NVIDIA's open-source Nemotron-Cascade RL recipe wins NeurIPS Oral, IOI silver
_weiping · x · 2026-09-25
- NVIDIA's Nemotron-Cascade, a fully open-source RL recipe for LLM post-training (model + data on Hugging Face), is accepted as an Oral at NeurIPS 2026.
- Instead of mixing tasks, it scales Cascade RL as a curriculum: RLHF → Instruct → Math → Code → SWE.
- Results: Silver Medal at IOI 2025 and outperforms DeepSeek-R1-0528 on LiveCodeBench; the team's technical report details learnings.
More from Models
- Vercel gateway data: Anthropic spend share falls 69%→40% as OpenAI doubles — ctjlewis · 2026-09-25
- Muse Spark 1.3 Now Available via Oracle, in Private Preview on Google Cloud — alexandr_wang · 2026-09-25
- Gemini 3.8 Flash scores 89.2% on ARC-AGI-2 at $0.40/task, 98.5% on ARC-AGI-1 — fchollet · 2026-09-25
- Arena Launches Redesigned Leaderboard Hub Unifying Live Model Eval Signals — arena · 2026-09-25
- Early verdict: Opus 5.5 is the best Claude yet — well-rounded and faster, weaker at math — marcosalvi · 2026-09-25
- Using Jev-style system-1 models as a cheap calibrated decision layer for Bittensor validators — markjeffrey · 2026-09-25