iiinova — where your digital self keeps evolving

Reposted by Tianwei Ni

Continual RL Workshop @continual-rl.bsky.social · 13/07/2026

📚 Interested in Continual RL but not sure where to start? 👇 Dive in: sites.google.com/view/continu... ♾️ We've curated a resource hub with key papers, benchmarks, codebases, tutorials, and more to help you get up to speed quickly. #ContinualRL #ReinforcementLearning #MachineLearning #AI

1184

Reposted by Tianwei Ni

Continual RL Workshop @continual-rl.bsky.social · 20/06/2026

🔥 Accepted papers are out! They cover a diverse range of topics, contributing novel insights and solid findings! 🧠 The reviewers have invested substantial effort. We truly appreciate their invaluable feedback. 📄 Papers: tinyurl.com/vs4t4kne 🖼️ Reviewers: tinyurl.com/w5fy4dcm #ContinualRL #RLC2026

042

Tianwei Ni @twni2016.bsky.social · 11/04/2026

🔥Thrilled to announce the Continual Reinforcement Learning (CRL) Workshop @continual-rl.bsky.social @rl-conference.bsky.social 2026 in Montreal, Canada! 📣 We welcome submissions on broad topics of continual RL. Interested in submitting or reviewing? Check out our website for more details!

140

Tianwei Ni @twni2016.bsky.social · 23/04/2025

Work completed during my internship at Amazon Science. Thank you to my co-authors @allenanie.bsky.social, Sapana Chaudhary, Yao Liu, Huzefa Rangwala, @rasoolfa.bsky.social!

021

Tianwei Ni @twni2016.bsky.social · 23/04/2025

Results on challenging math games, Countdown & Game-of-24: ⚡180× faster inference than search-based baseline 📈Beats CoT and inference-time search (ToT, RAP) 📄 Paper: arxiv.org/abs/2504.11364 💻 Code & data: github.com/twni2016/llm...

arxiv.org

Teaching Large Language Models to Reason through Learning and Forgetting

Leveraging inference-time search in large language models has proven effective in further enhancing a trained model's capability to solve complex mathematical and reasoning problems. However, this app...

120

Tianwei Ni @twni2016.bsky.social · 23/04/2025

2️⃣ Learn successful reasoning paths ✅ while forgetting failed reasoning paths ❌ at the same time, which we call Unlikelihood Fine-Tuning (UFT) 3️⃣ Small learning rate is crucial to preserve inference-time search capabilities

110

Tianwei Ni @twni2016.bsky.social · 23/04/2025

1️⃣ Aggregate reasoning paths from diverse sources: Chain-of-Thought, inference-time search (Tree-of-Thought, Reasoning-via-Planning), classic algorithms (BFS, DFS)

100

Tianwei Ni @twni2016.bsky.social · 23/04/2025

Can we make LLMs reason effectively without a huge inference time cost? We show a powerful approach through learning and forgetting! Our recipe: ⬇️

142