tfevents
tfevents logs TensorBoard events from R, and this release only changes who maintains it.
Comparison · ai-assistants
Docling vs mlr3hyperband
A side-by-side editorial comparison of Docling and mlr3hyperband — release velocity, themes, recent moves, and the top alternatives to consider.
Docling vs mlr3hyperband: at a glance
What is Docling?
Docling keeps swallowing new formats, and now the parsing engines behind them are swappable.
Docling converts an unusually wide set of document formats into a single structured representation, and the release train is dense: nine releases in a month, most carrying one or two new capabilities under a long tail of backend fixes. The recent work splits cleanly in two directions. Format reach keeps extending outward (Outlook .msg, EBCDIC, legacy binary Office formats, video), while the internals are being pulled apart into selectable components: v2.120.0 exposes --layout-engine and --table-structure-engine on the CLI, and the OCR layer was refactored to resolve PP-OCR languages by version and backbone. Parsing fidelity work is concentrated in docx, pptx and odf, where reading order and list structure are still being corrected release over release.
What is mlr3hyperband?
Hyperband tuning for mlr3, now built on an asynchronous backend it treats as mandatory
mlr3hyperband supplies successive-halving and Hyperband optimizers to the mlr3 tuning stack. Its recent releases are dominated by ecosystem plumbing rather than new search algorithms: a hard floor of `rush` 1.0.0, alignment with mlr3 1.7.2, and a move onto the ecosystem's new base logger. The last genuinely new optimizer was `OptimizerAsyncSuccessiveHalving` in 1.0.0.
Docling vs mlr3hyperband: editorial side-by-side
Docling
6.3AI-ASSISTANTS
Docling keeps swallowing new formats, and now the parsing engines behind them are swappable.
◆ Current state
Docling converts an unusually wide set of document formats into a single structured representation, and the release train is dense: nine releases in a month, most carrying one or two new capabilities under a long tail of backend fixes. The recent work splits cleanly in two directions. Format reach keeps extending outward (Outlook .msg, EBCDIC, legacy binary Office formats, video), while the internals are being pulled apart into selectable components: v2.120.0 exposes --layout-engine and --table-structure-engine on the CLI, and the OCR layer was refactored to resolve PP-OCR languages by version and backbone. Parsing fidelity work is concentrated in docx, pptx and odf, where reading order and list structure are still being corrected release over release.
◆ Where it's heading
The engine layer is where the interesting movement is. Docling is shifting from one opinionated pipeline to a set of interchangeable layout, table and OCR backends the caller picks per run, which turns the library into a harness for models rather than a fixed parser. A second thread worth watching: the project shipped agent skills for itself in v2.118.0 and added uvx installation docs for them in v2.120.0, alongside a separate docling-client package, all of which point at being consumed programmatically by agents rather than only imported as a Python library. The heading-level inference from font weight, slant and case in v2.120.0 shows the other half of the strategy, extracting structure from typography rather than from markup.
◆ Prediction
Expect the --layout-engine and --table-structure-engine selection to spread from the CLI into the service API, which already gained heading-level inference and chunking options in the last two releases. The agent-skills and docling-client threads are too new across two releases to call a direction with confidence.
mlr3hyperband
2.5AI-ASSISTANTS
Hyperband tuning for mlr3, now built on an asynchronous backend it treats as mandatory
◆ Current state
mlr3hyperband supplies successive-halving and Hyperband optimizers to the mlr3 tuning stack. Its recent releases are dominated by ecosystem plumbing rather than new search algorithms: a hard floor of `rush` 1.0.0, alignment with mlr3 1.7.2, and a move onto the ecosystem's new base logger. The last genuinely new optimizer was `OptimizerAsyncSuccessiveHalving` in 1.0.0.
◆ Where it's heading
The package has finished a transition from synchronous tuning to a distributed one and is now consolidating it. 1.1.1 raised the `rush` minimum to 1.0.0 and deleted every compatibility workaround for older versions, which ends the period where the async backend was optional. Logging moved the same way in 1.1.0: `bbotk`, `mlr3tuning` and `mlr3hyperband` now log through a child of a shared `mlr3` logger rather than their own.
◆ Prediction
With the compatibility layer gone, the next release is more likely to extend async optimizers than to revisit the backend, since the recent versions spent their changes on removing optionality rather than adding surface. The entries give no signal on which optimizer comes next.
Alternatives to Docling and mlr3hyperband
Other ai-assistants products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either Docling or mlr3hyperband.
safetensors
safetensors for R changes hands with no code change to show for it.
torchdatasets
torchdatasets ships custodial work as mlverse gathers its torch satellites under one maintainer.
mlr3tuningspaces
A curated catalogue of published hyperparameter search spaces, now reaching deep neural networks
LibreChat
LibreChat's agents stop being fire-and-forget: you can now interrupt, steer, and answer them mid-run.
Ollama
Ollama now ships on the model release calendar, with an MLX build attached to each drop.
See all Docling alternatives → · See all mlr3hyperband alternatives →
Recent activity from Docling and mlr3hyperband
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 1d agoDoclingRelease CI fix, no user-facing changes
- 1d agoDoclingHeading levels inferred from font weight; pluggable CLI engines
- 5d agoDoclingOutlook .msg support and Unlimited-OCR grounding
- 8d agoDoclingLayout label and PDF picture-in-table fixes
- 11d agoDoclingEBCDIC backend, docling agent skills, all PP-OCR languages
- 16d agoDoclingChunking options reach the service API
- 21d agomlr3hyperbandrush 1.0.0 required; old compatibility paths removed
- 5mo agomlr3hyperbandLogging reparented under a shared mlr3 base logger
- 1y agomlr3hyperbandAsync successive halving lands in 1.0.0 ⚡
- 2y agomlr3hyperbandCompatibility with bbotk and mlr3tuning 1.0.0
- 2y agomlr3hyperbandCompatibility with paradox 1.0.0
- 3y agomlr3hyperbandUnloading now clears registered optimizers
Frequently asked questions
What is the difference between Docling and mlr3hyperband?
They serve adjacent needs but don't currently overlap on shipped themes. Docling is currently shipping more aggressively (velocity 6.3 vs 2.5), with 0 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is Docling better than mlr3hyperband?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Docling is currently shipping more aggressively (velocity 6.3 vs 2.5), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other ai-assistants products to evaluate alongside.
What are the best alternatives to Docling?
Top Docling alternatives in ai-assistants are ranked by recent ship velocity. Browse the "Docling alternatives" section above for the current picks, or visit /alternatives/docling for the full list with editorial commentary on each.
What are the best alternatives to mlr3hyperband?
Top mlr3hyperband alternatives in ai-assistants are ranked by recent ship velocity. Browse the "mlr3hyperband alternatives" section above for the current picks, or visit /alternatives/mlr3hyperband for the full list with editorial commentary on each.