共找到 20 条结果
Researchers fear AI is moving too fast, while Mark Zuckerberg is worried about who owns it。 Plus: Inside Black Forest Labs’ push into robotics
Multimodal Large Language Models (MLLMs) suffer from hallucinations. Existing hallucination evaluation benchmarks are often limited by over-simplified tasks leading to saturated metrics, or insufficient diversity that fails to adequately assess the hallucination extent in state-of-the-art multimodal models. To address this gap, we propose FREAK, a comprehensive multimodal benchmark designed for fine-grained hallucination assessment in MLLMs. Through high-quality photorealistic images featuring fine-grained counter-commonsense edits, FREAK innovatively evaluates hallucination phenomena in detailed visual perception of MLLMs. Extensive experiments on FREAK show severe hallucination issues in SOTA models regarding detailed visual perception. To enable deeper investigation, we curate a controlled subset to indirectly evaluate the model's ability to perceive target detailed information. Through systematic evaluation of prevailing Chain-of-Thought (CoT) prompting techniques within this task, we reveal critical insights regarding hallucination patterns and model reasoning processes.
Waves propagating through weakly disordered smooth linear media undergo a universal phenomenon called branched flow. Branched flow has been observed and studied experimentally in various systems by considering coherent waves. Recent experiments have reported the observation of optical branched flow by using an incoherent light source, thus revealing the key role of coherent phase-sensitive effects in the development of incoherent branched flow. By considering the paraxial wave equation as a generic representative model, we elaborate a stochastic theory of both coherent and incoherent branched flow. We derive closed-form equations that determine the evolution of the intensity correlation function, as well as the value and the propagation distance of the maximum of the scintillation index, which characterize the dynamical formation of incoherent branched flow. We report accurate numerical simulations that are found in quantitative agreement with the theory without free parameters. Our theory highlights the important impact of coherence and interference on branched flow, thereby providing a framework for exploring branched flow in nonlinear media, in relation with the formation of fre
The purpose of this short note is to explain how the existing results on the validity of the NLS approximation can be extended from Sobolev spaces $H^s(\mathbb{R})$ to the spaces of functions $u = v + w$ where $v \in H_{per}^s$ and $w \in H^s(\mathbb{R})$. This allows us to use the Peregrine solution of the NLS equation to find freak or rogue wave dynamics in more complicated systems.
Achieving high-fidelity lip-speech synchronization in audio-driven talking portrait synthesis remains challenging. While multi-stage pipelines or diffusion models yield high-quality results, they suffer from high computational costs. Some approaches perform well on specific individuals with low resources, yet still exhibit mismatched lip movements. The aforementioned methods are modeled in the pixel domain. We observed that there are noticeable discrepancies in the frequency domain between the synthesized talking videos and natural videos. Currently, no research on talking portrait synthesis has considered this aspect. To address this, we propose a FREquency-modulated, high-fidelity, and real-time Audio-driven talKing portrait synthesis framework, named FREAK, which models talking portraits from the frequency domain perspective, enhancing the fidelity and naturalness of the synthesized portraits. FREAK introduces two novel frequency-based modules: 1) the Visual Encoding Frequency Modulator (VEFM) to couple multi-scale visual features in the frequency domain, better preserving visual frequency information and reducing the gap in the frequency spectrum between synthesized and natural
Pair soliton interactions play a significant role in the dynamics of soliton turbulence. The interaction of solitons with different polarities is particularly crucial in the context of abnormally large wave formation, often referred to as freak or rogue waves, as these interactions result in an increase in the maximum wave field. In this article, we investigate the features and properties of bipolar soliton interactions within the framework of the non-integrable Schamel equation, contrasting them with the integrable modified Korteweg-de Vries equation. We examine variations in moments and extrema of the wave fields. Additionally, we identify scenarios in which, in the bipolar solitary wave interaction, the smaller solitary wave transfers a portion of its energy to the larger one, causing an increase in the amplitude of the larger solitary wave and a decrease in the amplitude of the smaller one, returning them to their pre-interaction state. Notably, we observe that non-integrability can be considered a factor that triggers the formation of rogue waves.
In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of samples. Building on these findings, we propose FREAK, a frequency-based poisoned sample detection algorithm that is simple yet effective. Our experimental results demonstrate the efficacy of FREAK not only against frequency backdoor attacks but also against some spatial attacks. Our work is just the first step in leveraging these insights. We believe that our analysis and proposed defense mechanism will provide a foundation for future research and development of backdoor defenses.
The ``ugly duckling'' of the Segré-Plebański-Hawking-Ellis classification of stress-energy tensors is believed to be either impossible or extremely difficult to realise in Einstein gravity. Effective stress-energy tensors in alternative gravity offer a wider range of possibilities. We report a class of type III realisations in ``first-generation'' scalar-tensor and in Horndeski gravity, and their physical interpretation. The ugly duckling may be a freak of nature of limited importance but it is not physically impossible.
Fisheye lens, which is suitable for panoramic imaging, has the prominent advantage of a large field of view and low cost. However, the fisheye image has a severe geometric distortion which may interfere with the stage of image registration and stitching. Aiming to resolve this drawback, we devise a stronger stitching algorithm for fisheye images by combining the traditional image processing method with deep learning. In the stage of fisheye image correction, we propose the Attention-based Nonlinear Activation Free Network (ANAFNet) to deblur fisheye images corrected by Zhang calibration method. Specifically, ANAFNet adopts the classical single-stage U-shaped architecture based on convolutional neural networks with soft-attention technique and it can restore a sharp image from a blurred image effectively. In the part of image registration, we propose the ORB-FREAK-GMS (OFG), a comprehensive image matching algorithm, to improve the accuracy of image registration. Experimental results demonstrate that panoramic images of superior quality stitching by fisheye images can be obtained through our method.
Researchers discovered a proton-assisted mechanism that greatly improves how triplet energy moves between quantum dots and nearby molecules。 The proton briefly shifts position, helps coordinate electron movement, and then returns to where it started。 This quantum-driven shuttle could offer a powerful new way to tune solar cells, lasers, and catalyt
Scientists have created a programmable optical chip that can slow light on demand, giving engineers far greater control over how optical signals propagate through a circuit。 The technology could provide the delays, synchronization, and buffering functions needed to make light-based computing more practical。 A single chip could eventually perform se
Plus, a new policy for the AI protocol ensures features aren't removed suddenly
NASA is preparing for future astronaut landings on the Moon with an unusually ambitious orbital rehearsal。 During Artemis III in 2027, Orion astronauts will rendezvous and dock separately with prototype lunar landers from Blue Origin and SpaceX, allowing crews and ground teams to test the complex maneuvers needed for later missions
Rice University chemists have found a new way to make neodymium, a rare-earth metal, interact with oxygen。 Using a specially designed molecular structure described as a “basket,” the team positioned the atoms so they could form a bond once thought unlikely。 The breakthrough produced highly reactive compounds that could eventually give chemists alte
Scientists are testing two promising ways to destroy PFAS, the stubborn “forever chemicals” that can accumulate in water and resist normal treatment。 One method uses collapsing vapor bubbles to generate extreme heat and reactive molecules, while the other uses cold plasma and rising gas bubbles to pull PFAS to the surface and break them apart
A distant Sun-like star appears to have devoured one of its planets, leaving behind a surprising chemical fingerprint。 Researchers found an unusually high concentration of lithium, a strong sign that planetary material was mixed into the star。 Careful comparisons with dozens of similar stars confirmed the signal is highly unusual, and scientists th
Ars Pro subscribers get customizable layouts along with no ads and no trackers
The Backrooms began as a single eerie image of empty yellow rooms, but internet users transformed it into a vast fictional world that feels disturbingly real。 Through videos, games, maps, survival guides and social media stories, audiences do more than watch the horror unfold。 They help build and explore it