Related papers: Unifying (Machine) Vision via Counterfactual World…

Transformer-based models have transformed the landscape of natural language processing (NLP) and are increasingly applied to computer vision tasks with remarkable success. These models, renowned for their ability to capture long-range…

Contemporary computational neuroscience features two prominent modeling traditions. Bottom-up whole-brain modeling (WBM) builds biophysically detailed simulations of brain structure and dynamics, whereas top-down neuroconnectionism…

Understanding causes and effects in mechanical systems is an essential component of reasoning in the physical world. This work poses a new problem of counterfactual learning of object mechanics from visual input. We develop the CoPhy…

Learning predictive models from high-dimensional sensory observations is fundamental for cyber-physical systems, yet the latent representations learned by standard world models lack physical interpretability. This limits their reliability,…

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a…

Autonomous driving systems depend on on models that can reason about high-level scene contexts and accurately predict the dynamics of their surrounding environment. Vision- Language Models (VLMs) have recently emerged as promising tools for…

Computer vision can be understood as the ability to perform inference on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques. This thesis proposes novel inference schemes and…

Visual Question Answering (VQA) has been a popular task that combines vision and language, with numerous relevant implementations in literature. Even though there are some attempts that approach explainability and robustness issues in VQA…

Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…

Counterfactual explanation methods have recently received significant attention for explaining CNN-based image classifiers due to their ability to provide easily understandable explanations that align more closely with human reasoning.…

Object-centric world models (OCWM) aim to decompose visual scenes into object-level representations, providing structured abstractions that could improve compositional generalization and data efficiency in reinforcement learning. We…

Multi-view clustering has gained broad attention owing to its capacity to exploit complementary information across multiple data views. Although existing methods demonstrate delightful clustering performance, most of them are of high time…

Self-supervised learning has proved effective for skeleton-based human action understanding, which is an important yet challenging topic. Previous works mainly rely on contrastive learning or masked motion modeling paradigm to model the…

Large language models, trained on extensive corpora, successfully unify diverse linguistic tasks within a single generative framework. Inspired by this, recent works like Large Vision Model (LVM) extend this paradigm to vision by organizing…

The advent of foundation models, which are pre-trained on vast datasets, has ushered in a new era of computer vision, characterized by their robustness and remarkable zero-shot generalization capabilities. Mirroring the transformative…

Working memory (WM), a fundamental cognitive process facilitating the temporary storage, integration, manipulation, and retrieval of information, plays a vital role in reasoning and decision-making tasks. Robust benchmark datasets that…

Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, but important…

While reinforcement learning from scratch has shown impressive results in solving sequential decision-making tasks with efficient simulators, real-world applications with expensive interactions require more sample-efficient agents.…

Advances in computer vision have brought us to the point where we have the ability to synthesise realistic fake content. Such approaches are seen as a source of disinformation and mistrust, and pose serious concerns to governments around…

Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, current multimodal large language models (MLLMs) cannot do this,…