相关论文: Hypo3D: Exploring Hypothetical Reasoning in 3D

Multiview 3D evaluation assumes that the images being scored are observations of one static 3D scene. This assumption can fail in NVS and sparse-view reconstruction: inputs or generated outputs may contain artifacts, outlier frames,…

Transformers have demonstrated remarkable performance in natural language processing and related domains, as they largely focus on sequential, autoregressive next-token prediction tasks. Yet, they struggle in logical reasoning, not…

Many real-world tasks require an agent to reason jointly over text and visual objects, (e.g., navigating in public spaces), which we refer to as context-sensitive text-rich visual reasoning. Specifically, these tasks require an…

Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth…

Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing…

Machine learning models are often brittle on production data despite achieving high accuracy on benchmark datasets. Benchmark datasets have traditionally served dual purposes: first, benchmarks offer a standard on which machine learning…

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of…

The recent development of Large Language Models (LLMs) with strong reasoning ability has driven research in various domains such as mathematics, coding, and scientific discovery. Meanwhile, 3D visual grounding, as a fundamental task in 3D…

Visual Question Answering (VQA) has witnessed tremendous progress in recent years. However, most efforts only focus on the 2D image question answering tasks. In this paper, we present the first attempt at extending VQA to the 3D domain,…

Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate…

Reliable three-dimensional human pose estimation (3D HPE) remains challenging due to the differences in viewpoints, environments, and camera conventions among datasets. As a result, methods that achieve near-optimal in-dataset accuracy…

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…

Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliably ground language into spatially coherent, plausibly executable actions in 3D digital…

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language…

While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant challenge. Current approaches focus primarily on aligning 3D…

Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be…

The hallucination of large multimodal models (LMMs), providing responses that appear correct but are actually incorrect, limits their reliability and applicability. This paper aims to study the hallucination problem of LMMs in video…

Inductive reasoning is a core problem-solving capacity: humans can identify underlying principles from a few examples, which robustly generalize to novel scenarios. Recent work evaluates large language models (LLMs) on inductive reasoning…

Building models that can understand and reason about 3D scenes is difficult owing to the lack of data sources for 3D supervised training and large-scale training regimes. In this work we ask - How can the knowledge in a pre-trained language…