SourcesSpargeAttention2 — 95% Sparsity 16.2x Attention SpeeduparXiv·high signalXBlueskyLinkedInCopy linkTsinghua hybrid Top-k plus Top-p masking with distillation fine-tuning. 95% attention sparsity, 16.2x speedup on video diffusion. arXiv 2602.13515.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternVibe Coding Cut Task Time 27% and Raised Security Vulnerabilities in the Same TrialarXiv 2609.09560Policy dependency / Follow-up threadMr.LHDR benchmark: the best deep-research agent gets 43.1% of final answers right but only 34.3% with a correct intermediate chainarXivStack layer / Follow-up threadModels Spot Only 9.6% of Implementation Gaps in Research Specs but Fix 80.6% Once You Point Them OutarXiv 2609.10539Stack layerSnowflake's HybridDeepResearch shows frontier models hit only ~50-54% Pass@8 when an answer needs both SQL and web searcharXivStack layerVikingRAG Matches State-of-the-Art Structured-Document RAG Using 5.1-32.5% of the TokensarXivStack layerNVIDIA Opens a Natural-Language-Only IMO 2026 Gold Pipeline on Nemotron 3 Ultra, Weights and Proofs IncludedarXivStack layerShow-Harness gets frontier VLMs controlling robots zero-shot through discrete semantic action unitsarXivStack layerThe Era by Eon Benchmark generates a whole fake company — Salesforce, Zendesk, Slack, Gong simulators — with exact answer keysarXiv