# zero-shot Published articles for zero-shot. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Understanding W8A8 INT8 LLM quantization: Accuracy and performance results DevFeed: [Understanding W8A8 INT8 LLM quantization: Accuracy and performance results]() Original publisher: [Read original article]() Author: Sana Fayyaz Published: 2026-09-14T13:01:43Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Large Language Model](), [quantization](), [llama](), [Compression](), [Benchmark](), [dataset](), [Algorithms]() Tags: [ai-inference](), [artificial-intelligence](), [benchmark](), [benchmarks](), [compression](), [evaluation](), [hardware](), [llama](), [llm](), [model](), [models](), [performance](), [quantization](), [reasoning](), [zero-shot]() ### AI overview The article evaluates W8A8 INT8 quantization of a Llama 3.1 8B Instruct model. It describes reducing the model from 14.9 GB to 8.0 GB with SmoothQuant and GPTQ, then compares the base and compressed models on four benchmarks to assess accuracy and performance. ### Source excerpt In Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy, we compressed a Llama 3.1 8B Instruct model from 14.9 GB to 8.0 GB using 8-bit integer (INT8) W8A8 quantization with SmoothQuant and Generative Pre-trained Transformer Quantization (GPTQ). The post Understanding W8A8 INT8 LLM quantization: Accuracy and performance results appeared first on Red Hat Developer. ## From zero-shot forecast to purchase order with Amazon Bedrock AgentCore DevFeed: [From zero-shot forecast to purchase order with Amazon Bedrock AgentCore]() Original publisher: [Read original article]() Author: Hyunsoo Kim, Ph.D. Published: 2026-09-11T14:08:01Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots](), [Training AI Models](), [SDKs]() Tags: [advanced-300](), [agents](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [automation](), [best-practices](), [orchestration](), [strands-agents](), [time-series](), [training](), [zero-shot]() ### AI overview An architecture article on using Amazon Chronos2 zero-shot forecasting and Bedrock AgentCore multi-agent orchestration to turn demand forecasts into validated purchase orders without per-product model training. ### Source excerpt Combine zero-shot forecasting with Amazon Chronos2 and multi-agent orchestration on Amazon Bedrock AgentCore to turn demand forecasts into validated purchase orders. No per-product model training, with business rules, auditability, and cost that scales to zero. ## IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license DevFeed: [IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license]() Original publisher: [Read original article]() Author: Roman Vaculin; Wesley M Gifford; Jiri Navratil; Chandra Reddy; Ayhan Sebin Published: 2026-09-09T15:36:24Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [foundation-models](), [Temporal data](), [releases](), [benchmarking](), [Open Source Models & Datasets](), [Inference]() Tags: [apache](), [benchmarking](), [foundation-models](), [ibm](), [inference](), [model-architecture](), [open-source](), [releases](), [time-series](), [zero-shot]() ### AI overview IBM released Granite Time Series PatchTST-FM-r2, a roughly 385M-parameter time-series foundation model for zero-shot forecasting. The article covers its architecture, probabilistic forecasting, missing-value imputation, benchmark results, licensing, and available reproducibility resources. ### Source excerpt Time-series foundation models are changing the way forecasting systems are built. Instead of training and maintaining a separate model for every dataset, users can use a pretrained model and generate forecasts zero-shot. IBM has released Granite Time Series PatchTST-FM-r2, the latest model in the Granite TSFM family (github, blog). ## TimesFM-3: A zero-shot foundation model for multivariate forecasting DevFeed: [TimesFM-3: A zero-shot foundation model for multivariate forecasting]() Original publisher: [Read original article]() Published: 2026-08-31T17:19:40Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [foundation-models](), [Time Series](), [Google](), [datasets](), [Transformer architecture](), [Fine-tuning](), [generalization in machine learning]() Tags: [data-management](), [features](), [fine-tuning](), [foundation-models](), [google](), [machine-intelligence](), [model](), [product](), [time-series](), [transformer-architecture](), [zero-shot]() ### AI overview Google Research introduces TimesFM-3, a 330-million-parameter time-series foundation model designed for accurate multivariate forecasting in a single forward pass. Pre-trained on more than one trillion real-world and synthetic time points, it jointly models coevolving series and external covariates in zero-shot settings without task-specific fine-tuning. ### Source excerpt Data Management ## Beyond VLAs: How World Action Models Reshape Robot Manipulation DevFeed: [Beyond VLAs: How World Action Models Reshape Robot Manipulation]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-08-04T16:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Robotics](), [World models](), [vlm](), [post-training](), [Cosmos](), [Nvidia](), [NVIDIA Research]() Tags: [agentic-ai-generative-ai](), [cosmos](), [featured](), [nvidia](), [nvidia-research](), [physical-ai](), [post-training](), [robot-manipulation](), [robotics](), [simulation-modeling-design](), [thor](), [vlm](), [world-model](), [zero-shot]() ### AI overview The article explains how World Action Models (WAMs) use video world models as backbones for robot policies, addressing the physical-generalization limitations of vision-language-action models. It discusses post-training WAMs into specialized policies and presents NVIDIA Cosmos 3 as a foundation for building them. ### Source excerpt A central challenge in robotics is building policies that generalize beyond the demonstrations they're trained on. A policy that succeeds in a training scene... ## Introducing TabFM: A zero-shot foundation model for tabular data DevFeed: [Introducing TabFM: A zero-shot foundation model for tabular data]() Original publisher: [Read original article]() Published: 2026-06-30T10:26:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [foundation-models](), [datasets](), [Machine learning](), [Google](), [Feature Engineering](), [Hyperparameter optimization](), [Language models](), [BigQuery](), [GitHub](), [hugging face](), [AI Inference]() Tags: [bigquery](), [classification](), [data](), [data-management](), [feature-engineering](), [github](), [google](), [hugging-face](), [hyperparameter-optimization](), [machine-intelligence](), [model](), [product](), [zero-shot]() ### AI overview Google Research introduces TabFM, a zero-shot foundation model for tabular-data classification and regression. It frames prediction as in-context learning, reducing the need for dataset-specific training, hyperparameter optimization, and feature engineering, with availability through Hugging Face, GitHub, and BigQuery. ### Source excerpt Data Management ## Re-autoresearching MSMARCO BM25, on Vespa DevFeed: [Re-autoresearching MSMARCO BM25, on Vespa]() Original publisher: [Read original article]() Author: andreer thomas Published: 2026-05-29T00:00:00Z Content type: article Language: en Sources: [Vespa Blog]() Topics: [Benchmark](), [dataset](), [Python](), [Large Language Model](), [generalization in machine learning](), [pandas](), [Google Search]() Tags: [benchmark](), [bm25](), [dataset](), [evaluation](), [experiment](), [google-search](), [information-retrieval](), [openai](), [pandas](), [python](), [ranking](), [retrieval](), [zero-shot]() ### AI overview This article reproduces an MSMARCO BM25 autoresearch experiment in Vespa. It compares LLM-driven Python reranking with an approach restricted to existing Vespa rank features and reports a comparable improvement on a 650,000-passage subset, with better generalization to the full dataset. ### Source excerpt BM25 is having a moment. We reproduce Doug Turnbull's MSMARCO autoresearch experiment in Vespa and get a comparable MRR@10 lift from existing rank features -- with twice the generalization to full MSMARCO. ## Mistral AI Releases Voxtral TTS, a Multilingual Text-to-Speech Model DevFeed: [Mistral AI Releases Voxtral TTS, a Multilingual Text-to-Speech Model]() Original publisher: [Read original article]() Published: 2026-03-23T16:00:00Z Content type: release Language: en Sources: [Mistral AI Blog]() Topics: [voice ai](), [Artificial Intelligence](), [API](), [Low Latency](), [User experience (UX)]() Tags: [agents](), [ai-agents](), [api](), [audio](), [customization](), [latency](), [low-latency](), [quality](), [speech](), [text-to-speech](), [voice-ai](), [zero-shot]() ### AI overview Mistral AI has released Voxtral TTS, a 4B-parameter text-to-speech model designed to generate realistic, emotionally expressive speech in nine languages. It emphasizes low latency, contextual understanding, speaker modeling, and zero-shot cross-lingual voice adaptation for enterprise voice workflows and AI agents. The model is available through an API and Mistral Studio. ### Source excerpt Voxtral TTS: A frontier, open-weights text-to-speech model that's fast, instantly adaptable, and produces lifelike speech for voice agents. ## Introducing RTEB: A New Standard for Retrieval Evaluation DevFeed: [Introducing RTEB: A New Standard for Retrieval Evaluation]() Original publisher: [Read original article]() Author: Frank Liu; Kenneth Enevoldsen; Solomatin Roman; Isaac Chung; Tom Aarsen; Fődi, Zoltán Published: 2025-10-01T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Benchmark](), [LLM evaluation / benchmarking](), [Retrieval Augmented Generation (RAG)](), [generalization in machine learning](), [recommendation systems]() Tags: [artificial-intelligence](), [benchmark](), [benchmarks](), [community](), [datasets](), [developers](), [embedding](), [evaluation](), [models](), [nlp](), [open](), [performance](), [rag](), [recommendation-systems](), [research](), [retrieval](), [search](), [zero-shot]() ### AI overview Hugging Face introduces the beta Retrieval Embedding Benchmark (RTEB), designed to evaluate the retrieval accuracy and generalization of embedding models in real-world applications. It combines open and private datasets to provide a fairer, more transparent, application-focused evaluation standard. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## SigLIP 2: A better multilingual vision language encoder DevFeed: [SigLIP 2: A better multilingual vision language encoder]() Original publisher: [Read original article]() Author: Aritra Roy Gosthipaty; merve; Pavel Iakubovskii Published: 2025-02-21T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Artificial Intelligence](), [computer-use](), [object-detection](), [Google AI](), [Open Source]() Tags: [artificial-intelligence](), [multimodal](), [object-detection](), [open-source](), [performance](), [retrieval](), [train](), [training](), [vision](), [vlms](), [zero-shot]() ### AI overview Google's SigLIP 2 is a multilingual vision-language encoder family that extends SigLIP's sigmoid-loss training with additional objectives for semantic understanding, localization, and dense visual features. The models improve on SigLIP across scales and core capabilities including zero-shot classification, image-text retrieval, and visual representation transfer, with a dynamic-resolution variant for resolution- and aspect-ratio-sensitive tasks. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Introducing the Open FinLLM Leaderboard DevFeed: [Introducing the Open FinLLM Leaderboard]() Original publisher: [Read original article]() Author: Xie; Jimin Huang; Sophia Ananiadou; Xiao-Yang Liu Yanglet; Alejandro Lopez-Lira; Wang; ldruth; Ruoyu Xiang; chenzhengyu; Yangyang Yu Published: 2024-10-04T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Finance](), [LLMs](), [Human-AI evaluation](), [Natural language processing](), [Open Source]() Tags: [artificial-intelligence](), [benchmarks](), [collaboration](), [community](), [evaluation](), [finance](), [financial-sector](), [fine-tuning](), [leaderboard](), [open-source](), [qa](), [testing](), [text-generation](), [zero-shot]() ### AI overview The article introduces the Open FinLLM Leaderboard, a specialized evaluation framework for financial language models. It evaluates models on finance-specific tasks such as information extraction, sentiment analysis, credit risk scoring, stock forecasting, question answering, text generation, and decision-making, using real-world datasets and metrics including Accuracy, F1 Score, ROUGE, and MCC. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning? DevFeed: [LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?]() Original publisher: [Read original article]() Author: Dana Aubakirova; Andres Marafioti Published: 2024-07-25T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [LLMs](), [datasets](), [Benchmark](), [Artificial Intelligence]() Tags: [benchmark](), [community](), [dataset](), [evaluation](), [fine-tuning](), [llms](), [metrics](), [research](), [synthetic-data](), [vlm](), [vlms](), [vqa](), [zero-shot]() ### AI overview This article examines zero-shot visual question answering evaluation on the synthetic Docmatix dataset using large language models and vision-language models. It explains why traditional VQA Accuracy can undervalue semantically correct answers in out-of-distribution settings and discusses the trade-off between fine-tuning models and developing metrics that better reflect human judgment. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Accelerating Protein Language Model ProtST on Intel Gaudi 2 DevFeed: [Accelerating Protein Language Model ProtST on Intel Gaudi 2]() Original publisher: [Read original article]() Author: Julien Simon; Jiqing.Feng; Santiago Miret; Xinyu Yuan; Yi Wang; Matrix Yao; Minghao Xu; Ke Ding Published: 2024-07-03T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [Large Language Model](), [Inference](), [Inference Performance](), [Fine-tuning](), [intel](), [Open Source](), [AI, ML & Data Engineering]() Tags: [accelerators](), [artificial-intelligence](), [batch](), [datasets](), [fine-tuning](), [hugging-face](), [inference](), [inference-performance](), [intel](), [language-models](), [llm](), [model](), [nvidia](), [optimum](), [partnerships](), [pcie](), [precision](), [transformers](), [zero-shot]() ### AI overview This tutorial explains how to run inference and fine-tune ProtST, a multimodal protein language model, using Intel Gaudi 2 accelerators and the Optimum for Intel Gaudi open-source library. It compares ProtST inference on NVIDIA A100 and Gaudi 2, reporting identical accuracy and 1.76x faster inference on Gaudi 2. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Vision Language Models Explained DevFeed: [Vision Language Models Explained]() Original publisher: [Read original article]() Author: merve; Edward Beeching Published: 2024-04-11T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [vlm](), [multimodal](), [hugging face](), [trl](), [Inference](), [Machine learning]() Tags: [blog-post](), [guide](), [hallucinations](), [hugging-face](), [inference](), [leaderboard](), [models](), [multimodal](), [trl](), [vision](), [vlm](), [zero-shot]() ### AI overview An introduction to vision language models that explains their architecture, capabilities, use cases, model selection, inference, and fine-tuning with trl. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Pollen-Vision: Unified interface for Zero-Shot vision models in robotics DevFeed: [Pollen-Vision: Unified interface for Zero-Shot vision models in robotics]() Original publisher: [Read original article]() Author: Antoine Pirrone; Simon Le Goff; Rouanet; Simon Revelly Published: 2024-03-25T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Library](), [object-detection](), [Robotics](), [Open Source](), [reachy](), [real-time](), [3D](), [Google](), [Meta]() Tags: [3d](), [artificial-intelligence](), [image-tagging](), [object-detection](), [open-source](), [reachy](), [real-time](), [robotic-manipulation](), [robotics](), [robots](), [tools](), [training](), [vision](), [zero-shot]() ### AI overview Pollen-Vision is an open-source library from the Pollen Robotics team that provides a modular interface for zero-shot vision models in robotics. Its initial release combines models for 3D object detection and segmentation, producing object coordinates to support autonomous grasping and other basic manipulation tasks without additional training. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## A clustering-based approach to create deep learning datasets in a day DevFeed: [A clustering-based approach to create deep learning datasets in a day]() Original publisher: [Read original article]() Author: Roland Meertens Published: 2023-11-28T17:33:30Z Content type: article Language: en Sources: [Bumble Tech]() Topics: [dataset](), [Computer vision](), [Deep learning](), [foundation-models](), [Fine-tuning](), [Inference]() Tags: [clustering](), [computer-vision](), [data-science](), [dataset](), [deep-learning](), [fine-tuning](), [inference](), [machine-learning](), [models](), [retrieval](), [zero-shot]() ### AI overview The article discusses the cost and time involved in creating labeled computer vision datasets. It considers zero-shot learning and foundational models such as GPT-3 and CLIP for data retrieval, while noting that some use cases still require fine-tuning on task-specific data. ### Source excerpt A clustering-based approach to create deep learning datasets in a day Introduction Understanding what's happening in an image is both an important task, as well as a costly one. In the last few years, the field of computer vision has greatly accelerated due to the advances in neural networks. At Bumble Inc., we see potential value in computer vision for a variety of use cases, such as improving the safety of our platform and providing our members with a better user experience. The most common way to train these neural networks is by showing it many images with the corresponding label. Unfortunately, this can be a costly task. Not only does one need to build and train the model, one also wants to do hyperparameter search over multiple configurations of possible networks, and -- of course -- one needs to find or build a dataset suitable for the task at hand. Building the dataset is both the most important task, as well as a very time consuming one. Gathering data, setting up labelling requirements, and of course the labelling itself all take a lot of time and money. This normally leads to trade-offs, by choosing either to build only a small dataset, or by trying to fit existing datasets into your specific use-case. One alternative is of course to not build a dataset at all, to instead use zero-shot learning for your use case. I argued in the past that this is unreasonably effective, and allows you to test your use-case before even training a model. When using zero-shot learning one predicts labels without explicitly training on the classes you are trying to learn. One example of this can be achieved by using the CLIP model, which is trained to have a strong association between text and images. By looking at the distance between the description of your class and the image you can run inference without training anything. However, there are some use cases where we need the strongest possible model by fine-tuning it to our specific data. Using foundational models for data s ## Implicit Product Tagging DevFeed: [Implicit Product Tagging]() Original publisher: [Read original article]() Author: Alessandro Joabar Published: 2023-06-29T06:00:00Z Content type: tutorial Language: en Sources: [Square Corner Blog](), [Square Corner Blog RSS Feed]() Topics: [data](), [datasets](), [Transformers]() Tags: [data](), [data-science](), [dataset](), [how-to](), [install](), [model](), [packages](), [train](), [transformers](), [zero-shot]() ### AI overview This tutorial explains implicit product tagging: using zero-shot classification transformers to assign labels when explicit labels are unavailable. It uses product names and candidate labels to build a dataset, with examples involving fraud, alcohol sales, and coffee classification. ### Source excerpt How To Label With Data You Don't Have