As large language models (LLMs) become more advanced, it is increasingly difficult to distinguish between human-written and AI-generated text. This paper draws a conceptual parallel between quantum uncertainty and the limits of authorship detection in natural language. We argue that there is a fundamental trade-off: the more confidently one tries to identify whether a text was written by a human or an AI, the more one risks disrupting the text's natural flow and authenticity. This mirrors the tension between precision and disturbance found in quantum systems. We explore how current detection methods--such as stylometry, watermarking, and neural classifiers--face inherent limitations. Enhancing detection accuracy often leads to changes in the AI's output, making other features less reliable. In effect, the very act of trying to detect AI authorship introduces uncertainty elsewhere in the text. Our analysis shows that when AI-generated text closely mimics human writing, perfect detection becomes not just technologically difficult but theoretically impossible. We address counterarguments and discuss the broader implications for authorship, ethics, and policy. Ultimately, we suggest that the challenge of AI-text detection is not just a matter of better tools--it reflects a deeper, unavoidable tension in the nature of language itself.

We introduce EgoMem, the first lifelong memory agent tailored for full-duplex models that process real-time omnimodal streams. EgoMem enables real-time models to recognize multiple users directly from raw audiovisual streams, to provide personalized response, and to maintain long-term knowledge of users' facts, preferences, and social relationships extracted from audiovisual history. EgoMem operates with three asynchronous processes: (i) a retrieval process that dynamically identifies user via face and voice, and gathers relevant context from a long-term memory; (ii) an omnimodal dialog process that generates personalized audio responses based on the retrieved context; and (iii) a memory management process that automatically detects dialog boundaries from omnimodal streams, and extracts necessary information to update the long-term memory. Unlike existing memory agents for LLMs, EgoMem relies entirely on raw audiovisual streams, making it especially suitable for lifelong, real-time, and embodied scenarios. Experimental results demonstrate that EgoMem's retrieval and memory management modules achieve over 95% accuracy on the test set. When integrated with a fine-tuned RoboEgo omnimodal chatbot, the system achieves fact-consistency scores above 87% in real-time personalized dialogs, establishing a strong baseline for future research.

Abstract-- Language and embodied perspective taking are essential for human collaboration, yet few computational models address both simultaneously. This work investigates the PerspAct system [1], which integrates the ReAct (Reason and Act) paradigm with Large Language Models (LLMs) to simulate developmental stages of perspective taking, grounded in Selman's theory [2]. Using an extended director task, we evaluate GPT's ability to generate internal narratives aligned with specified developmental stages, and assess how these influence collaborative performance both qualitatively (action selection) and quantitatively (task efficiency). Results show that GPT reliably produces developmentally-consistent narratives before task execution but often shifts towards more advanced stages during interaction, suggesting that language exchanges help refine internal representations. Higher developmental stages generally enhance collaborative effectiveness, while earlier stages yield more variable outcomes in complex contexts. These findings highlight the potential of integrating embodied perspective taking and language in LLMs to better model developmental dynamics and stress the importance of evaluating internal speech during combined linguistic and embodied tasks.

Scaling Transformer policies and diffusion models has advanced robotic manipulation, yet combining these techniques in lightweight, cross-embodiment learning settings remains challenging. We study design choices that most affect stability and performance for diffusion-transformer policies trained on heterogeneous, multimodal robot data, and introduce Tenma, a lightweight diffusion-transformer for bi-manual arm control. Tenma integrates multiview RGB, proprioception, and language via a cross-embodiment normalizer that maps disparate state/action spaces into a shared latent space; a Joint State-Time encoder for temporally aligned observation learning with inference speed boosts; and a diffusion action decoder optimized for training stability and learning capacity. Across benchmarks and under matched compute, Tenma achieves an average success rate of 88.95% in-distribution and maintains strong performance under object and scene shifts, substantially exceeding baseline policies whose best in-distribution average is 18.12%. Despite using moderate data scale, Tenma delivers robust manipulation and generalization, indicating the great potential for multimodal and cross-embodiment learning strategies for further augmenting the capacity of transformer-based imitation learning policies.

Video Question Answering (VQA) requires models to reason over spatial, temporal, and causal cues in videos. Recent vision language models (VLMs) achieve strong results but often rely on shallow correlations, leading to weak temporal grounding and limited interpretability. We study symbolic scene graphs (SGs) as intermediate grounding signals for VQA. SGs provide structured object-relation representations that complement VLMs holistic reasoning. We introduce SG-VLM, a modular framework that integrates frozen VLMs with scene graph grounding via prompting and visual localization. Across three benchmarks (NExT-QA, iVQA, ActivityNet-QA) and multiple VLMs (QwenVL, InternVL), SG-VLM improves causal and temporal reasoning and outperforms prior baselines, though gains over strong VLMs are limited. These findings highlight both the promise and current limitations of symbolic grounding, and offer guidance for future hybrid VLM-symbolic approaches in video understanding.

As large language models (LLMs) become embedded in interactive text generation, disclosure of AI as a source depends on people remembering which ideas or texts came from themselves and which were created with AI. We investigate how accurately people remember the source of content when using AI. In a pre-registered experiment, 184 participants generated and elaborated on ideas both unaided and with an LLM-based chatbot. One week later, they were asked to identify the source (noAI vs withAI) of these ideas and texts. Our findings reveal a significant gap in memory: After AI use, the odds of correct attribution dropped, with the steepest decline in mixed human-AI workflows, where either the idea or elaboration was created with AI. We validated our results using a computational model of source memory. Discussing broader implications, we highlight the importance of considering source confusion in the design and use of interactive text generation technologies.

Online AI platforms for creating music from text prompts (AI music), such as Suno and Udio, are now being used by hundreds of thousands of users. Some AI music is appearing in advertising, and even charting, in multiple countries. How are these platforms being used? What subjects are inspiring their users? This article answers these questions for Suno and Udio using a large collection of songs generated by users of these platforms from May to October 2024. Using a combination of state-of-the-art text embedding models, dimensionality reduction and clustering methods, we analyze the prompts, tags and lyrics, and automatically annotate and display the processed data in interactive plots. Our results reveal prominent themes in lyrics, language preference, prompting strategies, as well as peculiar attempts at steering models through the use of metatags. To promote the musicological study of the developing cultural practice of AI-generated music we share our code and resources.

Online medical forums are a rich and underutilized source of insight into patient concerns, especially regarding medication use. Some of the many questions users pose may signal confusion, misuse, or even the early warning signs of a developing health crisis. Detecting these critical questions that may precede severe adverse events or life-threatening complications is vital for timely intervention and improving patient safety. This study introduces a novel annotated dataset of medication-related questions extracted from online forums. Each entry is manually labelled for criticality based on clinical risk factors. We benchmark the performance of six traditional machine learning classifiers using TF-IDF textual representations, alongside three state-of-the-art large language model (LLM)-based classification approaches that leverage deep contextual understanding. Our results highlight the potential of classical and modern methods to support real-time triage and alert systems in digital health spaces. The curated dataset is made publicly available to encourage further research at the intersection of patient-generated data, natural language processing, and early warning systems for critical health events. The dataset and benchmark are available at: https://github.com/Dvora-coder/LLM-Medication-QA-Risk-Classifier-MediGuard.

Customer feedback in industrial forums reflect a rich but underexplored source of insight into real-world product experience. These publicly shared discussions offer an organic view of user expectations, frustrations, and success stories shaped by the specific contexts of use. Yet, harnessing this information for systematic analysis remains challenging due to the unstructured and domain-specific nature of the content. The lack of structure and specialized vocabulary makes it difficult for traditional data analysis techniques to accurately interpret, categorize, and quantify the feedback, thereby limiting its potential to inform product development and support strategies. To address these challenges, this paper presents the User eXperience Perception Insights Dataset (UXPID), a collection of 7130 artificially synthesized and anonymized user feedback branches extracted from a public industrial automation forum. Each JavaScript object notation (JSON) record contains multi-post comments related to specific hardware and software products, enriched with metadata and contextual conversation data. Leveraging a large language model (LLM), each branch is systematically analyzed and annotated for UX insights, user expectations, severity and sentiment ratings, and topic classifications. The UXPID dataset is designed to facilitate research in user requirements, user experience (UX) analysis, and AI-driven feedback processing, particularly where privacy and licensing restrictions limit access to real-world data. UXPID supports the training and evaluation of transformer-based models for tasks such as issue detection, sentiment analysis, and requirements extraction in the context of technical forums.

While foundation models show remarkable progress in language and vision, existing vision-language models (VLMs) still have limited spatial and embodiment understanding. Transferring VLMs to embodied domains reveals fundamental mismatches between modalities, pretraining distributions, and training objectives, leaving action comprehension and generation as a central bottleneck on the path to AGI. We introduce WALL-OSS, an end-to-end embodied foundation model that leverages large-scale multimodal pretraining to achieve (1) embodiment-aware vision-language understanding, (2) strong language-action association, and (3) robust manipulation capability. Our approach employs a tightly coupled architecture and multi-strategies training curriculum that enables Unified Cross-Level CoT-seamlessly unifying instruction reasoning, subgoal decomposition, and fine-grained action synthesis within a single differentiable framework. Our results show that WALL-OSS attains high success on complex long-horizon manipulations, demonstrates strong instruction-following capabilities, complex understanding and reasoning, and outperforms strong baselines, thereby providing a reliable and scalable path from VLMs to embodied foundation models.