November 2026

87 stories so far · page 5 of 5

Thursday 12 November

17:56
Vision & multimodalIIBenchmarked

Which models and sampling choices matter when humans and AI count together

A preprint benchmark of 12 image-counting tasks finds that free, off-the-shelf vision-language models are a strong starting point for estimating totals with a small human-labelled sample. Letting the model pick which images people check usually helps further.

17:56
AgentsIIBenchmarked

Testing an agent's lessons before they enter its long-term memory

A preprint proposes that AI agents should treat each lesson learned from a task as a hypothesis to test, and keep it only if it helps without breaking anything. The benchmark gains are large, but the comparisons need care and no code is released.

17:56
Vision & multimodalIIIOpen source

A 17 MB speech recogniser that often names words before they end

A single-author preprint retrains a small open streaming model so its median word appears about 90 ms before the speaker finishes it, each word tagged with a usable confidence. The cost is more words taken back, and it is less accurate than larger models.

All months