Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global features--such as CLIP's [CLS] token--between adversarial and target samples, they often overlook the rich local information encoded in patch tokens. This leads to suboptimal alignment and limited transferability, particularly for closed-source models. To address this limitation, we propose a targeted transferable adversarial attack method based on feature optimal alignment, called FOA-Attack, to improve adversarial transfer capability. Specifically, at the global level, we introduce a global feature loss based on cosine similarity to align the coarse-grained features of adversarial samples with those of target samples. At the local level, given the rich local representations within Transformers, we leverage clustering techniques to extract compact local patterns to alleviate redundant local features. We then formulate local feature alignment between adversarial and target samples as an optimal transport (OT) problem and propose a local clustering optimal transport loss to refine fine-grained feature alignment. Additionally, we propose a dynamic ensemble model weighting strategy to adaptively balance the influence of multiple models during adversarial example generation, thereby further improving transferability. Extensive experiments across various models demonstrate the superiority of the proposed method, outperforming state-of-the-art methods, especially in transferring to closed-source MLLMs.

Hemodynamics has a substantial influence on normal cardiovascular growth and disease formation, but requires time-consuming simulations to obtain. Deep Learning algorithms to rapidly predict hemodynamics parameters can be very useful, but their development is hindered by the lack of large dataset on anatomic geometries and associated fluid dynamics. This paper presents a new large-scale dataset of intracranial aneurysm (IA) geometries and hemodynamics to support the development of neural operators to solve geometry-dependent flow governing partial differential equations. The dataset includes 14,000 steady-flow cases and 730 pulsatile-flow cases simulated with computational fluid dynamics. All cases are computed using a laminar flow setup with more than 3 million cells.

Large language models (LLMs) have emerged as a dominant AI paradigm due to their exceptional text understanding and generation capabilities. However, their tendency to generate inconsistent or erroneous outputs challenges their reliability, especially in high-stakes domains requiring accuracy and trustworthiness. Existing research primarily focuses on detecting and mitigating model misbehavior in general-purpose scenarios, often overlooking the potential of integrating domain-specific knowledge. In this work, we advance misbehavior detection by incorporating domain knowledge. The core idea is to design a general specification language that enables domain experts to customize domain-specific constraints in a lightweight and intuitive manner, supporting later runtime monitoring of LLM outputs.

Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which can compromise output integrity. Existing defenses often apply aggressive filtering, leading to unnecessary loss of valuable information and reduced reliability in generation. To address this problem, we propose a two-stage semantic filtering and conflict-free framework for trustworthy RAG. In the first stage, we perform a joint filter with semantic and cluster-based filtering which is guided by the Entity-intent-relation extractor (EIRE). EIRE extracts entities, latent objectives, and entity relations from both the user query and filtered documents, scores their semantic relevance, and selectively adds valuable documents into the clean retrieval database. In the second stage, we proposed an EIRE-guided conflict-aware filtering module, which analyzes semantic consistency between the query, candidate answers, and retrieved knowledge before final answer generation, filtering out internal and external contradictions that could mislead the model. Through this two-stage process, SeCon-RAG effectively preserves useful knowledge while mitigating conflict contamination, achieving significant improvements in both generation robustness and output trustworthiness. Extensive experiments across various LLMs and datasets demonstrate that the proposed SeCon-RAG markedly outperforms state-of-the-art defense methods.

In collaborative data sharing and machine learning, multiple parties aggregate their data resources to train a machine learning model with better model performance. However, as the parties incur data collection costs, they are only willing to do so when guaranteed incentives, such as fairness and individual rationality. Existing frameworks assume that all parties join the collaboration simultaneously, which does not hold in many real-world scenarios. Due to the long processing time for data cleaning, difficulty in overcoming legal barriers, or unawareness, the parties may join the collaboration at different times. In this work, we propose the following perspective: As a party who joins earlier incurs higher risk and encourages the contribution from other wait-and-see parties, that party should receive a reward of higher value for sharing data earlier. To this end, we propose a fair and time-aware data sharing framework, including novel time-aware incentives. We develop new methods for deciding reward values to satisfy these incentives. We further illustrate how to generate model rewards that realize the reward values and empirically demonstrate the properties of our methods on synthetic and real-world datasets.

Environment Animals Wildlife New box jellyfish name warns of'death from behind' More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. The jellyfish looks nearly identical to a relative species. Breakthroughs, discoveries, and DIY tips sent six days a week. A recently discovered box jellyfish species living in near Singapore looks nearly identical to jellyfish previously discovered by the same scientist. But regardless of whether or not you can tell and apart, you'll want to steer clear of both of them.

A team of scientists from Nanyang Technological University Singapore has developed a new biochip that, when paired with computer vision, can detect quickly and accurately extremely small amounts of microRNAs, which are tiny genetic markers linked to diseases such as heart disease. Published in the scientific journal, the new biosensing platform combines a specially designed nanophotonic chip with AI-automated image analysis. With a tiny drop of blood loaded into the chip, it can rapidly detect multiple microRNA biomarkers. With its integrated AI imaging function, thousands of microRNA signals can be imaged and analysed in a single snapshot. Compared with the current gold standard of detecting microRNA - PCR (polymerase chain reaction) detects tiny amounts of genetic material by copying them many times - the new device can cut detection time from hours to 20 minutes. MicroRNAs are short RNA molecules that help regulate genes that work in the body.

Earlier today, Meta announced that it was testing a new Meta AI chatbot for Threads that would function a lot like Grok on X. Even though the early beta isn't available to most people on the platform yet, a number of Threads users have discovered its not possible to opt out of the feature or block chatbot's the account. While most people aren't able to interact with bot yet -- the initial testing is limited to Malaysia, Saudi Arabia, Mexico, Argentina and Singapore -- the public-facing @ meta.ai account is viewable to everyone on the platform. The account's initial post has been met with a flood of angry replies from users demanding to know why, unlike any other Threads account, there's no option to block it entirely. Some users have even said that they have reported the account for spam, which typically ends with the option to block, only to find out that the block didn't actually go into effect.

Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions. We introduce Curiosity-Critic, which grounds its intrinsic reward in the improvement of this cumulative objective, and show that it reduces to a tractable per-step form: the difference between the current prediction error and the asymptotic error baseline of the current state transition. We estimate this baseline online with a learned critic co-trained alongside the world model; regressing a single scalar, the critic converges well before the world model saturates, redirecting exploration toward learnable transitions without oracle knowledge of the noise floor. The reward is higher for learnable transitions and collapses toward the baseline for stochastic ones, effectively separating epistemic (reducible) from aleatoric (irreducible) prediction error online. Prior prediction-error curiosity formulations, from Schmidhuber (1991) to learned-feature-space variants, emerge as special cases corresponding to specific approximations of this baseline. Experiments on a stochastic grid world show that Curiosity-Critic outperforms prediction-error and visitation-count baselines in convergence speed and final world model accuracy.

What if training a robot to handle dirty, dangerous work on the factory floor was as simple as showing it how? Czech startup RoboTwin is doing exactly that, helping factory workers teach robots new skills by demonstration. Instead of writing complex code, workers perform the job once and RoboTwin's technology turns those movements into a robot programme - opening the door to automation for smaller manufacturers. Founded in Prague in 2021, RoboTwin builds handheld devices and no-code software that capture human movements and translate them into instructions for industrial robots. The aim is to make automation faster, simpler and more accessible to manufacturers that do not have specialist robotics programmers.