Tootfinder

Active Model Selection for Large Language Models
Yavuz Durmazkeser, Patrik Okanovic, Andreas Kirsch, Torsten Hoefler, Nezihe Merve G\"urel
https://arxiv.org/abs/2510.09418 …

Active Model Selection for Large Language Models
We introduce LLM SELECTOR, the first framework for active model selection of Large Language Models (LLMs). Unlike prior evaluation and benchmarking approaches that rely on fully annotated datasets, LLM SELECTOR efficiently identifies the best LLM with limited annotations. In particular, for any given task, LLM SELECTOR adaptively selects a small set of queries to annotate that are most informative about the best model for the task. To further reduce annotation cost, we leverage a judge-based or…

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
Wentian Zhu, Zhen Xiang, Wei Niu, Le Guan
https://arxiv.org/abs/2510.10271 https://

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs). Serving as metadata of training data, these tokens play a crucial role in instructing LLMs to generate coherent and context-aware responses. We demonstrate that special tokens can be exploited to construct four attack primitives, with which malicious users can reliably bypass the internal safety ali…

Experimentell ließ ich über Scribber (https://scriberr.app), ein recht flexibel konfigurierbares Transkriptions-Tool (Docker-isierbar), eine alte über Zoom mitgeschnittene Vorlesungseinheit von mir transkribieren. Das Ergebnis ließ ich Mistral.AI zusammenfassen. Funktionierte sehr präzise und gut, auch mit Personennamen …

A look at data labeling startups like Objectways, whose workers record and annotate repetitive tasks like folding towels to train AI robots for physical tasks (Nilesh Christopher/Los Angeles Times)
https://www.latimes.com/business/story/202…

Inside the race to train AI robots how to act human in the real world
Humanoid robot training is booming around the world. Tech companies are rushing to build the robots for a market projected to reach $38 billion within the next decade.

{annotater}: Annotate package load calls, so we can have an idea of the overall purpose of the libraries we’re loading: #rstats

Aligning Large Language Models via Fully Self-Synthetic Data
Shangjian Yin, Zhepei Wei, Xinyu Zhu, Wei-Lin Chen, Yu Meng
https://arxiv.org/abs/2510.06652 https://

Aligning Large Language Models via Fully Self-Synthetic Data
Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses, often necessitating external reward models or proprietary models like GPT-4 to annotate preference pairs. In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework…

TART: A Comprehensive Tool for Technique-Aware Audio-to-Tab Guitar Transcription
Akshaj Gupta, Andrea Guzman, Anagha Badriprasad, Hwi Joo Park, Upasana Puranik, Robin Netzorg, Jiachen Lian, Gopala Krishna Anumanchipalli
https://arxiv.org/abs/2510.02597

TART: A Comprehensive Tool for Technique-Aware Audio-to-Tab Guitar Transcription
Automatic Music Transcription (AMT) has advanced significantly for the piano, but transcription for the guitar remains limited due to several key challenges. Existing systems fail to detect and annotate expressive techniques (e.g., slides, bends, percussive hits) and incorrectly map notes to the wrong string and fret combination in the generated tablature. Furthermore, prior models are typically trained on small, isolated datasets, limiting their generalizability to real-world guitar recordings…

Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?
Lucas Roberts, Denisa Roberts
https://arxiv.org/abs/2510.00324 https://

Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?
Code search is an important information retrieval application. Benefits of better code search include faster new developer on-boarding, reduced software maintenance, and ease of understanding for large repositories. Despite improvements in search algorithms and search benchmarks, the domain of code search has lagged behind. One reason is the high cost of human annotation for code queries and answers. While humans may annotate search results in general text QA systems, code annotations require s…

This might win the the most unusual #BGP image in a paper award.

TraitSpaces: Towards Interpretable Visual Creativity for Human-AI Co-Creation
Prerna Luthra
https://arxiv.org/abs/2509.24326 https://arxiv.org/pdf/2509.243…

TraitSpaces: Towards Interpretable Visual Creativity for Human-AI Co-Creation
We introduce a psychologically grounded and artist-informed framework for modeling visual creativity across four domains: Inner, Outer, Imaginative, and Moral Worlds. Drawing on interviews with practicing artists and theories from psychology, we define 12 traits that capture affective, symbolic, cultural, and ethical dimensions of creativity.Using 20k artworks from the SemArt dataset, we annotate images with GPT 4.1 using detailed, theory-aligned prompts, and evaluate the learnability of these …

AI academic research hub alphaXiv, which lets users comment on, annotate, and discuss arXiv papers, raised a $7M seed co-led by Menlo Ventures and Haystack (Mike Wheatley/SiliconANGLE)
https://siliconangle.com/2025/11/19/alphaxiv-raises-7m-funding-be…

AlphaXiv raises $7M in funding to become the GitHub of AI research - SiliconANGLE
AlphaXiv raises $7M in funding to become the GitHub of AI research - SiliconANGLE

OpenGVL - Benchmarking Visual Temporal Progress for Data Curation
Pawe{\l} Budzianowski, Emilia Wi\'snios, Gracjan G\'oral, Igor Kulakov, Viktor Petrenko, Krzysztof Walas
https://arxiv.org/abs/2509.17321

OpenGVL - Benchmarking Visual Temporal Progress for Data Curation
Data scarcity remains one of the most limiting factors in driving progress in robotics. However, the amount of available robotics data in the wild is growing exponentially, creating new opportunities for large-scale data utilization. Reliable temporal task completion prediction could help automatically annotate and curate this data at scale. The Generative Value Learning (GVL) approach was recently proposed, leveraging the knowledge embedded in vision-language models (VLMs) to predict task prog…

3D Aware Region Prompted Vision Language Model
An-Chieh Cheng, Yang Fu, Yukang Chen, Zhijian Liu, Xiaolong Li, Subhashree Radhakrishnan, Song Han, Yao Lu, Jan Kautz, Pavlo Molchanov, Hongxu Yin, Xiaolong Wang, Sifei Liu
https://arxiv.org/abs/2509.13317

3D Aware Region Prompted Vision Language Model
We present Spatial Region 3D (SR-3D) aware vision-language model that connects single-view 2D images and multi-view 3D data through a shared visual token space. SR-3D supports flexible region prompting, allowing users to annotate regions with bounding boxes, segmentation masks on any frame, or directly in 3D, without the need for exhaustive multi-frame labeling. We achieve this by enriching 2D visual features with 3D positional embeddings, which allows the 3D model to draw upon strong 2D priors…

Visual Authority and the Rhetoric of Health Misinformation: A Multimodal Analysis of Social Media Videos
Mohammad Reza Zarei, Barbara Stead-Coyle, Michael Christensen, Sarah Everts, Majid Komeili
https://arxiv.org/abs/2509.20724

Visual Authority and the Rhetoric of Health Misinformation: A Multimodal Analysis of Social Media Videos
Short form video platforms are central sites for health advice, where alternative narratives mix useful, misleading, and harmful content. Rather than adjudicating truth, this study examines how credibility is packaged in nutrition and supplement videos by analyzing the intersection of authority signals, narrative techniques, and monetization. We assemble a cross platform corpus of 152 public videos from TikTok, Instagram, and YouTube and annotate each on 26 features spanning visual authority, p…

How People Manage Knowledge in their "Second Brains"- A Case Study with Industry Researchers Using Obsidian
Juliana Jansen Ferreira, Vin\'icius Segura, Joana Gabriela Souza, Joao Henrique Gallas Brasil
https://arxiv.org/abs/2509.20187

How People Manage Knowledge in their "Second Brains"- A Case Study with Industry Researchers Using Obsidian
People face overwhelming information during work activities, necessitating effective organization and management strategies. Even in personal lives, individuals must keep, annotate, organize, and retrieve knowledge from daily routines. The collection of records for future reference is known as a personal knowledge base. Note-taking applications are valuable tools for building and maintaining these bases, often called a ''second brain''. This paper presents a case study on how people build and e…

Importance-Weighted Domain Adaptation for Sound Source Tracking
Bingxiang Zhong, Thomas Dietzen
https://arxiv.org/abs/2509.13215 https://arxiv.org/pdf/2509…

Importance-Weighted Domain Adaptation for Sound Source Tracking
In recent years, deep learning has significantly advanced sound source localization (SSL). However, training such models requires large labeled datasets, and real recordings are costly to annotate in particular if sources move. While synthetic data using simulated room impulse responses (RIRs) and noise offers a practical alternative, models trained on synthetic data suffer from domain shift in real environments. Unsupervised domain adaptation (UDA) can address this by aligning synthetic and re…

Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis
Zhizheng Wang, Yifan Yang, Qiao Jin, Zhiyong Lu
https://arxiv.org/abs/2509.10575 https://

Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis
The gene set analysis (GSA) is a foundational approach for uncovering the molecular functions associated with a group of genes. Recently, LLM-powered methods have emerged to annotate gene sets with biological functions together with coherent explanatory insights. However, existing studies primarily focus on proprietary models, which have been shown to outperform their open-source counterparts despite concerns over cost and data privacy. Furthermore, no research has investigated the application …

Framing Migration: A Computational Analysis of UK Parliamentary Discourse
Vahid Ghafouri, Robert McNeil, Teodor Yankov, Madeleine Sumption, Luc Rocher, Scott A. Hale, Adam Mahdi
https://arxiv.org/abs/2509.14197

Framing Migration: A Computational Analysis of UK Parliamentary Discourse
We present a large-scale computational analysis of migration-related discourse in UK parliamentary debates spanning over 75 years and compare it with US congressional discourse. Using open-weight LLMs, we annotate each statement with high-level stances toward migrants and track the net tone toward migrants across time and political parties. For the UK, we extend this with a semi-automated framework for extracting fine-grained narrative frames to capture nuances of migration discourse. Our findi…

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Zekang Liu, Wei Feng, Fanhua Shang, Lianyu Hu, Jichao Feng, Liqing Gao
https://arxiv.org/abs/2509.14036

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Sign Language Translation (SLT) bridges the communication gap between deaf people and hearing people, where dialogue provides crucial contextual cues to aid in translation. Building on this foundational concept, this paper proposes Question-based Sign Language Translation (QB-SLT), a novel task that explores the efficient integration of dialogue. Unlike gloss (sign language transcription) annotations, dialogue naturally occurs in communication and is easier to annotate. The key challenge lies i…

Prominence-aware automatic speech recognition for conversational speech
Julian Linke, Barbara Schuppler
https://arxiv.org/abs/2509.10116 https://arxiv.org/…

Prominence-aware automatic speech recognition for conversational speech
This paper investigates prominence-aware automatic speech recognition (ASR) by combining prominence detection and speech recognition for conversational Austrian German. First, prominence detectors were developed by fine-tuning wav2vec2 models to classify word-level prominence. The detector was then used to automatically annotate prosodic prominence in a large corpus. Based on those annotations, we trained novel prominence-aware ASR systems that simultaneously transcribe words and their prominen…