# New Release: Ultralytics v8.4.68 **URL:** \ **Category:** Discussion\ **Tags:** ultralytics-official, releases, announcements\ **Created:** [June 16, 2026, 2:37pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-68/2067 "2026-06-16T14:37:27Z")\ **Posts on this page:** 1\ **Page:** 1

**Author:** ![glenn-jocher](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/glenn-jocher/32/83_2.png) [@glenn-jocher](https://community.ultralytics.com/u/glenn-jocher)\ **Post date:** [June 16, 2026, 2:37pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-68/2067/1 "2026-06-16T14:37:27Z")

# Ultralytics v8.4.68 is out 🚀 We’ve released **Ultralytics `v8.4.68`** , a practical quality update focused on **better training control for semantic segmentation** and **stronger day-to-day reliability** across training, inference, docs, and tooling. ## 🌟 Quick Summary The headline in `v8.4.68` is **semantic segmentation class weighting via `cls_pw`** 🎯 This gives users training on imbalanced segmentation datasets a new way to emphasize underrepresented classes, while keeping default behavior unchanged for existing pipelines. Alongside that, this release includes several important robustness fixes, safer compatibility behavior on older PyTorch versions, a UI security fix, and documentation updates including new **Ultralytics YOLO26** Windows on Snapdragon benchmarks. * * * ## New Features ### 🖼 Semantic segmentation now supports class weights with `cls_pw` The biggest addition in this release comes from [PR #24843 by @Y-T-G](https://github.com/ultralytics/ultralytics/pull/24843) and brings **user-configurable class weighting** to semantic segmentation. Why this matters: - Rare classes can now receive more attention during training - This is especially useful for **imbalanced datasets** - It gives researchers and practitioners more control over semantic segmentation optimization A few important details: - If `cls_pw` is **not set** or set to `0`, behavior remains the same ✅ - Existing **Cityscapes-specific weighting** still applies automatically where appropriate - The new logic is based on **class pixel frequency** , which is better suited to dense pixel-level tasks than detection-style weighting This means you get a meaningful new tuning option without disrupting current training workflows. Minimal example: ```python from ultralytics import YOLO model = YOLO("yolo11n-seg.pt") model.train(data="data.yaml", task="segment", cls_pw=1.0) ``` If you’re starting a new project, we recommend exploring [Ultralytics YOLO26](https://platform.ultralytics.com/ultralytics/yolo26) for the latest models and using the [Ultralytics Platform](https://platform.ultralytics.com) to annotate, train, and deploy end to end. * * * ## Improvements ### 🧠 Better weighting logic for semantic segmentation The same [PR #24843 by @Y-T-G](https://github.com/ultralytics/ultralytics/pull/24843) also improves how class weighting is computed for segmentation tasks. The new approach is designed specifically for **dense prediction** , helping avoid overly aggressive weighting while still boosting underrepresented classes. ### 📦 Detection classification loss can now use class weights too This release also refactors class counting and weighting into reusable trainer helpers, allowing detection training to apply computed class weights directly in classification loss as part of [PR #24843 by @Y-T-G](https://github.com/ultralytics/ultralytics/pull/24843). ### 💻 Windows on Snapdragon benchmark docs [PR #24834 by @ShuaiLYU](https://github.com/ultralytics/ultralytics/pull/24834) adds **Windows on Snapdragon** QNN benchmark documentation for **YOLO26n** across all six tasks, helping users evaluate deployment on modern ARM and NPU-enabled systems. ### 💳 Ultralytics Platform pricing docs update [PR #24838 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24838) updates **Ultralytics Platform** GPU pricing documentation for clearer planning and usage guidance. * * * ## Bug Fixes ### 🚑 Four production reliability fixes [PR #24840 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24840) resolves four real-world issues: - crashes from empty prediction batches - corrupt cached AMP asset loading - truncated downloads - invalid non-mapping YAML files These are the kinds of fixes that make pipelines noticeably smoother in production. ### 🔐 Safer model loading on older PyTorch versions [PR #24830 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24830) makes restricted model loading **gracefully fall back on `torch<2.5`** instead of erroring out, improving compatibility for older environments and export workflows. ### 🛡 Similarity search UI security fix [PR #24828 by @orbisai0security](https://github.com/ultralytics/ultralytics/pull/24828) properly escapes user query input to prevent a high-severity browser injection issue. ### 📁 ClearML path fix [PR #24827 by @MUKILAN0608](https://github.com/ultralytics/ultralytics/pull/24827) fixes ClearML project path handling. * * * ## Docs Updates Several documentation improvements landed in this release as well: - [PR #24836 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24836) fixes broken docs link checks - [PR #24839 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24839) cleans up docs metadata and URL issues - [PR #24837 by @RizwanMunawar](https://github.com/ultralytics/ultralytics/pull/24837) adds a new docs video resource Together these updates make docs navigation and browsing more polished and reliable. * * * ## New Contributors 🙌 A big welcome to our new contributors: - [@orbisai0security](https://github.com/orbisai0security) for [PR #24828](https://github.com/ultralytics/ultralytics/pull/24828) - [@MUKILAN0608](https://github.com/MUKILAN0608) for [PR #24827](https://github.com/ultralytics/ultralytics/pull/24827) Thanks for helping improve Ultralytics for everyone 💙 * * * ## Why upgrade? `v8.4.68` is a strong update if you want: - better semantic segmentation training on imbalanced datasets - more reliable handling of bad labels, masks, YAML, caches, and downloads - improved compatibility on older PyTorch stacks - cleaner docs and more deployment guidance for YOLO26 Most importantly, the new segmentation weighting is **opt-in** , so existing setups should continue working as expected. * * * ## Try it out You can upgrade with: ```bash pip install -U ultralytics ``` See the [full release page for Ultralytics v8.4.68](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.68) or browse the [full changelog from v8.4.67 to v8.4.68](https://github.com/ultralytics/ultralytics/compare/v8.4.67...v8.4.68). If you test the new segmentation weighting, YOLO26 deployment flows, or any of the reliability fixes, we’d love to hear how it goes. Please share feedback, results, or edge cases with the community 🙌