A faint ribbon of stars around a distant galaxy has become the first globular cluster stellar stream ever identified beyond the Milky Way. Because the stars trace the galaxy’s gravity, researchers used the stream to estimate how much invisible dark matter surrounds it and how that matter is distribu
Researchers have created a tiny chip that produces a stable “rainbow” of light capable of generating multiple high-frequency signals at once, potentially boosting the speed and capacity of future 6G networks. Its extreme precision could also make it valuable for quantum timing, navigation, radar, an
More screen time during infancy and around the start of school was linked to poorer academic performance and weaker working memory years later. The findings suggest that early childhood may contain particularly sensitive windows when screen habits can have longer-lasting effects.
Researchers have found a way to create a complete 3D image of a molecule’s wavefunction, one of quantum mechanics’ most fundamental yet elusive features. By combining advanced photoelectron measurements with newly designed algorithms, the University of Göttingen team reconstructed the molecular orbi
NASA’s Roman Space Telescope has been cleared for final launch preparations ahead of a targeted August 30 liftoff aboard SpaceX’s Falcon Heavy. The powerful new observatory will probe cosmic expansion, the history of the universe, and distant exoplanets.
The Artemis II crew will receive the Congressional Space Medal of Honor after becoming the first humans in more than 50 years to travel beyond the Moon. Their 10-day Orion mission also carried them farther into space than anyone in history.
arXiv:2608.20344v1 Announce Type: new Abstract: LLM-based "digital twins" aim to simulate how an individual would behavein new environments or respond to novel questions, given some representation of that individual's prior responses. A common approach constructs this representation from survey tra
arXiv:2608.20345v1 Announce Type: new Abstract: Conversational AI systems have become informal mental health support resources for Generation Alpha (Gen Alpha, born 2010-2024), with 13.1% of U.S. adolescents (5.4 million) using generative AI for mental health advice. While these systems, from thera
arXiv:2608.20346v1 Announce Type: new Abstract: Speech systems used in customer-facing applications often require domain-specific language coverage. We present a synthetic Bengali speech dataset for telecom customer-care scenarios. The dataset contains 10,000 audio-text pairs, approximately 26.82 h
arXiv:2608.20347v1 Announce Type: new Abstract: Language models (LMs) often pass behavioral bias evaluations, but it remains unclear whether they no longer represent the underlying associations that give rise to biases, or have merely learned not to express them. In this study, we show that represe
arXiv:2608.20348v1 Announce Type: new Abstract: Electronic health records now routinely exceed 100,000 tokens per patient. Yet large language models exhibit the lost-in-the-middle (LitM) effect: information near the center of a long context is retrieved less reliably than information near the edges
arXiv:2608.20349v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit extreme sensitivity to surface-level prompt variations, in which minor lexical changes can trigger disproportionate performance fluctuations. Moving beyond black-box optimization and coarse-grained templates, we pr
arXiv:2608.20350v1 Announce Type: new Abstract: Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high l
arXiv:2608.20351v1 Announce Type: new Abstract: We ask whether stereotype-loaded queries about culturally marked people leak more personal information from a retrieval-augmented generation (RAG) system than otherwise-equivalent neutral queries. We pre-register a four-culture audit (en-Anglo, es-LAT
arXiv:2608.20353v1 Announce Type: new Abstract: Computational mental health (CMH) classifiers often degrade under distribution shift because human annotators and distant-supervision pipelines reward different linguistic signals. We introduce TSS (Triple-Stream Stress probe), a multi-channel diagnos
arXiv:2608.20355v1 Announce Type: new Abstract: Large Language Model (LLM) agents have demonstrated considerable potential for social simulation, yet struggle to accurately model individual value systems. Most existing methods mechanically stitch survey responses into prompts, which suffer from sem
arXiv:2608.20359v1 Announce Type: new Abstract: Large language models (LLMs) are deployed for increasingly complex tasks involving planning and multi-step decision making, but high-quality performance on these tasks often requires generating long reasoning traces. This is a poor fit for latency-sen
arXiv:2608.20360v1 Announce Type: new Abstract: We study whether tiny decoder-only language models benefit from feed-forward layers that directly multiply learned feature projections. TriPLU, a Trilinear Product Linear Unit, replaces the usual gated FFN branch with a product-only degree-3 branch th
arXiv:2608.20361v1 Announce Type: new Abstract: Automated research-idea generation systems built on large language models (LLMs) share a structural weakness: they reduce ideation to free-text recombination, random paper pairing, or embedding-similarity retrieval. The three approaches fail in the sa
arXiv:2608.20362v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an answer verifier serves as a language-neutral reward function. We show that this assumption fails in multi