相关论文: Linton Stereo Illusion: Response on Johnston (1991…

I argue that there is a crisis in optical Astronomy due to a paucity of telescopes and thus the need for a paradigm shift in telescope technology. Large increases in collecting areas and observing time/astronomer are only possible if we…

Comment on Phys. Rev. Lett. 86, 2086 (2001)

Next generation observatories will enable us to study the first billion years of our Universe in unprecedented detail. Foremost among these are 21-cm interferometry with the HERA and the SKA, and high-$z$ galaxy observations with the James…

Strong gravitational lensing enables a wide range of science: probing cosmography; testing dark matter models; understanding galaxy evolution; and magnifying the faint, small and distant Universe. However to date exploiting strong lensing…

Convolutional neural networks (CNN) have shown state-of-the-art results for low-level computer vision problems such as stereo and monocular disparity estimations, but still, have much room to further improve their performance in terms of…

Logit Lens is a widely adopted method for mechanistic interpretability of transformer-based language models, enabling the analysis of how internal representations evolve across layers by projecting them into the output vocabulary space.…

Large Vision-Language Models (LVLMs) bridge the gap between visual and linguistic modalities, demonstrating strong potential across a variety of domains. However, despite significant progress, LVLMs still suffer from severe hallucination…

Vision-Language Models (VLMs) have achieved remarkable success in various tasks, yet their robustness to real-world illumination variations remains largely unexplored. To bridge this gap, we propose \textbf{I}llumination…

Both humans and computational methods struggle to discriminate the depths of objects hidden beneath foliage. However, such discrimination becomes feasible when we combine computational optical synthetic aperture sensing with the human…

Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quantify such behaviours are lacking. Classical…

This review aims to provide a comprehensive update on the progress made on the Sequential Testing problem (STP) in the last 20 years after the review, [1] was published. Many studies have provided new theoretical results, extensions of the…

Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right images to infer depth. In this work, we revisit the problem from a sequence-to-sequence correspondence perspective to…

In this paper we investigate the opportunities provided by the James Webb Space Telescope (JWST) for significant scientific advances in the study of solar system bodies and rings using stellar occultations. The strengths and weaknesses of…

The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification and detection, VLMs are capable of visual comprehension and…

In a systematic way, we investigate a widely asked question: Do LLMs really understand what they say?, which relates to the more familiar term Stochastic Parrot. To this end, we propose a summative assessment over a carefully designed…

Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden states appear to already encode future reasoning before CoT…

Conventional stereoscopic displays suffer from vergence-accommodation conflict and cause visual fatigue. Integral-imaging-based displays resolve the problem by directly projecting the sub-aperture views of a light field into the eyes using…

In the study of LLMs, sycophancy represents a prevalent hallucination that poses significant challenges to these models. Specifically, LLMs often fail to adhere to original correct responses, instead blindly agreeing with users' opinions,…

Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual…

The dual thinking framework considers fast, intuitive, and slower logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and logical processing differ, and the latter is under-explored…