Tootfinder

Google introduces Veo 3.1, with improved audio output and stronger prompt adherence, and rolls out new updates to its AI video editor Flow (The Keyword)
https://blog.google/technology/ai/veo-updates-flow/

Introducing Veo 3.1 and advanced capabilities in Flow
Today, we’re introducing new and enhanced creative capabilities to edit your clips.

Dual Data Scaling for Robust Two-Stage User-Defined Keyword Spotting
Zhiqi Ai, Han Cheng, Yuxin Wang, Shiyi Mu, Shugong Xu, Yongjin Zhou
https://arxiv.org/abs/2510.10740 https:/…

Dual Data Scaling for Robust Two-Stage User-Defined Keyword Spotting
In this paper, we propose DS-KWS, a two-stage framework for robust user-defined keyword spotting. It combines a CTC-based method with a streaming phoneme search module to locate candidate segments, followed by a QbyT-based method with a phoneme matcher module for verification at both the phoneme and utterance levels. To further improve performance, we introduce a dual data scaling strategy: (1) expanding the ASR corpus from 460 to 1,460 hours to strengthen the acoustic model; and (2) leveraging…

Google releases Cell2Sentence-Scale 27B (C2S-Scale), a 27B-parameter foundation model for single-cell analysis built on its Gemma family of open models (The Keyword)
https://blog.google/technology/ai/google-gemma-ai-cancer-therapy-discovery/

How a Gemma model helped discover a new potential cancer therapy pathway
We’re launching a new 27 billion parameter foundation model for single-cell analysis built on the Gemma family of open models.

finde dass python ein "praise" keyword braucht
um exceptions zu lobpreisen 🙏

When even #Firefox ends up in my Mastodon filters. What a timeline. #FuckAI

Unlike keyword search,
semantic search lets you search using natural language.
It looks beyond exact matches to understand the meaning and intent behind your query.
This means it can surface relevant precedents even when they're phrased differently
—something keyword searches often miss.
Semantic search is currently available through an API, but we're already working to bring it to the website—stay tuned!
And don't worry, keyword search isn…

An interview with Nikita Bier, who wants to lure journalists back to X with a rebuilt recommendation algorithm with no keyword suppression or manual downranking (Alex Heath/Sources)
https://sources.news/p/x-wants-its-haters-back

X wants its haters back
Product chief Nikita Bier's message to journalists who left: “We have to earn their trust.”

from my link log —
Unification-free ("keyword") type checking.
https://www.haskellforall.com/2024/02/unification-free-keyword-type-checking.html
saved 2025-09-01

Unification-free ("keyword") type checking
Unification-free ("keyword") type checking From my perspective, one of the biggest open problems in imple...

IKNet: Interpretable Stock Price Prediction via Keyword-Guided Integration of News and Technical Indicators
Jinwoong Kim, Sangjin Park
https://arxiv.org/abs/2510.07661 https://

IKNet: Interpretable Stock Price Prediction via Keyword-Guided Integration of News and Technical Indicators
The increasing influence of unstructured external information, such as news articles, on stock prices has attracted growing attention in financial markets. Despite recent advances, most existing newsbased forecasting models represent all articles using sentiment scores or average embeddings that capture the general tone but fail to provide quantitative, context-aware explanations of the impacts of public sentiment on predictions. To address this limitation, we propose an interpretable keyword-g…

Repository-Aware File Path Retrieval via Fine-Tuned LLMs
Vasudha Yanuganti, Ishaan Puri, Swapnil Chhatre, Mantinder Singh, Ashok Jallepalli, Hritvik Shrivastava, Pradeep Kumar Sharma
https://arxiv.org/abs/2510.08850

Repository-Aware File Path Retrieval via Fine-Tuned LLMs
Modern codebases make it hard for developers and AI coding assistants to find the right source files when answering questions like "How does this feature work?" or "Where was the bug introduced?" Traditional code search (keyword or IR based) often misses semantic context and cross file links, while large language models (LLMs) understand natural language but lack repository specific detail. We present a method for file path retrieval that fine tunes a strong LLM (Qwen3-8B) with QLoRA and Unslot…

Great article on MIDI and a reminder that open protocols won't easily go obsolete once adopted
https://www.sweetwater.com/insync/midi-essenti…

there's something very amusing to me in how the `go` keyword is among the least essential parts of the Go language
it could've been a part of the standard library, like every other language does it, and absolutely nothing of value would be lost
(`select` is a different and much more complicated story)

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Cheng Qian, Zuxin Liu, Shirley Kokane, Akshara Prabhakar, Jielin Qiu, Haolin Chen, Zhiwei Liu, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang
https://arxiv.org/abs/2510.08439

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle on complex tasks. Static escalation rules and keyword heuristics under-utilize this spectrum and fail to adapt across task types. We present xRouter, a tool-calling-based routing system in which a learned router can either answer directly or invoke one or more external models. The router is trained end-to-end with re…

NLP Methods for Detecting Novel LLM Jailbreaks and Keyword Analysis with BERT
John Hawkins, Aditya Pramar, Rodney Beard, Rohitash Chandra
https://arxiv.org/abs/2510.01644 https:…

NLP Methods for Detecting Novel LLM Jailbreaks and Keyword Analysis with BERT
Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into circumventing the safety guardrails put in place to keep responses acceptable to the developer's policies. In this study, we analyse the ability of different machine learning models to distinguish jailbreak prompts from genuine uses, including looking at our abi…

An interview with Nikita Bier, who wants to lure journalists back to X with a rebuilt recommendation algorithm with no keyword suppression or manual downranking (Alex Heath/Sources)
https://sources.news/p/x-wants-its-haters-back

X wants its haters back
Product chief Nikita Bier's message to journalists who left: “We have to earn their trust.”

My latest rabbit hole has been "LLM Routers"
Read and tried all the LLM Router code I could find. None of them were what I was looking for.
So I asked Claude to write what I wanted in Python. Simple and elegant. Based on a keyword search of the prompt, the prompt is sent to the proper model running in ollama. Seems to work.
#Claude #VibeCoding #Ollama #AI #LLM

DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction
Jian Chen, Zhenyan Chen, Xuming Hu, Peilin Zhou, Yining Hua, Han Fang, Cissy Hing Yee Choy, Xinmei Ke, Jingfeng Luo, Zixuan Yuan
https://arxiv.org/abs/2509.14507

DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction
Natural Language to SQL (NL2SQL) provides a new model-centric paradigm that simplifies database access for non-technical users by converting natural language queries into SQL commands. Recent advancements, particularly those integrating Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) reasoning, have made significant strides in enhancing NL2SQL performance. However, challenges such as inaccurate task decomposition and keyword extraction by LLMs remain major bottlenecks, often lea…

Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluation
Yongye Su, Zeya Zhang, Jane Kou, Cheng Ju, Shubhojeet Sarkar, Yamin Wang, Ji Liu, Shengbo Guo
https://arxiv.org/abs/2509.13603

Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluation
Beyond general web-scale search, social network search uniquely enables users to retrieve information and discover potential connections within their social context. We introduce a framework of modernized Facebook Group Scoped Search by blending traditional keyword-based retrieval with embedding-based retrieval (EBR) to improve the search relevance and diversity of search results. Our system integrates semantic retrieval into the existing keyword search pipeline, enabling users to discover more…

Ooer missus
@… https://live.acarsdrama.com/@acarsdrama/115656952528729283

Google DeepMind launches an enhanced Gemini Deep Research agent accessible to developers via its new Interactions API, along with a new DeepSearchQA benchmark (The Keyword)
https://blog.google/technology/developers/deep-research-agent-gemini-api/

Build with Gemini Deep Research
We have reimagined Gemini Deep Research to be more powerful than ever, now accessible to developers via the new Interactions API.

Okay Shutterstock, I get the sentiment, but isn't it too much to suggest "animals in the wild" as a keyword for a photo of human crowd at the presidential rally, eh?

Google says Gemini 3 Pro sets new vision AI benchmark records, including in complex visual reasoning, beating Claude Opus 4.5 and GPT-5.1 in some categories (Rohan Doshi/The Keyword)
https://blog.google/technology/developers/gemini-3-pro-vision/

Gemini 3 Pro: the frontier of vision AI
Build with Gemini 3 Pro, the best model in the world for multimodal capabilities.

MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models
Vijay Govindarajan, Pratik Patel, Sahil Tripathi, Md Azizul Hoque, Gautam Siddharth Kashyap
https://arxiv.org/abs/2509.12591

MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models
Automated Audio Captioning (AAC) generates captions for audio clips but faces challenges due to limited datasets compared to image captioning. To overcome this, we propose the zero-shot AAC system that leverages pre-trained models, eliminating the need for extensive training. Our approach uses a pre-trained audio CLIP model to extract auditory features and generate a structured prompt, which guides a Large Language Model (LLM) in caption generation. Unlike traditional greedy decoding, our metho…

Bibliometric-enhanced Systematic Literature Review of EEG in Education: Learning Concepts, Computational Methods, and Research Opportunities
Adi Wijaya, Said Hasibuan, Wiga Maulana Baihaqi, Rizki Darmawan, Rifkie Primartha, Catur Supriyanto
https://arxiv.org/abs/2509.26083

Bibliometric-enhanced Systematic Literature Review of EEG in Education: Learning Concepts, Computational Methods, and Research Opportunities
Application of electroencephalography (EEG) in educational research has grown substantially, yet a comprehensive integration of methodological frameworks, educational constructs, computational methods, and research gaps remains limited. This study applies a Bibliometric-enhanced Systematic Literature Review (BenSLR) to provide a systematic overview of EEG in education. Literature was extracted from Scopus, screened, and analyzed, with keyword co-occurrence evaluated using VOSviewer and emerging…

Google releases the Gemini 2.5 Computer Use model, built on Gemini 2.5 Pro's capabilities to power agents that can interact with UIs, in preview via the API (The Keyword)
https://blog.google/technology/google-deepmind/gemini-computer-use-model/

Introducing the Gemini 2.5 Computer Use model
Today we are releasing the Gemini 2.5 Computer Use model via the API, which outperforms leading alternatives at browser and mobile tasks.

SandCell: Sandboxing Rust Beyond Unsafe Code
Jialun Zhang, Merve G\"ulmez, Thomas Nyman, Gang Tan
https://arxiv.org/abs/2509.24032 https://arxiv.org/p…

SandCell: Sandboxing Rust Beyond Unsafe Code
Rust is a modern systems programming language that ensures memory safety by enforcing ownership and borrowing rules at compile time. While the unsafe keyword allows programmers to bypass these restrictions, it introduces significant risks. Various approaches for isolating unsafe code to protect safe Rust from vulnerabilities have been proposed, yet these methods provide only fixed isolation boundaries and do not accommodate expressive policies that require sandboxing both safe and unsafe code. …

EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense
Wei Huang, De-Tian Chu, Lin-Yuan Bai, Wei Kang, Hai-Tao Zhang, Bo Li, Zhi-Mo Han, Jing Ge, Hai-Feng Lin
https://arxiv.org/abs/2509.21129

EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense
Modern email spam and phishing attacks have evolved far beyond keyword blacklists or simple heuristics. Adversaries now craft multi-modal campaigns that combine natural-language text with obfuscated URLs, forged headers, and malicious attachments, adapting their strategies within days to bypass filters. Traditional spam detection systems, which rely on static rules or single-modality models, struggle to integrate heterogeneous signals or to continuously adapt, leading to rapid performance degra…

How good are LLMs at Retrieving Documents in a Specific Domain?
Nafis Tanveer Islam, Zhiming Zhao
https://arxiv.org/abs/2509.22658 https://arxiv.org/pdf/25…

How good are LLMs at Retrieving Documents in a Specific Domain?
Classical search engines using indexing methods in data infrastructures primarily allow keyword-based queries to retrieve content. While these indexing-based methods are highly scalable and efficient, due to a lack of an appropriate evaluation dataset and a limited understanding of semantics, they often fail to capture the user's intent and generate incomplete responses during evaluation. This problem also extends to domain-specific search systems that utilize a Knowledge Base (KB) to access da…

Galaxy XR is the first Android XR headset and features Gemini Live that understands your surroundings and lets users interact with apps hands-free (Shahram Izadi/The Keyword)
https://blog.google/products/android/samsung-galaxy-xr/

Introducing Galaxy XR, the first Android XR headset
Galaxy XR is now available today. Here’s what to expect.

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO
Francesco Pappone, Ruggero Marino Lazzaroni, Federico Califano, Niccol\`o Gentile, Roberto Marras
https://arxiv.org/abs/2509.13081

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO
While Large Language Models (LLMs) excel at generating human-like text, aligning their outputs with complex, qualitative goals like pedagogical soundness remains a significant challenge. Standard reinforcement learning techniques often rely on slow and expensive LLM-as-a-judge evaluations or on brittle, keyword-based metrics like ROUGE, which fail to capture the semantic essence of a high-quality explanation. In this work, we introduce a novel approach to reward shaping within the Group Relativ…

Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings
Aysenur Kulunk, Berk Taskin, M. Furkan Eseoglu, H. Bahadir Sahin
https://arxiv.org/abs/2509.15858 https…

Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings
In large scale e-commerce marketplaces, duplicate product listings frequently cause consumer confusion and operational inefficiencies, degrading trust on the platform and increasing costs. Traditional keyword-based search methodologies falter in accurately identifying duplicates due to their reliance on exact textual matches, neglecting semantic similarities inherent in product titles. To address these challenges, we introduce a scalable, multimodal product deduplication designed specifically f…

Google updates Quick Share to work with Apple's AirDrop to make file transfers between iPhones and Android devices easier, starting with the Pixel 10 family (The Keyword)
https://blog.google/products/android/quick-share-airdrop/

Android and iPhone users can now share files, starting with the Pixel 10 family.
Today, we’re introducing a way for Quick Share to work with AirDrop.

Keywords are not always the key: A metadata field analysis for natural language search on open data portals
Lisa-Yao Gan, Arunav Das, Johanna Walker, Elena Simperl
https://arxiv.org/abs/2509.14457

Keywords are not always the key: A metadata field analysis for natural language search on open data portals
Open data portals are essential for providing public access to open datasets. However, their search interfaces typically rely on keyword-based mechanisms and a narrow set of metadata fields. This design makes it difficult for users to find datasets using natural language queries. The problem is worsened by metadata that is often incomplete or inconsistent, especially when users lack familiarity with domain-specific terminology. In this paper, we examine how individual metadata fields affect the…