Loading…
Topic
617 posts about Machine Learning. Every summary links to the original.
See the idea
A walkthrough of how a 3D CT model turns a voxel volume into a structured diagnostic report: isotropic resampling, 3D patch tokens, spatial encoding, and language-model reasoning.
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Newest first
Shopify describes a foundational generative recommender that predicts next products, and in some contexts ads, from buyer event sequences spanning searches, views, add-to-carts, favorites, and purchases. The system uses an autoregressive model with causal masking, time-aware attention combining RoPE-inspired rotary encoding with relative attention bias, and sampled softmax with shared and positive-aware hard negatives. Built on HSTU, it combines richer activity data, ensemble-focused training for incremental recall, and optimized CUDA kernels; the full training pipeline reached up to 7.3x the speed of a baseline implementation. In an online test of an August model version, relative shop orders rose 0.94%, high-quality click-through rate rose 5%, conversion rate rose 0.71%, and final served product recall at 2 rose 4.8%.
Hugging Face announces that GGML, the creators of llama.cpp, are joining the company to support the ggml and llama.cpp community as local AI advances. Georgi Gerganov and his team will continue dedicating 100% of their time to maintaining llama.cpp, retaining autonomy and leadership over its technical direction and community, while the project remains fully open-source and community driven. The technical focus is tighter integration between llama.cpp’s local-inference stack and Transformers’ model definitions, aiming to make shipping new models from Transformers’ “source of truth” nearly single-click, alongside better packaging and user experience for ggml-based software. The longer-term goal is an efficient inference stack that runs on devices and helps make open-source superintelligence accessible, with llama.cpp becoming ubiquitous and easier for casual users to deploy and access.
The post presents a workflow for fine-tuning the LiquidAI/LFM2.5-1.2B-Instruct small language model with Unsloth on Hugging Face Jobs, including optional use of Claude Code, Codex, or another coding agent. It explains that Unsloth is described as providing about 2x faster training and 60% lower VRAM use than standard methods, while the model runs under 1GB of memory and is optimized for on-device deployment. The tutorial covers claiming free Hugging Face Jobs credits through the Unsloth Jobs Explorers organization, installing the hf CLI or a model-training skill, and submitting a job with a dataset, GPU flavor, timeout, and output repository. An agent can generate a UV training script using 4-bit loading and LoRA, submit the managed cloud-GPU job, report Trackio monitoring details, and push the trained model to the Hugging Face Hub.
The post presents Gradio 6’s gr.HTML as a way to build interactive web components in a single Python file, combining custom HTML templates, scoped CSS, and JavaScript interactivity without a separate build step. It describes applications including a Pomodoro timer, contribution heatmap, Kanban board, spinning wheel, and machine-learning viewers for detection, 3D camera control, and speech transcription. Within the component API, ${value} injects Python state into the template, props.value updates that state from JavaScript, and trigger('change') synchronizes it back to Python; CSS keyframes and native HTML5 drag events supply richer behavior. For reuse, a gr.HTML subclass packages the templates and script so the result can be used like built-in Gradio components, while reload mode and Spaces deployment support rapid iteration from generated code to a live app.
Traditional movie search mechanisms depend on coarse filters such as genre, actor, or title, which fail to capture emotional context and narrative nuances. This guide demonstrates building a mood-based semantic recommendation system by combining the voyage-4-nano open-weights embedding model, Hugging Face datasets, and MongoDB Atlas Vector Search. The architecture uses Sentence Transformers to generate embeddings and exposes an endpoint through FastAPI to match user moods against movie plots. Truncating the Matryoshka embeddings from 2048 to 1024 dimensions balances semantic retrieval quality, storage footprint, and query latency. Testing shows that while abstract emotional queries return moderate similarity scores around 0.62 to 0.67, concrete descriptive queries exceed 0.75 without requiring exact keyword matches.
Writing CUDA kernels that integrate with diffusers and transformers involves GPU-specific optimization, library integration, PyTorch registration, and environment compatibility. It presents a cuda-kernels agent skill that packages architecture guides, integration patterns, kernel templates, troubleshooting material, benchmarks, and Kernel Hub examples for coding agents. Claude and Codex used it to generate RMSNorm, RoPE 3D, GEGLU, and AdaLN kernels for LTX-Video in diffusers, and an RMSNorm kernel for Qwen3-8B in transformers, including CUDA source, PyTorch bindings, build configuration, and benchmark scripts. On H100 80GB HBM3, the LTX-Video RMSNorm tests averaged 1.88x speedup and the optimized pipeline with torch.compile reached 1.43x the listed baseline, while Qwen3-8B RMSNorm averaged 1.94x and reached 2.47x at 8192 tokens. The skill supports packaging kernels for precompiled distribution through the Hub, where get_kernel selects a matching binary across Python, PyTorch, and CUDA variants.
Intercom introduces Resolution Bot, a machine-learning support chatbot designed to resolve customer issues rather than merely direct people to help-center articles. In the Intercom Messenger, it provides tailored resolutions, can use integrations such as Shopify to surface order status, and proactively suggests answers while customers type. The update adds six languages—Spanish, French, Italian, Brazilian Portuguese, Russian, and German—along with demographic targeting based on factors such as spend, business type, and location. New reporting shows answer-level sends and resolution rates, identifies underperforming answers, and lets teams filter conversation metrics for bot interactions. Intercom reports that the bot automatically resolves 33% of common support questions and saved businesses an average of 109 hours of customers’ time over the last year, positioning the release as a way to provide faster, more consistent support at global scale.
When randomized A/B tests are infeasible for evaluating partnerships or long-term effects, Lyft applies Augmented Inverse Propensity Weighting (AIPW) doubly robust models to estimate treatment effects from observational data. The quasi-experimentation platform mandates rigorous confounder selection prior to treatment exposure and adjusts for downsampling bias via propensity score conversions and outcome reweighting. When comparing AIPW against experimental ground truths, initial estimates understated effects because trimming extreme propensity scores removed key users and unobserved confounders persisted. To evaluate model health and external validity, the platform incorporates diagnostic scorecards featuring common support checks, Marginal Sensitivity Models, and covariate comparisons between trimmed and untrimmed cohorts.
Transformers.js v4 is now available on NPM, marking a major release after a year of development. It introduces a C++-rewritten WebGPU runtime tested across about 200 supported model architectures, enabling the same JavaScript code to run WebGPU-accelerated models in browsers, Node, Bun, Deno, and desktop applications. Specialized ONNX Runtime Contrib Operators support new export strategies for large language models, and the post reports a roughly fourfold speedup for BERT-based embedding models using MultiHeadAttention. The release also restructures the repository as a pnpm-workspaces monorepo, modularizes model definitions, moves examples to a separate repository, and switches from Webpack to esbuild, reducing build times from two seconds to 200 milliseconds and shrinking transformers.web.js by 53%. New APIs cover model asset inspection, caching, environment fetch controls, logging, and standalone tokenization, while added architectures include Mamba, MLA, and MoE models compatible with WebGPU.
Hugging Face is introducing Community Evals, a system for decentralized and transparent reporting of model evaluation results on the Hub. It responds to saturated benchmarks and inconsistent scores across model cards, papers, and evaluation platforms, while acknowledging that benchmark performance does not necessarily reflect real-world capabilities. Benchmark dataset repositories can register as benchmarks, define reproducible eval specifications in eval.yaml, aggregate scores from model repositories and community submissions, and display leaderboards in dataset cards. Model results are stored in .eval_results/*.yaml, while users can submit sourced scores through pull requests that remain visible as community results, with Git history and APIs supporting tracking and further aggregation. The beta feature aims to expose what was evaluated, how, when, and by whom, but it does not claim to solve benchmark saturation, test-set training, or the benchmark-reality gap.
Modern edge AI deployments require immediate real-time decision-making, local privacy, and offline operation while retaining the analytical scale of central cloud infrastructure. To address these hybrid demands, MongoDB and ObjectBox partnered to release the ObjectBox MongoDB Sync Connector as part of ObjectBox 5.0. ObjectBox operates as a lightweight on-device database with local vector search, multi-language bindings, and high-throughput I/O suited for resource-constrained hardware. In environments such as industrial factory floors and restaurant point-of-sale terminals, devices capture and evaluate operational data onsite without depending on active network connections. The native connector subsequently synchronizes critical operational datasets to MongoDB Atlas for long-term storage, fleet-wide monitoring, and machine learning model retraining.
The second part of a series on training efficient text-to-image models from scratch documents training-design ablations for the PRX model. The authors establish a Flow Matching baseline (PRX-1.2B, 100K steps, 256×256, AdamW, GemmaT5, RoPE, 1M MidJourneyV6 synthetic images) and benchmark interventions against FID, CMMD, DINO-MMD, and throughput across four buckets: Representation Alignment, Training Objectives, Token Routing and Sparsification, and Data. REPA representation alignment boosts early convergence when used as a burn-in, while the Muon optimizer lowered FID from 18.20 to 15.55 and improved CMMD and DINO-MMD. Storing denoiser weights in BF16 instead of using BF16 autocast raised FID to 21.87, and token routing methods such as TREAD/SPRINT were minor at 256² but became major wins at higher resolutions. Long captions proved critical, synthetic versus real data shifted texture versus structure, and upcoming work releases the full training code alongside a 24-hour end-to-end speedrun.
Building AI applications that connect multiple models and APIs often results in fragile scripts or requires complex production orchestration tools. To address rapid experimentation needs, Daggr introduces an open-source Python library created by the Gradio team for chaining AI workflows programmatically. Developers define workflows in Python code using components like GradioNode, FnNode, and InferenceNode, which automatically generate an interactive visual canvas served on port 7860. The interface allows users to inspect intermediate outputs, modify inputs, rerun individual pipeline steps without complete re-execution, and maintain persistent state across workspaces called sheets. Currently in beta, Daggr supports local execution with automatic fallback to remote APIs and integrates directly with Hugging Face Spaces.
Chinese open-source artificial intelligence development has shifted focus toward architectural choices, ecosystem toolchains, and domestic hardware integration following the January 2025 DeepSeek release. Leading groups have adopted Mixture-of-Experts architectures like Kimi K2 and Qwen3 to balance capability, dynamic compute allocation, and operating costs. Development expanded beyond text into multimodal domains including speech, video, and 3D systems while prioritizing smaller 0.5B to 30B distilled models under permissive Apache 2.0 licensing. Furthermore, model releases increasingly provide day-zero alignment with domestic inference and training infrastructure, including Huawei Ascend, Cambricon, and Baidu Kunlun chips. Production serving engines such as Moonshot AI's Mooncake and Baidu's FastDeploy 2.0 reflect a transition from standalone models to comprehensive system-level design.
Standard Arabic language model evaluations predominantly assess Modern Standard Arabic while overlooking regional spoken dialects that feature distinct syntax, vocabulary, and cultural grounding. To address this evaluation gap, researchers created Alyah, a benchmark comprising 1,173 manually curated multiple-choice questions collected from native Emirati speakers across seven cultural and linguistic categories. Distractor answer choices were synthetically generated using language models and manually reviewed for semantic plausibility. Evaluating base and instruction-tuned Arabic-native, adapted, and multilingual models revealed that instruction-tuned systems consistently outperformed base variants, with falcon-h1-arabic-7b-instruct achieving the top instruction accuracy at 82.18%. However, questions involving implicit meanings, rare expressions, and specific dialect phenomena remained difficult across all tested model families and sizes.
Engineers evaluated the GPT-OSS model for agentic reinforcement learning across multi-step tasks such as ReTool and GSM8K using the verl framework. Initial training runs suffered from exploding gradient norms, increasing KL divergence, and stagnating rewards. Investigation revealed that non-deterministic expert routing in the Mixture of Experts architecture caused log-probability mismatches between forward passes, which falsely triggered Proximal Policy Optimization clipping. The team resolved this by substituting detached current log-probabilities for old log-probabilities during on-policy updates. To address further training instabilities and memory bottlenecks, the implementation integrated an attention-sink-aware backward pass into FlashAttention v3 and applied sequence parallelism using all-to-all communication around attention layers.
Two Sigma leadership outlines the evolving role of artificial intelligence across quantitative investing workflows heading into 2026. The firm is embedding frontier large language models into internal systems, incident management, and feature generation pipelines to accelerate research tasks that previously took months into days. Technical focus across the broader field is shifting from raw parameter scaling toward efficiency optimizations, multimodal unified representations, and mechanistic interpretability circuits. In forecasting pipelines, rapid automated hypothesis generation introduces severe risks of overfitting and compromised backtesting, particularly when pre-trained models already contain historical regime knowledge prior to their cutoff dates. Consequently, engineering success requires strong institutional research discipline, production monitoring, and skepticism alongside the adoption of automated agentic tooling.
AssetOpsBench is an evaluation framework designed to benchmark agentic AI systems within industrial Asset Lifecycle Management operations, such as chillers and air handling units. The benchmark incorporates 2.3 million sensor telemetry points, 4,200 work orders, 53 structured failure modes, and over 140 curated scenarios spanning four agent roles. Systems are assessed across six qualitative criteria, including task completion, retrieval accuracy, result verification, sequence correctness, clarity and justification, and hallucination rate. Evaluation traces are analyzed using a trajectory-level diagnostic pipeline called TrajFM, which extracts and clusters failure patterns. In community tests covering over 300 agents, no evaluated model family reached the 85-point readiness threshold.
The January 2025 release of DeepSeek's R1 model transformed China's artificial intelligence sector from a closed ecosystem into an organic open-source ecosystem. By releasing under the MIT license and sharing reasoning paths and post-training methods, DeepSeek turned complex reasoning into a reusable, downloadable engineering asset suitable for distillation in compute-constrained environments. Chinese technology organizations subsequently shifted from comparing standalone benchmark scores to developing ecosystem interfaces, application scenarios, and system-level infrastructure. Major players rapidly expanded their open footprints, driving downloads of newly created Chinese models on Hugging Face past those of any other nation. This momentum catalyzed global open-source adoption across international markets while prompting Western organizations to develop competing open-weight alternatives or build directly upon open Chinese foundations.
Differential Transformer V2 introduces an architectural refinement to differential attention that pairs and subtracts query heads within the same grouped-query attention group. The architecture doubles query heads while preserving key-value head counts, which avoids increasing key-value cache demands and removes the need for custom kernels. DIFF V2 replaces the per-head RMSNorm of its predecessor with a per-token, per-head projected lambda passed through a sigmoid function. This formulation expands the context root-mean-square range to between zero and root two, preventing massive gradient magnifications, mitigating attention sinks, and stabilizing large learning rate pretraining. Ablations confirm that sharing keys and values across subtracted heads and constraining lambda scaling are necessary to prevent training instability and elevated loss.
The best engineering reads, once a week.
