Skip to content

#Hugging Face

0 today

Nov 14

Saturday
  1. XYBench: Helping with the problem behind the question

    We’re releasing XYBench, a benchmark of 8K+ questions that tests how AI assistants respond to requests based on misconceptions, such as asking how to thicken frosting that keeps sliding off cupcakes when the real problem is that the cupcakes are still too warm to frost. XYBench won the Best Resource Paper Award at EMNLP 2026.

Nov 10

Tuesday
  1. Nemotron-Personas-Finance-Japan: A Synthetic Dataset Capturing Japan's Demographics and Financial Context

    To address these challenges, Elith and NVIDIA have released Nemotron-Personas-Finance-Japan , a financial domain extension of the open-source persona dataset " Nemotron-Personas-Japan ." To our knowledge, it is the first open persona dataset at million-record scale that pairs Japan’s official statistics with household finance and financial literacy data.

Nov 9

Monday

Nov 8

Sunday

Nov 6

Friday

Nov 5

Thursday
  1. GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights

    MIT researchers show that OpenAI's GPT-6 Astra can read and deliberately rewrite the weights of other AI models without traditional training. In one experiment, Astra boosted a Qwen model's math accuracy from 7.9 to 48.1 percent by changing just 0.016 percent of its weights. The approach could fundamentally simplify AI optimization but still hits clear limits.

Nov 4

Wednesday

Oct 28

Wednesday

Oct 23

Friday

Oct 21

Wednesday

Oct 20

Tuesday

Oct 16

Friday
  1. Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

    Native-script data for 22 languages, romanized data for twelve, and a reusable GPU-accelerated pipeline for translation, quality assessment, and repair. We're excited to introduce Nemotron-pretraining-Indic-v1 approximately 2.8 trillion tokens across 22 Indian languages, releasing soon alongside the open, GPU-accelerated data generation pipeline used to create it.

Oct 15

Thursday
  1. GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece

    On the TheoPhysEval benchmark, GPT-6-Astra solves 49 of 50 unpublished theoretical physics calculations as accurately as leading specialists. In some cases where the agent seemed to fail, the experts' own reference solutions turned out to contain errors. But the researchers say physics hasn't had a breakthrough like the ones in mathematics, because the agents lack "taste."

Oct 7

Wednesday

Oct 4

Sunday

Sep 30

Wednesday

Sep 29

Tuesday
  1. Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents

    Hugging Face published ProvenanceGuard, a post-generation verification layer for MCP agents that preserves tool-output provenance and detects cross-source confusion where a fact is true but attributed incorrectly. Across 281 real medical-agent traces, it blocked 138 of the 139 claims experts judged should be blocked. Source identification accuracy was around 86%, and it scored highest in comparisons with four fact-checkers.

Sep 22

Tuesday

Sep 16

Wednesday

Sep 2

Wednesday

Aug 28

Friday

Aug 25

Tuesday

Aug 21

Friday
  1. Measuring benchmark optimization in speech recognition

    Hugging Face proposed three tests to quantify benchmark optimisation in speech recognition: a consensus-disagreement probe, masked-entity retrieval and spelling switches. Evaluating 11 open-source ASR models, it found some high-scoring models reproduce errors in VoxPopuli and LibriSpeech reference transcripts even when contradicted by audio, when relevant words are muted or when both spellings fit the audio.

Aug 13

Thursday

Aug 10

Monday

Jul 15

Wednesday

Jul 1

Wednesday

Jun 30

Tuesday