The exponential growth of scientific publications poses a formidable challenge for researchers seeking to validate emerging hypotheses or synthesize existing evidence. In this paper, we introduce Valsci, an open-source, self-hostable utility that automates large-batch scientific claim verification using any OpenAI-compatible large language model. Valsci unites retrieval-augmented generation with structured bibliometric scoring and chain-of-thought prompting, enabling users to efficiently search, evaluate, and summarize evidence from the Semantic Scholar database and other academic sources. Unlike conventional standalone LLMs, which often suffer from hallucinations and unreliable citations, Valsci grounds its analyses in verifiable published findings. A guided prompt-flow approach is employed to generate query expansions, retrieve relevant excerpts, and synthesize coherent, evidence-based reports. Preliminary evaluations across claims from the SciFact benchmark dataset reveal that Valsci significantly outperforms base GPT-4o outputs in citation hallucination rate while maintaining a low misclassification rate. The system is highly scalable, processing hundreds of claims per hour through asynchronous parallelization. By providing an open and transparent platform for large-batch literature verification, Valsci substantially lowers the barrier to comprehensive evidence-based reviews and fosters a more reproducible research ecosystem.
暂无摘要，请点击原文查看详情
DeepSeek is a free and self-hostable large language model (LLM) that recently became the most downloaded app across 156 countries. As early academic literature on ChatGPT was predominantly critical of the model, this mini-review is interested in examining how DeepSeek is being evaluated across academic disciplines. The review analyzes available articles with DeepSeek in the title, abstract, or keywords, using the VADER sentiment analysis library. Due to limitations in comparing sentiment across languages, we excluded Chinese literature in our selection. We found that Computer Science, Engineering, and Medicine are the most prominent fields studying DeepSeek, showing an overall positive sentiment. Notably, Computer Science had the highest mean sentiment and the most positive articles. Other fields of interest included Mathematics, Business, and Environmental Science. While there is substantial academic interest in DeepSeek's practicality and performance, discussions on its political or ethical implications are limited in academic literature. In contrast to ChatGPT, where all early literature carried a negative sentiment, DeepSeek literature is mainly positive. This study enhances our understanding of DeepSeek's reception in the scientific community and suggests that further research could explore regional perspectives.
As the amount of genomic data continues to grow, there is an increasing need for systematic ways to organize, explore, compare, analyze and share this data. Despite this, there is a lack of suitable platforms to meet this need. OpenGenomeBrowser is a self-hostable, open-source platform to manage access to genomic data and drastically simplifying comparative genomics analyses. It enables users to interactively generate phylogenetic trees, compare gene loci, browse biochemical pathways, perform gene trait matching, create dot plots, execute BLAST searches, and access the data. It features a flexible user management system, and its modular folder structure enables the organization of genomic data and metadata, and to automate analyses. We tested OpenGenomeBrowser with bacterial, archaeal and yeast genomes. We provide a docker container to make installation and hosting simple. The source code, documentation, tutorials for OpenGenomeBrowser are available at opengenomebrowser.github.io and a demo server is freely accessible at opengenomebrowser.bioinformatics.unibe.ch . To our knowledge, OpenGenomeBrowser is the first self-hostable, database-independent comparative genome browser. It drastically simplifies commonly used bioinformatics workflows and enables convenient as well as fast data exploration.
We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While end-to-end speech-to-speech models may ultimately provide the best latency for voice agents, fully self-hosted end-to-end solutions are not yet available. We evaluate the closest candidate, Qwen3-Omni, across three configurations: its cloud-only DashScope Realtime API achieves $\sim$702ms audio-to-audio latency with streaming, but is not self-hostable; its local vLLM deployment supports only the Thinker (text generation from audio, 516ms), not the Talker (audio synthesis); and its local Transformers deployment runs the full pipeline but at $\sim$146s -- far too slow for realtime. The cascaded streaming pipeline (STT $\rightarrow$ LLM $\rightarrow$ TTS) therefore remains the practical architecture for self-hosted realtime voice agents, and the focus of this tutorial. We build a complete voice agent using Deepgram (streaming STT), vLLM-served LLMs with function calling (streaming text generation), and ElevenLabs (streaming TTS), achieving a measured time-to-first-audio of 755ms (best case 729ms) with full function calling support. We release the full codebase as a 9-chapte
ResearchPilot is an open-source, self-hostable multi-agent system for literature-review assistance. Given a natural-language research question, it retrieves papers from Semantic Scholar and arXiv, extracts structured findings from paper abstracts, synthesizes cross-paper patterns, and drafts a citation-aware related-work section. The system combines FastAPI, Next.js, DSPy, SQLite, and Qdrant in a local-first architecture that supports bring-your-own-key model access and remote-or-local embeddings. This paper describes the system design, typed agent interfaces, persistence and history-search mechanisms, and the engineering tradeoffs involved in building a transparent research assistant. Rather than claiming algorithmic novelty, we present ResearchPilot as a systems contribution and evaluate it through automated tests and end-to-end local runs. We discuss limitations including external API rate limits, abstract-only extraction, incomplete corpus coverage, and the lack of citation verification.
Formal languages are an integral part of modeling and simulation. They allow the distillation of knowledge into concise simulation models amenable to automatic execution, interpretation, and analysis. However, the arguably most humanly accessible means of expressing models is through natural language, which is not easily interpretable by computers. Here, we evaluate how a Large Language Model (LLM) might be used for formalizing natural language into simulation models. Existing studies only explored using very large LLMs, like the commercial GPT models, without fine-tuning model weights. To close this gap, we show how an open-weights, 7B-parameter Mistral model can be fine-tuned to translate natural language descriptions to reaction network models in a domain-specific language, offering a self-hostable, compute-efficient, and memory efficient alternative. To this end, we develop a synthetic data generator to serve as the basis for fine-tuning and evaluation. Our quantitative evaluation shows that our fine-tuned Mistral model can recover the ground truth simulation model in up to 84.5% of cases. In addition, our small-scale user study demonstrates the model's practical potential for
Scientists have uncovered unexpected quantum complexity inside cobalt, a metal long thought to be fully understood。 Advanced measurements revealed a dense network of topological electronic states that remain robust at room temperature。 These states enable extremely fast electron behavior and can be switched or controlled using magnetism
Nicolas Cage was born to play 1930s PI Ben Reilly/The Spider: part Bogart, part Bugs Bunny, 100% Cage-y
A remarkable crystal called molybdenum oxychloride could help make futuristic technologies like smart contact lenses and ultrathin AR glasses a reality。 Scientists have created the first detailed experimental map of its optical properties, revealing the strongest light-bending effect ever measured in a natural material。 The crystal can act either l
A giant planet nearly 700 light-years away has a bizarre daily weather cycle where mineral clouds appear every morning and vanish by nightfall。 Using the James Webb Space Telescope, astronomers discovered that WASP-94A b’s mornings are filled with clouds made of rock-like minerals, while its evenings are surprisingly clear。 The finding gave scienti
Researchers have finally resolved a key problem in a 100-year-old theory of color, showing that the qualities we perceive in colors are intrinsic to the mathematics of color space itself。 The discovery sharpens our understanding of human vision and could lead to more precise color technologies and visualizations
Scientists say moons around rogue planets wandering through the galaxy could remain warm enough for life thanks to tidal heating and hydrogen-rich atmospheres。 These dark, starless worlds may have had stable oceans for billions of years — long enough for complex life to potentially emerge
SpaceX won’t get easy access to billions of dollars from passive investors
A team at the University of Chicago has discovered a surprisingly simple way to create powerful quantum states that are normally difficult to produce。 By making small adjustments to the energy levels of atoms inside an optical cavity, researchers can generate a wide variety of highly entangled states without adding complicated hardware
As traditional chip miniaturization slows, researchers have found a way to pack more computing power into the same space by stacking silicon circuits in multiple layers。 The new process uses ultra-thin silicon membranes and low-temperature manufacturing techniques to overcome a major obstacle that has long blocked the production of true 3D chips
Scientists have developed a solar desalination system that turns seawater into drinking water without creating environmentally damaging brine。 Special laser-textured metal panels use sunlight to evaporate water while automatically moving salt deposits away from the working surface, preventing clogging。 The process was successfully tested with water
A new room-temperature quantum device uses twisted light to entangle photons and electrons, overcoming one of the biggest hurdles in quantum technology。 The breakthrough could pave the way for smaller, cheaper quantum systems with applications ranging from secure communications to future AI and computing platforms
Scientists have uncovered a surprising new way to control superconductivity — the mysterious phenomenon where electricity flows with zero energy loss。 By pairing twisted layers of graphene with a synthetic diamond material, researchers were able to effectively switch superconductivity on and off by tweaking how electrons interact with their surroun
Researchers at EPFL have developed a chip-scale ultrafast laser that performs on par with traditional tabletop femtosecond lasers。 The innovation could make advanced laser technologies far smaller, cheaper, and more accessible for applications ranging from medical diagnostics to atomic clocks