How and where does a transformer notice that a sentence has gone semantically off the rails? To explore this question, we evaluated the causal language model (phi-2) using a carefully curated corpus, with sentences that concluded plausibly or implausibly. Our analysis focused on the hidden states sampled at each model layer. To investigate how violations are encoded, we utilized two complementary probes. First, we conducted a per-layer detection using a linear probe. Our findings revealed that a simple linear decoder struggled to distinguish between plausible and implausible endings in the lowest third of the model's layers. However, its accuracy sharply increased in the middle blocks, reaching a peak just before the top layers. Second, we examined the effective dimensionality of the encoded violation. Initially, the violation widens the representational subspace, followed by a collapse after a mid-stack bottleneck. This might indicate an exploratory phase that transitions into rapid consolidation. Taken together, these results contemplate the idea of alignment with classical psycholinguistic findings in human reading, where semantic anomalies are detected only after syntactic resolution, occurring later in the online processing sequence.

Untethered magnetic manipulation of biomedical millirobots has a high potential for minimally invasive surgical applications. However, it is still challenging to exert high actuation forces on the small robots over a large distance. Permanent magnets offer stronger magnetic torques and forces than electromagnetic coils, however, feedback control is more difficult. As proven by Earnshaw's theorem, it is not possible to achieve a stable magnetic trap in 3D by static permanent magnets. Here, we report a stable 2D magnetic force trap by an array of permanent magnets to control a millirobot. The trap is located in an open space with a tunable distance to the magnet array in the range of 20 - 120mm, which is relevant to human anatomical scales. The design is achieved by a novel GPU-accelerated optimization algorithm that uses mean squared error (MSE) and Adam optimizer to efficiently compute the optimal angles for any number of magnets in the array. The algorithm is verified using numerical simulation and physical experiments with an array of two magnets. A millirobot is successfully trapped and controlled to follow a complex trajectory. The algorithm demonstrates high scalability by optimizing the angles for 100 magnets in under three seconds. Moreover, the optimization workflow can be adapted to optimize a permanent magnet array to achieve the desired force vector fields.

Contradictory multimodal inputs are common in real-world settings, yet existing benchmarks typically assume input consistency and fail to evaluate cross-modal contradiction detection - a fundamental capability for preventing hallucinations and ensuring reliability. We introduce CLASH, a novel benchmark for multimodal contradiction detection, featuring COCO images paired with contradictory captions containing controlled object-level or attribute-level contradictions. The samples include targeted questions evaluated in both multiple-choice and open-ended formats. The benchmark provides an extensive fine-tuning set filtered through automated quality checks, alongside a smaller human-verified diagnostic set. Our analysis of state-of-the-art models reveals substantial limitations in recognizing cross-modal conflicts, exposing systematic modality biases and category-specific weaknesses. Furthermore, we empirically demonstrate that targeted fine-tuning on CLASH substantially enhances conflict detection capabilities.

Surgical planning and training based on machine learning requires a large amount of 3D anatomical models reconstructed from medical imaging, which is currently one of the major bottlenecks. Obtaining these data from real patients and during surgery is very demanding, if even possible, due to legal, ethical, and technical challenges. It is especially difficult for soft tissue organs with poor imaging contrast, such as the prostate. To overcome these challenges, we present a novel workflow for automated 3D anatomical data generation using data obtained from physical organ models. We additionally use a 3D Generative Adversarial Network (GAN) to obtain a manifold of 3D models useful for other downstream machine learning tasks that rely on 3D data. We demonstrate our workflow using an artificial prostate model made of biomimetic hydrogels with imaging contrast in multiple zones. This is used to physically simulate endoscopic surgery. For evaluation and 3D data generation, we place it into a customized ultrasound scanner that records the prostate before and after the procedure. A neural network is trained to segment the recorded ultrasound images, which outperforms conventional, non-learning-based computer vision techniques in terms of intersection over union (IoU). Based on the segmentations, a 3D mesh model is reconstructed, and performance feedback is provided.

Abstract--Detecting deepfake images is crucial in combating misinformation. We present a lightweight, generalizable binary classification model based on EfficientNet-B6, fine-tuned with transformation techniques to address severe class imbalances. By leveraging robust preprocessing, oversampling, and optimization strategies, our model achieves high accuracy, stability, and generalization. While incorporating Fourier transform-based phase and amplitude features showed minimal impact, our proposed framework helps non-experts to effectively identify deepfake images, making significant strides toward accessible and reliable deepfake detection. Advances in synthetic data generation have introduced both opportunities and challenges, particularly with the rise of deep-fake technology.

Designing new protein structures is fundamental to computational biology, enabling advances in therapeutic molecule discovery and enzyme engineering. Existing diffusion-based generative models typically operate in Cartesian coordinate space, where adding noise disrupts strict geometric constraints such as fixed bond lengths and angles, often producing physically invalid structures. To address this limitation, we propose a Torsion-Space Diffusion Model that generates protein backbones by denoising torsion angles, ensuring perfect local geometry by construction. A differentiable forward-kinematics module reconstructs 3D coordinates with fixed 3.8 Angstrom backbone bond lengths while a constrained post-processing refinement optimizes global compactness via Radius of Gyration (Rg) correction, without violating bond constraints. Experiments on standard PDB proteins demonstrate 100% bond-length accuracy and significantly improved structural compactness, reducing Rg error from 70% to 18.6% compared to Cartesian diffusion baselines. Overall, this hybrid torsion-diffusion plus geometric-refinement framework generates physically valid and compact protein backbones, providing a promising path toward full-atom protein generation.

Advertising (Ad) is a cornerstone of the digital economy, yet the moderation of video advertisements remains a significant challenge due to their complexity and the need for precise violation localization. While recent advancements, such as the RAVEN model, have improved coarse-grained violation detection, critical gaps persist in fine-grained understanding, explainability, and generalization. To address these limitations, we propose RAVEN++, a novel framework that introduces three key innovations: 1) Active Reinforcement Learning (RL), which dynamically adapts training to samples of varying difficulty; 2) Fine-Grained Violation Understanding, achieved through hierarchical reward functions and reasoning distillation; and 3) Progressive Multi-Stage Training, which systematically combines knowledge injection, curriculum-based passive RL, and active RL. Extensive experiments on both public and proprietary datasets, on both offline scenarios and online deployed A/B Testing, demonstrate that RAVEN++ outperforms general-purpose LLMs and specialized models like RAVEN in terms of fine-grained violation understanding, reasoning capabilities, and generalization ability.

This paper introduces the retrieval-augmented framework for automatic fashion caption and hashtag generation, combining multi-garment detection, attribute reasoning, and Large Language Model (LLM) prompting. The system aims to produce visually grounded, descriptive, and stylistically interesting text for fashion imagery, overcoming the limitations of end-to-end captioners that have problems with attribute fidelity and domain generalization. The pipeline combines a YOLO-based detector for multi-garment localization, k-means clustering for dominant color extraction, and a CLIP-FAISS retrieval module for fabric and gender attribute inference based on a structured product index. These attributes, together with retrieved style examples, create a factual evidence pack that is used to guide an LLM to generate human-like captions and contextually rich hashtags. A fine-tuned BLIP model is used as a supervised baseline model for comparison. Experimental results show that the YOLO detector is able to obtain a mean Average Precision (mAP@0.5) of 0.71 for nine categories of garments. The RAG-LLM pipeline generates expressive attribute-aligned captions and achieves mean attribute coverage of 0.80 with full coverage at the 50% threshold in hashtag generation, whereas BLIP gives higher lexical overlap and lower generalization. The retrieval-augmented approach exhibits better factual grounding, less hallucination, and great potential for scalable deployment in various clothing domains. These results demonstrate the use of retrieval-augmented generation as an effective and interpretable paradigm for automated and visually grounded fashion content generation.

Aspect category sentiment analysis (ACSA) has achieved remarkable progress with large language models (LLMs), yet existing approaches primarily emphasize sentiment polarity while overlooking the underlying emotional dimensions that shape sentiment expressions. This limitation hinders the model's ability to capture fine-grained affective signals toward specific aspect categories. To address this limitation, we introduce a novel emotion-enhanced multi-task ACSA framework that jointly learns sentiment polarity and category-specific emotions grounded in Ekman's six basic emotions. Leveraging the generative capabilities of LLMs, our approach enables the model to produce emotional descriptions for each aspect category, thereby enriching sentiment representations with affective expressions. Furthermore, to ensure the accuracy and consistency of the generated emotions, we introduce an emotion refinement mechanism based on the Valence-Arousal-Dominance (VAD) dimensional framework. Specifically, emotions predicted by the LLM are projected onto a VAD space, and those inconsistent with their corresponding VAD coordinates are re-annotated using a structured LLM-based refinement strategy. Experimental results demonstrate that our approach significantly outperforms strong baselines on all benchmark datasets. This underlines the effectiveness of integrating affective dimensions into ACSA.

In AI, the existential risk denotes the hypothetical threat posed by an artificial system that would possess both the capability and the objective, either directly or indirectly, to eradicate humanity. This issue is gaining prominence in scientific debate due to recent technical advancements and increased media coverage. In parallel, AI progress has sparked speculation and studies about the potential emergence of artificial consciousness. The two questions, AI consciousness and existential risk, are sometimes conflated, as if the former entailed the latter. Here, I explain that this view stems from a common confusion between consciousness and intelligence. Yet these two properties are empirically and theoretically distinct. Arguably, while intelligence is a direct predictor of an AI system's existential threat, consciousness is not. There are, however, certain incidental scenarios in which consciousness could influence existential risk, in either direction. Consciousness could be viewed as a means towards AI alignment, thereby lowering existential risk; or, it could be a precondition for reaching certain capabilities or levels of intelligence, and thus positively related to existential risk. Recognizing these distinctions can help AI safety researchers and public policymakers focus on the most pressing issues.