOD Generalization?
Ayan Banerjee, Abhra Chaudhuri, Josep Llados +2
Can out-of-distribution (OOD) generalization be predicted from a trained model's weights alone, without any target-domain data? Existing representational similarity metrics (CKA, S…
3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
Deyin Liu, Jicheng Xu, Lin Yuanbo Wu +4
Human image animation, which aims to generate a video of a reference subject following a provided action sequence, has received increasing research interest. With the development o…
Beyond Consistency: Preserving Temporal Structure in Zero-Shot Video Editing
Deyin Liu, Yisheng Ding, Zhe Jin +3
Existing zero-shot video editing methods rely on pre-trained diffusion models, successfully achieving spatial control and basic temporal consistency but fundamentally fail to prese…
ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation
Anindya Mondal, Sauradip Nag, Anjan Dutta
We present ABACUS, a unified vision-language model that jointly addresses object counting, crowd counting, referring-expression counting, and count-faithful image generation within…
RAIGen: Rare Attribute Identification in Text-to-Image Generative Models
Silpa Vadakkeeveetil Sreelatha, Dan Wang, Serge Belongie +2
Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses thi…
RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation
Silpa Vadakkeeveetil Sreelatha, Sauradip Nag, Muhammad Awais +2
The rapid advancement of diffusion models has enabled high-fidelity and semantically rich text-to-image generation; however, ensuring fairness and safety remains an open challenge.…
TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
Ayan Banerjee, Josep Llados, Umapada Pal +1
Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency,…
CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance
Anindya Mondal, Ayan Banerjee, Sauradip Nag +3
Diffusion models excel at photorealistic synthesis but struggle with object count fidelity, especially in high-density settings. We introduce COUNTLOOP, a training-free framework t…
A Closer Look at Multimodal Representation Collapse
Abhra Chaudhuri, Anjan Dutta, Tu Bui +1
We aim to develop a fundamental understanding of modality collapse, a recently observed empirical phenomenon wherein models trained for multimodal fusion tend to rely only on a sub…
CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion
Ayan Banerjee, Nityanand Mathur, Josep Llados +2
Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research h…
DeNetDM: Debiasing by Network Depth Modulation
Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, Abhra Chaudhuri +1
Neural networks trained on biased datasets tend to inadvertently learn spurious correlations, hindering generalization. We formally prove that (1) samples that exhibit spurious cor…
OmniCount: Multi-label Object Counting with Semantic-Geometric Priors
Anindya Mondal, Sauradip Nag, Xiatian Zhu +1
Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adapta…
Learning Conditional Invariances through Non-Commutativity
Abhra Chaudhuri, Serban Georgescu, Anjan Dutta
Invariance learning algorithms that conditionally filter out domain-specific random variables as distractors, do so based only on the data semantics, and not the target domain unde…
CLIPDraw++: Text-to-Sketch Synthesis with Simple Primitives
Nityanand Mathur, Shyam Marjit, Abhra Chaudhuri +1
With the goal of understanding the visual concepts that CLIP associates with text prompts, we show that the latent space of CLIP can be visualized solely in terms of linear transfo…
Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata +1
Recent advances in fine-grained representation learning leverage local-to-global (emergent) relationships for achieving state-of-the-art results. The relational representations rel…
Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection
Swapnil Bhosale, Abhra Chaudhuri, Alex Lee Robert Williams +5
The introduction of the MUStARD dataset, and its emotion recognition extension MUStARD++, have identified sarcasm to be a multi-modal phenomenon -- expressed not only in natural la…