News
Research milestones, paper releases, and selected updates.
| Sep 11, 2026 | 🚀 We released Atria-Dawn Preview, a 744B-parameter MoE model with a 256K-token context window for research and engineering — combining tool use, coding, and multi-step experimentation to produce verifiable, reproducible results. Model weights · Technical report. |
|---|---|
| Sep 11, 2026 | 🤗 SCALER has been included in Hugging Face’s Repo2RLEnv! |
| May 27, 2026 | 📄 New preprint: DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes — learning to recover from weak-model failures without a stronger teacher. |
| May 04, 2026 | 📄🎉 SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning — accepted to ACL 2026 Findings. |
| Oct 20, 2024 | 📄🎉 Exploring High-Order User Preference with Knowledge Graph for Recommendation — accepted to CIKM 2024 (short paper). |
| Dec 03, 2023 | 🥉 Won ICPC Bronze Medal (Jinan). |
| Nov 05, 2023 | 🥈 Won CCPC Silver Medal (Harbin). |
| Oct 22, 2023 | 🥉 Won ICPC Bronze Medal (Xi’an). |