---
title: "Machine Learning"
description: "622 posts about Machine Learning, summarised, each linking to the original."
---

# Machine Learning
> 622 posts about Machine Learning, summarised, each linking to the original.

## Articles

### [DeepMath: A lightweight math reasoning Agent with smolagents](https://yomu.fyi/post/deepmath-a-lightweight-math-reasoning-agent-with-smolagents.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Daniel Fleischer, Moshe Berchansky, Moshe Wasserblat
- Published: Dec 4, 2025
- Type: Problem & solution

Mathematical reasoning in large language models often suffers from lengthy chain-of-thought traces and frequent arithmetic mistakes. To address these issues, DeepMath pairs a Qwen3-4B Thinking base model with a sandboxed Python execution environment built using the smolagents library and vLLM backend. The system offloads deterministic calculations by emitting concise Python snippets, executing them safely with restricted module imports and no network access, and folding returned values back into the context. Training utilizes Group Relative Policy Optimization on the Tool-Integrated Reasoning subset of OpenMathReasoning with temperature scheduling and length constraints. Across benchmarks including MATH500, AIME, HMMT, and HLE, DeepMath reduces output token lengths by up to 66% while increasing overall problem-solving accuracy.


### [We Got Claude to Fine-Tune an Open Source LLM](https://yomu.fyi/post/we-got-claude-to-fine-tune-an-open-source-llm.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: ben burtenshaw, shaun smith
- Published: Dec 4, 2025
- Type: Tutorial

Hugging Face Skills equips coding agents like Claude Code, OpenAI Codex, and Google's Gemini CLI to manage end-to-end language model fine-tuning. Using the hf-llm-trainer skill, an agent validates dataset formats, selects cloud hardware, configures authentication, and submits jobs to Hugging Face Jobs. Supported techniques include Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Group Relative Policy Optimization (GRPO) for models ranging across various parameter sizes. The integration incorporates Trackio for real-time monitoring and automates LoRA configuration for larger models. Once training completes, the agent pushes artifacts to the Hugging Face Hub and can convert models to GGUF format for local execution.


### [Transformers v5: Simple model definitions powering the AI ecosystem](https://yomu.fyi/post/transformers-v5-simple-model-definitions-powering-the-ai-ecosystem.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Lysandre, Arthur Zucker, Cyril Vallez, Vaibhav Srivastav
- Published: Dec 1, 2025
- Type: Announcement

Transformers v5.0.0rc-0 introduces major architectural updates focused on simplicity, training, inference, and ecosystem interoperability across modern AI workflows. The release adopts a modular modeling approach and centralizes attention implementations into a unified AttentionInterface abstraction to reduce contribution and code review overhead. Support for Flax and TensorFlow is officially sunset in favor of focusing on PyTorch as the primary backend, while tokenization is standardized around the tokenizers library. For execution workloads, v5 adds native continuous batching, paged attention mechanisms, and a dedicated transformers serve OpenAI-compatible serving system. Finally, weight loading is refactored to make low-precision quantization a first-class citizen alongside broad interoperability with formats such as GGUF, MLX, and TorchAO.


### [Reducing experiment duration with predicted control variates](https://yomu.fyi/post/reducing-experiment-duration-with-predicted-control-variates.md)
- Company: [Etsy](https://yomu.fyi/company/etsy.md)
- Author: Kelly McManus
- Published: Nov 25, 2025
- Type: Explainer

Etsy describes how its experimentation platform evolved from CUPED to CUPAC to shorten the time needed to reach statistically powered results. CUPED uses pre-experiment visitor data as covariates in linear regression, while CUPAC first uses a nonlinear model to predict the outcome and then uses that prediction in the variance-reduction correction. Etsy trained and tuned LightGBM models on more than 100 pre-experiment features in Vertex AI, generating predictions through parallel Dataflow jobs and applying the correction with Spark within an Airflow-orchestrated pipeline. CUPED reduced variance by 7% on average, whereas CUPAC achieved 27%, shortening average experiment duration by almost three additional days, although results ranged from 2% to 77% depending on the metric and experiment; Etsy is balancing CUPAC’s impact against its training and maintenance costs.


### [Diffusers welcomes FLUX-2](https://yomu.fyi/post/diffusers-welcomes-flux-2.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: YiYi Xu, Daniel Gu, Sayak Paul, Alvaro Somoza, Dhruv Nair, Aritra Roy Gosthipaty, Linoy Tsaban, Apolinário from multimodal AI art
- Published: Nov 25, 2025
- Type: Tutorial

Diffusers introduces support for FLUX-2 models through the Flux2Pipeline and Flux2Transformer2DModel classes. Running the 4-bit quantized checkpoint diffusers/FLUX.2-dev-bnb-4bit requires loading Mistral3ForConditionalGeneration as the text encoder and the transformer in bfloat16 precision with CPU offloading enabled. During image generation with a prompt and 50 inference steps, the pipeline encodes text embeddings through the Mistral 3 model before executing diffusion operations. However, executing the pipeline on a GPU with 14.56 GiB capacity triggers a CUDA OutOfMemoryError during 4-bit dequantization inside bitsandbytes matrix multiplication operations. Additionally, the execution logs warn that Flax classes are deprecated in Diffusers and will be removed in version 1.0.0.


### [Continuous batching from first principles](https://yomu.fyi/post/continuous-batching-from-first-principles.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Rémi Ouazan Reboul, Arthur Zucker, Luc Georges
- Published: Nov 25, 2025
- Type: Explainer

Large language model serving requires running expensive next-token generation across multiple concurrent user requests. Traditional batching approaches introduce severe padding inefficiencies when mixing variable-length prompts and different generation phases, especially under static shape constraints like CUDA graphs. Continuous batching resolves these inefficiencies by combining key-value caching, chunked prefill, ragged batching, and dynamic request scheduling. Ragged batching eliminates the traditional batch axis by concatenating token sequences into a single tensor and using boolean attention masks to isolate independent sequences. By dynamically removing completed prompts and packing decoding tokens alongside chunked prefill tokens up to a hardware memory budget, serving systems maintain high hardware utilization and throughput.


### [OVHcloud on Hugging Face Inference Providers 🔥](https://yomu.fyi/post/ovhcloud-on-hugging-face-inference-providers.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Gilles Closset, Fabien Ric, Elias Tourneux
- Published: Nov 24, 2025
- Type: Announcement

OVHcloud is now integrated as a supported Inference Provider on the Hugging Face Hub, expanding serverless inference options across model pages and client SDKs. The integration enables access to open-weight models, including gpt-oss, Qwen3, DeepSeek R1, and Llama, using European infrastructure with pay-per-token pricing starting at €0.04 per million tokens. Developers can connect via Python and JavaScript SDKs using either direct custom API keys or automatic routing through Hugging Face tokens. The service supports structured outputs, function calling, multimodal workflows, and embedding models while providing sub-200ms first-token response times. Calls routed through Hugging Face pass through standard provider pricing without markups, and PRO tier subscribers receive monthly inference credits.


### [20x Faster TRL Fine-tuning with RapidFire AI](https://yomu.fyi/post/20x-faster-trl-fine-tuning-with-rapidfire-ai.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Kamran Bigdely, Arun Kumar, Quentin Gallouédec
- Published: Nov 21, 2025
- Type: Announcement

Hugging Face TRL now officially integrates with RapidFire AI to accelerate LLM fine-tuning and post-training experimentation through concurrent configuration evaluation. Instead of executing training configurations sequentially, the platform shards datasets into discrete chunks and cycles multiple model configurations across GPUs at chunk boundaries. The runtime handles automatic checkpointing via a shared-memory-based adapter and model spilling mechanism to maintain consistent training state. Experimenters can monitor live metrics on an MLflow-based dashboard and use Interactive Control Ops to stop underperforming runs or clone and warm-start promising configurations mid-flight. Benchmark results on NVIDIA A100 GPUs demonstrate experimentation speedups ranging from 15x to 20x over sequential runs when training TinyLlama-1.1B and Llama-3.2-1B models.


### [Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks](https://yomu.fyi/post/open-asr-leaderboard-trends-and-insights-with-new-multilingual-long-fo.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Eric Bezzam, Steven Zheng, Eustache Le Bihan, Vaibhav Srivastav
- Published: Nov 21, 2025
- Type: Benchmark

The Open ASR Leaderboard expanded its evaluation framework by introducing dedicated multilingual and long-form transcription tracks across eleven datasets. Benchmarking more than sixty open- and closed-source models from eighteen organizations revealed clear operational trade-offs between accuracy and inference speed. Systems combining Conformer encoders with large language model decoders achieved the lowest word error rates in short-form English speech recognition. In contrast, connectionist temporal classification and token-and-duration transducer decoders yielded tenfold to hundredfold improvements in throughput with only slight accuracy penalties. While closed-source commercial systems maintained performance leads in long-form audio transcription, specialized single-language models consistently outperformed generalized systems supporting hundreds of languages.


### [Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models](https://yomu.fyi/post/apriel-h1-the-surprising-key-to-distilling-efficient-reasoning-models.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Torsten Scholak, Oleksiy Ostapenko, Raymond Li, Luke Kumar, Joel Lamy-Poirier
- Published: Nov 19, 2025
- Type: Problem & solution

Retrofitting efficiency into existing large language models often fails when naive distillation disrupts complex multi-step reasoning mechanisms. The Apriel-H1 project addresses this challenge by converting a 15B full-attention reasoning model into a Mamba hybrid using targeted distillation on high-quality SFT reasoning traces rather than diffuse pretraining data. Built on the open-source Fast-LLM framework, the process applies reverse KL divergence alongside a staged layer replacement strategy combining Leave-One-Out analysis and dynamic loss evaluations. Across fifty total blocks, replacing thirty attention layers with Mamba mixers yielded the flagship Apriel-H1-15b-Thinker-SFT checkpoint. This configuration achieved a 2.1x throughput increase with minimal benchmark degradation after 76.8B training tokens.


### [Easily Build and Share ROCm Kernels with Hugging Face](https://yomu.fyi/post/easily-build-and-share-rocm-kernels-with-hugging-face.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Abdennacer Badaoui, Daniel Huang, colorswind, Zesen Liu
- Published: Nov 17, 2025
- Type: Tutorial

Compiling custom deep learning GPU kernels across architectures often leads to complex build flag management, compiler errors, and ABI issues. Hugging Face's kernels library and kernel-builder streamline this workflow by supporting backends such as ROCm, CUDA, Metal, and XPU. Using the RadeonFlow FP8 block-wise GEMM kernel optimized for the AMD Instinct MI300X GPU as an example, developers organize files into specific headers and HIP implementations. The build is configured via a build.toml manifest and flake.nix to ensure reproducible compilation across supported PyTorch and ROCm versions. Artifacts can then be pushed to the Hugging Face Hub, allowing users to load and execute custom operators directly via get\_kernel without traditional installation steps.


### [Join the AMD Open Robotics Hackathon](https://yomu.fyi/post/join-the-amd-open-robotics-hackathon.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Eric Ma, Guruprasad MP
- Published: Nov 13, 2025
- Type: Announcement

AMD, Hugging Face, and Data Monsters announced the AMD Open Robotics Hackathon, an in-person competition scheduled for Tokyo and Paris in December 2025. Participating teams of up to four adults will compete over three days across two core missions. The first mission covers an instructor-led session on configuring the LeRobot development environment using AMD AI solutions. During the second mission, teams spend two days developing a freestyle project to address a real-world problem using LeRobot. Participants receive access to SO-101 robotics kits, AMD Ryzen AI laptops, and AMD Instinct MI300X GPUs via AMD Developer Cloud, with prizes awarded to the top seven teams in each city based on creativity, difficulty, ease-of-use, and practicality.


### [Building for an Open Future - our new partnership with Google Cloud](https://yomu.fyi/post/building-for-an-open-future-our-new-partnership-with-google-cloud.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Jeff Boudier, Simon Pagezy
- Published: Nov 13, 2025
- Type: Announcement

Hugging Face and Google Cloud announced an expanded strategic partnership designed to streamline the deployment and management of open models on Google Cloud infrastructure. Prompted by a tenfold increase in Hugging Face usage on Google Cloud over three years, the collaboration introduces a joint CDN Gateway using Hugging Face Xet technology to cache models and datasets directly on Google Cloud. This caching mechanism aims to shorten download times, strengthen model supply chain resilience, and accelerate time-to-first-token across Vertex AI, Google Kubernetes Engine, Cloud Run, and Compute Engine virtual machines. Hugging Face plans to integrate native library support for Google Cloud TPUs, lower instance prices on Inference Endpoints, and enhance Hub security scanning via VirusTotal, Google Threat Intelligence, and Mandiant.


### [Building world-class product search at Shopify: Where C++ excellence meets ML innovation](https://yomu.fyi/post/building-world-class-product-search-at-shopify-where-c-excellence-meet.md)
- Company: [Shopify](https://yomu.fyi/company/shopify.md)
- Author: 2023-10-18
- Published: Nov 12, 2025
- Type: Problem & solution

Shopify describes a product-search stack built for multi-tenant commerce, where real-time indexing, retrieval, ranking, experimentation, and merchant controls must operate at global scale. Commerce ranking combines classical information retrieval with transformers, neural rankers, LightGBM, Catboost, and signals such as relevance, purchase popularity, brand trust, and navigational intent, while supporting privacy, multi-language, and accessibility requirements. RankFlow, a Python-like domain-specific language, lets data scientists change ranking logic without C++ expertise, while TurboDSL compiles and executes it with type safety, vectorized operations, cache optimization, predictable latency, and efficient memory use. The team first shipped SimScorerDSL in C++, then built TurboDSL without changing the DSL syntax, enabling continued experimentation during the transition. TurboDSL achieved a 48% speedup in ranking feature computation, and automated pull-request analysis compares component timings, statistical significance within a ±2% tolerance, and side-by-side results to detect performance or accuracy regressions.


### [Improving agent with semantic search](https://yomu.fyi/post/improving-agent-with-semantic-search.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Stefan Heule, Emily Jia & Naman Jain
- Published: Nov 6, 2025
- Type: Benchmark

Cursor describes semantic search as a complement to grep for helping coding agents locate relevant code in large codebases. Its evaluation used Cursor Context Bench across widely used models, comparing tool sets with and without semantic search, and found an average 12.5% accuracy improvement, with gains ranging from 6.5% to 23.5%. In an online A/B test, semantic search increased code retention by 0.3% overall and 2.6% on codebases with at least 1,000 files, while its absence produced a 2.2% increase in dissatisfied follow-up requests. The retrieval system uses a custom embedding model trained from agent session traces, with an LLM ranking helpful content and training aligning embedding similarity scores to those rankings. The conclusion is that combining semantic search with grep produces the best outcomes, especially for large codebases.


### [How we built a custom vision LLM to improve document processing at Grab](https://yomu.fyi/post/how-we-built-a-custom-vision-llm-to-improve-document-processing-at-gra.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Jia Chen
- Published: Nov 4, 2025
- Type: Problem & solution

Grab developed a specialized Vision LLM for extracting text and key information from Southeast Asian identity cards, driver’s licenses, and registration certificates, where varied languages and layouts challenged traditional OCR and existing models. It selected Qwen2-VL 2B for its efficient size, SEA language tokenizer coverage, and dynamic native-resolution image handling, while synthetic Common Crawl text images and Documint supplied reviewed training labels for detection, orientation, OCR, and KIE. LoRA fine-tuning improved Latin-script documents but struggled with Thai, Vietnamese, and dense unstructured layouts, leading to two-stage full-parameter training with synthetic SEA text images followed by task-specific document fine-tuning. The fully fine-tuned 2B model raised Thai accuracy by 70 percentage points and Vietnamese accuracy by 40 points over baseline, while a custom roughly 1B-parameter model combining Qwen2-VL 2B’s vision encoder with Qwen2.5 0.5B’s decoder stayed within a 3-point accuracy gap across most document types and achieved lower latency.


### [Aligning to What? Rethinking Agent Generalization in MiniMax M2](https://yomu.fyi/post/aligning-to-what-rethinking-agent-generalization-in-minimax-m2.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: MiniMax
- Published: Oct 30, 2025
- Type: Problem & solution

MiniMax M2 addresses the performance gap between agent benchmark scores and real-world deployment across diverse scaffolding frameworks and environments. While initial alignment efforts relied on scaling tool variety, models continued to fail when subjected to slight variations in prompts, scaffolding, and tool responses. To resolve this instability, the team introduced interleaved thinking, which enables models to execute internal reasoning at arbitrary steps throughout long-horizon tasks to adapt dynamically to external tool outputs. Additionally, developers constructed a data pipeline designed for full-trajectory generalization by introducing perturbations across system prompts, user objectives, environments, and tool feedback. In internal evaluations, MiniMax M2 maintained robust tool-calling and instruction-following performance when tested against unfamiliar, cold-start agent scaffolding frameworks.


### [Machine-learning predictive autoscaling for Flink](https://yomu.fyi/post/machine-learning-predictive-autoscaling-for-flink.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Minh Nhat Nguyen
- Published: Oct 30, 2025
- Type: Problem & solution

Grab’s Flink platform saw application count grow 2.5 times, making cost-effective, self-service CPU provisioning difficult for users who often relied on trial and error and over-provisioned resources. Reactive autoscaling with Adaptive Scheduler, Kubernetes HPA, and metrics such as CPU usage or consumer latency caused restart spikes, scaling spirals, fluctuations, and additional constraints when connectors such as Kafka reached fixed partition parallelism. Predictive Resource Advisor instead uses vertical scaling and predictive, deterministic CPU decisions, automatically collecting data, training models, and applying configuration changes. The source says applications using it experienced fewer autoscaling-related disruptions, adapted to workload growth and surges, and averaged more than 35% cloud infrastructure cost savings. It also reports simpler default-configuration deployment, while planned work includes memory tuning, improved burst handling, and more efficient model training.


### [On the Shifting Global Compute Landscape](https://yomu.fyi/post/on-the-shifting-global-compute-landscape.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Tiezhen WANG, Irene Solaiman
- Published: Oct 29, 2025
- Type: Explainer

United States export controls on advanced artificial intelligence hardware have catalyzed rapid expansion across China's domestic silicon and open-weight model ecosystem. Faced with restricted access to high-end NVIDIA GPUs, Chinese developers accelerated deployments on domestic accelerators, including Huawei Ascend, Cambricon, and Baidu Kunlun. Hardware scarcity spurred architectural and algorithmic innovations in compute efficiency, notably DeepSeek's Multi-head Latent Attention and Group Relative Policy Optimization, alongside substantial post-training cost reductions. Organizations such as Baidu and Ant Group now train foundation models directly on domestic hardware, fostering non-CUDA software stacks and lowering inference costs globally. Consequently, the global artificial intelligence infrastructure is shifting from an exclusively American-focused paradigm toward a dual-ecosystem landscape powered by domestic chips and open-weight architectures.


### [Building a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac](https://yomu.fyi/post/building-a-healthcare-robot-from-simulation-to-deployment-with-nvidia.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Steven Palma, Andres Diaz-Pinto
- Published: Oct 29, 2025
- Type: Tutorial

Simulation in healthcare robotics has historically been slow, siloed, and difficult to translate into real-world physical systems. The NVIDIA Isaac for Healthcare v0.4 release introduces an end-to-end SO-ARM starter workflow to streamline simulation, training, and deployment for embodied surgical assistants. The architecture relies on a Sim2Real mixed training approach that fine-tunes the GR00T N1.5 foundation model on combined real-world and synthetic datasets using LeRobot. Synthetic data generated in simulation constitutes over 93 percent of the policy training data to bridge physical data collection constraints. Real-time inference on the SO-ARM101 precision manipulator utilizes RTI DDS communication, dual-camera vision, and TensorRT model conversion.


[Newer posts](https://yomu.fyi/topic/machine-learning/page/19.md) · [Older posts](https://yomu.fyi/topic/machine-learning/page/21.md)