95 citations · 303 across the 47 of their papers we have counts for
53 papers
PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance
Avijit Dasgupta, Shayon Dasgupta, Zakaria Laskar +2
Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical activities. For these assista…
Flow Matching in Feature Space for Stochastic World Modeling
Francois Porcher, Nicolas Carion, Karteek Alahari +1
World modeling requires forecasting uncertain futures while preserving information useful for downstream perception. Existing visual world models often struggle to satisfy both goa…
How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?
Yedidia Agnimo, Anna Korba, Annabelle Blangero +2
Large language models (LLMs) can hallucinate, but do model uncertainty estimators reliably reveal when they do? Although uncertainty estimators are increasingly used to identify un…
Exploring High-Order Self-Similarity for Video Understanding
Manjin Kim, Heeseung Kwon, Karteek Alahari +1
Space-time self-similarity (STSS), which captures visual correspondences across frames, provides an effective way to represent temporal dynamics for video understanding. In this wo…
Flowception: Temporally Expansive Flow Matching for Video Generation
Tariq Berrada Ifriqi, John Nguyen, Karteek Alahari +2
We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions…
Online In-Context Distillation for Low-Resource Vision Language Models
Zhiqi Kang, Rahaf Aljundi, Vaggelis Dorovatas +1
As the field continues its push for ever more resources, this work turns the spotlight on a critical question: how can vision-language models (VLMs) be adapted to thrive in low-res…
Entropy Rectifying Guidance for Diffusion and Flow Models
Tariq Berrada Ifriqi, Adriana Romero-Soriano, Michal Drozdzal +2
Guidance techniques are commonly used in diffusion and flow models to improve image quality and input consistency for conditional generative tasks such as class-conditional and tex…
Advancing Prompt-Based Methods for Replay-Independent General Continual Learning
Zhiqi Kang, Liyuan Wang, Xingxing Zhang +1
General continual learning (GCL) is a broad concept to describe real-world continual learning (CL) problems, which are often characterized by online data streams without distinct t…
Boosting Latent Diffusion with Perceptual Objectives
Tariq Berrada, Pietro Astolfi, Melissa Hall +6
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produ…
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
Tariq Berrada Ifriqi, Pietro Astolfi, Melissa Hall +8
Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, the key components of the best performing LDM training recipe…
Unlocking Pre-trained Image Backbones for Semantic Image Synthesis
Tariq Berrada, Jakob Verbeek, Camille Couprie +1
Semantic image synthesis, i.e., generating images from user-provided semantic label maps, is an important conditional image generation task as it allows to control both the content…
On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
Thomas De Min, Massimiliano Mancini, Karteek Alahari +2
State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forget…
Guided Distillation for Semi-Supervised Instance Segmentation
Tariq Berrada, Camille Couprie, Karteek Alahari +1
Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate th…
Multi-Domain Learning with Modulation Adapters
Ekaterina Iakovleva, Karteek Alahari, Jakob Verbeek
Deep convolutional networks are ubiquitous in computer vision, due to their excellent performance across different tasks for various domains. Models are, however, often trained in…
Semi-supervised learning made simple with self-supervised clustering
Enrico Fini, Pietro Astolfi, Karteek Alahari +4
Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations. However, in many real-world scenarios, labels are partiall…
Think Before You Act: Unified Policy for Interleaving Language Reasoning with Actions
Lina Mezghani, Piotr Bojanowski, Karteek Alahari +1
The success of transformer models trained with a language modeling objective brings a promising opportunity to the reinforcement learning framework. Decision Transformer is a step…
Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping
Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski +2
Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is ext…
Fake it till you make it: Learning transferable representations from synthetic ImageNet clones
Mert Bulent Sariyildiz, Karteek Alahari, Diane Larlus +1
Recent image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a simple text prompt. Could such mode…
A soft nearest-neighbor framework for continual semi-supervised learning
Zhiqi Kang, Enrico Fini, Moin Nabi +2
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle t…
From CNNs to Shift-Invariant Twin Models Based on Complex Wavelets
Hubert Leterme, Kévin Polisano, Valérie Perrier +1
We propose a novel method to increase shift invariance and prediction accuracy in convolutional neural networks. Specifically, we replace the first-layer combination "real-valued c…
Lightweight Structure-Aware Attention for Visual Understanding
Heeseung Kwon, Francisco M. Castro, Manuel J. Marin-Jimenez +2
Attention operator has been widely used as a basic brick in visual understanding since it provides some flexibility through its adjustable kernels. However, this operator suffers f…
Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
Jules BOURCIER, Thomas Floquet, Gohar Dashyan +3
In defense-related remote sensing applications, such as vehicle detection on satellite imagery, supervised learning requires a huge number of labeled examples to reach operational…
Evaluating the Label Efficiency of Contrastive Self-Supervised Learning for Multi-Resolution Satellite Imagery
Jules Bourcier, Gohar Dashyan, Jocelyn Chanussot +1
The application of deep neural networks to remote sensing imagery is often constrained by the lack of ground-truth annotations. Adressing this issue requires models that generalize…
On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks
Hubert Leterme, Kévin Polisano, Valérie Perrier +1
This paper focuses on improving the mathematical interpretability of convolutional neural networks (CNNs) in the context of image classification. Specifically, we tackle the instab…