Gemini 2.5 Pro

Mentions · 7d1
Mentions · 30d1
All mentions4
First seenSep 11, 2026
Last mentioned3d ago

Timeline

4 articles · newest first

VulnLens uses structured explanations for binary vuln detection

On a 526-function PrimeVul test set it reported 75.5% accuracy and 77.2% F1, ahead of DeepSeek V4 Pro and Gemini 2.5 Pro on those metrics.

arXiv cs.CROct 27, 18:16 UTC · 3d agoAI research1

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

D-RAC converts enterprise documents into retrieval-ready Markdown chunks, cutting chunking tokens 95.7% versus agentic methods.

Hugging Face daily papersSep 20, 20:00 UTC · Sep 20, 2026AI research3 · 1 read

ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers

ALIBI embeds fake benign-narrative sections into binaries, flipping 30 of 35 malware samples to benign verdicts on Gemini 2.5 Pro.

arXiv cs.CRSep 17, 05:27 UTC · Sep 17, 2026AI safety & security2 · 2 reads

Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation

Google Research and partners introduce ToolGrad, a verified tool-chain-first data generation framework reaching 99.8% pass rate and boosting Gemma-3-12B to 83.1 on BFCL.

MarkTechPostSep 11, 06:01 UTC · Sep 11, 2026AI research10 · 3 reads

Appears with

Googlevendor · 2
Claude 4.5 Opusai model · 1
Claude Opus 4.7ai model · 1
Googleorganization · 1
W-RACproduct · 1
Anthropicvendor · 1
GPT-5ai model · 1
DeepSeek V4 Proai model · 1
RIKEN AIPorganization · 1
University of Tokyoorganization · 1
Gemini 2.5 Flash-Liteai model · 1
GPT-4.1ai model · 1
VulnLensproduct · 1
GPT-5.5 Proai model · 1
Gemma-3ai model · 1
OpenAIvendor · 1

Entities are extracted by the model from each article. First seen Sep 11, 2026, last mentioned 3d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.