Related papers: Learning Abstract Visual Reasoning via Task Decomp…
To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies…
Spatial reasoning in large-scale 3D environments such as warehouses remains a significant challenge for vision-language systems due to scene clutter, occlusions, and the need for precise spatial understanding. Existing models often struggle…
Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key…
Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…
This study focuses on Embodied Complex-Question Answering task, which means the embodied robot need to understand human questions with intricate structures and abstract semantics. The core of this task lies in making appropriate plans based…
Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…
An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including modern 4D CT scanning methods, represent data natively as INRs. While INRs are…
The ability to hypothesise, develop abstract concepts based on concrete observations and apply these hypotheses to justify future actions has been paramount in human development. An existing line of research in outfitting intelligent…
Visual abstract reasoning is core to image processing. We present Valen, a unified probability-highlighting baseline that excels on both RPM (progression) and Bongard-Logo (clustering) tasks. Analysing its internals, we find solvers…
Deep learning architectures based on convolutional neural networks tend to rely on continuous, smooth features. While this characteristics provides significant robustness and proves useful in many real-world tasks, it is strikingly…
Human intelligence relies in part on our brains' ability to create abstract mental models that succinctly capture the hidden blueprint of our reality. Such abstract world models notably allow us to rapidly navigate novel situations by…
Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…
Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains. An established approach to interpretability is generating visual attribution maps that…
Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and…
We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem. A three-layer architecture is suggested that consists of a…
Abstract visual reasoning remains challenging as existing methods often prioritize either global context or local row-wise relations, failing to integrate both, and lack intermediate feature constraints, leading to incomplete rule capture…
Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which…
Statistics and Optimization are foundational to modern Machine Learning. Here, we propose an alternative foundation based on Abstract Algebra, with mathematics that facilitates the analysis of learning. In this approach, the goal of the…
Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or…
Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in…