A preprint is a signal, not a finished product or an independently confirmed result. We therefore track research papers separately and show the actual state of supporting evidence for each one.
1381
published research events
Latest work
A significant claim from a single source is published only after further confirmation.
AscendGYM is a new benchmark for optimizing LLM kernels on Ascend NPUs, featuring 48 kernels across 3 difficulty levels. The test cases come from real production tasks. It includes the Speedup-Token Score (STS) metric, which measures performance within a set token budget. The code is publicly available.
Research introduces the Self-Disagreement method: a language model generates the strongest argument against its own answer, decides whether the argument holds up, and learns from that decision without human annotations or model preferences. This increases dialectical competence — the ability to know when to hold a position and when to change it…
A research paper from arXiv presents the Reflect-Reasoning method, which teaches language models to reason about adherence to principles instead of simply memorizing them. The method outperforms system prompting, generalizes to new domains (medicine, finance) without additional training, and reduces principle violations without…
New pilot dataset CamSpokenNLI with 228 spoken NLI examples (114 each in Cameroon Pidgin English and Camfranglais). XLM-RoBERTa achieves 44.7-46.2% accuracy on text variants; cross-variety transfer 40.1-45.6%. Automatic speech recognition (Whisper) has a WER of 66.6-45.5% and poorly detects the language.
A research pipeline generates BPMN diagrams from natural language using fine-tuned RoBERTa transformers and LLMs. It achieves 90.7% accuracy in extracting control-flow relations. The method uses few-shot learning for better generalization with limited data and an ontological representation of processes. Tested on a real…
The study examined semantic knowledge in 76 self-supervised speech language models. It found uneven availability of semantics; scaling up OmniASR wav2vec (300M–7B) benefits mainly languages with more training data.
The SCALAR method achieves LoRA-level performance with 4% of the training parameters, with 20% lower memory usage and 6% higher performance on the Qwen2.5-7B model.
Scientists have published the VEPO method, which reduces hallucinations in vision-language models without external tools. It transfers visual evidence from English to low-resource languages (Chinese, French, Hindi) using preference optimization. Tests have demonstrated a consistent decrease in hallucinations, with…
A new research framework combines attention, activation, and representation signals to analyze the internal processing of 16 LLMs on 24 benchmarks. It identifies systematic differences between knowledge-focused tasks and tasks requiring reasoning. The authors release open-source code.
The research paper presents the VOPO algorithm with a novel regret analysis for adversarial MDPs. It achieves Õ(√(H³SAK)) regret, an improvement by a factor of √(H³) or √(S/H) over previous methods. The key innovation is the Stability-Matching Bonus for variance-aware analysis.
Scientific paper (arXiv:2611.17728) describes a spectral framework for solving parameter interference in merging models without data from other tasks. The authors propose three implementations of a proxy regularizer (Jacobian, Fisher, output-drift) and theoretically prove their properties, including equivalence under NTK…
The research introduces CV-PURe, a neural network architecture combining product-unit elements with residual connections to explicitly model nonlinear interactions between features. On benchmarks, it reduces error by 53.9% compared to a standard MLP and better identifies interacting features.
Apple Machine Learning Research presents a split-and-scale method for latent 3D representations. The method expands latent capacity at inference without increasing training costs by applying the tokenizer to smaller sub-regions of scenes. It achieves quality competitive with larger models without exceeding the memory of a single…
The CGMap model uses graph learning to identify oncogene candidates from biomolecular networks. Tested on 12 022 genes, 70 candidates were found. Results were validated by functional tests on cell lines; it outperforms existing methods in interpretability.
A new MDU benchmark with 23 146 examples across 13 tasks and 5 languages (English, French, German, Italian, Spanish) tests 45 open-weight VLM models and one commercial system. Best achieved average: 69 points. Performance varies by language and task; scaling up models…
Researchers tested whether editing the error history in LLM agents improves recovery. Editing with an annotation increased the success rate to 66% (from 51%), but editing with an action decreased it to 44%. On AppWorld: a false success message decreased the success rate from 45% to 28% when the effect is not carried out. Cleaning the history without changing…
The research paper presents a framework and infrastructure for testing products and services with AI agents simulating users. The methodology conducts controlled what-if experiments with defined cohorts across multiple domains. A pilot study on 12 industrial use cases shows that persona attributes influence…
Research preprint optimizes multimodal RAG for consumer GPUs (Tesla T4). NF4 quantization maintains stability in long contexts (81 ms/token), integrating Florence-2 adds only 430 MB of VRAM. Structured prompting reduces latency by 47% and improves mathematical accuracy from 35% to 92%. The system…
AI Radar monitors Czech and international sources every day, looking for changes that truly deserve attention.
MonitorsOfficial AI company blogs, specialist media, and research sources.
Selects and combinesFilters out information noise and combines articles about the same change into a single event.
Summarizes and explainsExplains significant events in English: what happened, why it matters and where the information comes from.
The result is a quick overview of what has actually changed in the AI world, rather than another stream of articles.
Use the CS/EN switch to read the same Radar in Czech or English. English content is published after its translation has been checked, so new and older items may appear later.
Everything you need to navigate the AI world
Today’s briefingAn overview of news from the past 24 hours and a main story when available. Beside them is Live · AI Flash, followed by research and links to other Radar sections. On mobile, the blocks appear one below another.
AI FlashAn ongoing feed of brief updates with an evidence status. Links lead to a Radar detail page when one is ready, otherwise to the original source. You can also find reset and outage histories here.
Practical applicationsWhat new tools and features can do, what you can try and what their actual impact could be.
Model selectionModel comparison by type of work, capabilities, price and speed.
Research and archiveA separate research overview, topic search and older events by date.
One event, everything that matters
Each row represents one event — not one article. At a glance, you can see its significance, credibility and main point.
Illustrative example, not a current news item.
Importance: ▮▮▮ majorOpenAIModels✓ 6
Agent mode is available to all paying users
Until now, the mode was available only on the highest plan; it is now available on all paid tiers without a waitlist.
▮▮▮ major · ▮▮ important · ▮ we're tracking = how significant the change is✓ 6 = six independent publishers, not the number of articles or feeds✓ official = a clear release, law or incident is substantiated by the relevant authority1 source = no independent confirmation yetbold = who is behind the changegray text = a brief summary of what happened
The detail page contains a fuller summary, its significance and original sources. Practical impact appears in the detail and the For individuals and For businesses views. An AI Flash item reaches the main selection only after it has been expanded and meets the publication rules.
The same news, two practical uses
We first summarize each event in the same way for everyone. Based on those same facts, we then explain what the change means for your own use and what it could mean for how a company operates.
For individualsWhat you can use or try, how the change can help you at work and what to watch out for.
For businessesWhat impact the change could have on processes, costs, risks and other business decisions.
Today’s briefing is the same for everyone. Pages
For individuals and For businesses
can be found in the main navigation — they select only events relevant to the given use case.