Related papers: The Perception-Physics Paradox: Probing Scientific…
Human perception is routinely assessing the similarity between images, both for decision making and creative thinking. But the underlying cognitive process is not really well understood yet, hence difficult to be mimicked by computer vision…
Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding. However, most methods rely on training…
Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in…
While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and…
While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race. Prior studies…
Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…
Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind.…
Structural equation modeling (SEM) is a statistical method widely used in educational research to investigate relationships between variables. SEM models are typically constructed based on theoretical foundations and assessed through fit…
Large vision-language models (VLMs) often rely on familiar semantic priors, but existing evaluations do not cleanly separate perception failures from rule-mapping failures. We study this behavior as semantic fixation: preserving a default…
Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this study, we move…
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…
Large Audio Language Models (LALMs) excel at semantic and paralinguistic tasks, yet their ability to perceive the fundamental physical attributes of audio such as pitch, loudness, and spatial location remains under-explored. To bridge this…
While quantum reality can be probed through measurements, the Two-State-Vector formalism (TSVF) reveals a subtler reality prevailing between measurements. Under special pre- and post-selections, odd physical values emerge. This unusual…
Humans appear to represent objects for intuitive physics with coarse, volumetric bodies'' that smooth concavities - trading fine visual details for efficient physical predictions - yet their internal structure is largely unknown.…
We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as ``black…
The funnel plot is a graphical visualisation of summary data estimates from a meta-analysis, and is a useful tool for detecting departures from the standard modelling assumptions. Although perhaps not widely appreciated, a simple extension…
Leveraging the vision foundation models has emerged as a mainstream paradigm that improves the performance of image feature matching. However, previous works have ignored the misalignment when introducing the foundation models into feature…
The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.g., text and images) align and eventually converge toward the same representation of reality. If true, this has significant implications…
2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect errors, and provide step-by-step guidance. In mixed reality settings, such systems must recognize…
Generalizable robotic mobile manipulation in open-world environments poses significant challenges due to long horizons, complex goals, and partial observability. A promising approach to address these challenges involves planning with a…