__SyedaAkter's profile picture. PhD student at @LTIatCMU @SCSatCMU and research intern @NVIDIA. Working on improving Reasoning of Generative Models! (@reasyaay.bsky.social)

Syeda Nahida Akter

@__SyedaAkter

PhD student at @LTIatCMU @SCSatCMU and research intern @NVIDIA. Working on improving Reasoning of Generative Models! (@reasyaay.bsky.social)

Pinned

Most LLMs learn to think only after pretraining—via SFT or RL. But what if they could learn to think during it? 🤔 Introducing RLP: Reinforcement Learning Pre-training—a verifier-free objective that teaches models to “think before predicting.” 🔥 Result: Massive reasoning…

__SyedaAkter's tweet image. Most LLMs learn to think only after pretraining—via SFT or RL. But what if they could learn to think during it? 🤔

Introducing RLP: Reinforcement Learning Pre-training—a verifier-free objective that teaches models to “think before predicting.”

🔥 Result: Massive reasoning…

Syeda Nahida Akter reposted

If you're a PhD student interested in doing an internship with me and @shrimai_ on RL–based pre-training/LLM reasoning, send an email ([email protected]) with: 1⃣: Short intro about you 2⃣: Link to your relevant paper I will read all emails but can't respond to all.


Syeda Nahida Akter reposted

Lot of insights in @YejinChoinka's talk on RL training. Rip for next token prediction training (NTP) and welcome to Reinforcement Learning Pretraining (RLP). #COLM2025 No place to even stand in the room.

sivareddyg's tweet image. Lot of insights in @YejinChoinka's talk on RL training. Rip for next token prediction training (NTP) and welcome to Reinforcement Learning Pretraining (RLP). #COLM2025

No place to even stand in the room.

Syeda Nahida Akter reposted

Thank you @rohanpaul_ai for highlighting our work!💫 Front-Loading Reasoning shows that inclusion of reasoning data in pretraining is beneficial, does not lead to overfitting after SFT, & has latent effect unlocked by SFT! Paper: arxiv.org/abs/2510.03264 Blog:…

New @nvidia paper shows that teaching reasoning early during pretraining builds abilities that later fine-tuning cannot recover. Doing this early gives a 19% average boost on tough tasks after all post-training. Pretraining is the long first stage where the model learns to…

rohanpaul_ai's tweet image. New @nvidia  paper shows that teaching reasoning early during pretraining builds abilities that later fine-tuning cannot recover. 

Doing this early gives a 19% average boost on tough tasks after all post-training.

Pretraining is the long first stage where the model learns to…


Thank you @rohanpaul_ai for sharing our work! In "Front-Loading Reasoning", we show that injecting reasoning data into pretraining builds models that reach the frontier. On average, +22% (pretraining) → +91% (SFT) → +49% (RL) relative gains. 🚀 🔗Paper:…

New @nvidia paper shows that teaching reasoning early during pretraining builds abilities that later fine-tuning cannot recover. Doing this early gives a 19% average boost on tough tasks after all post-training. Pretraining is the long first stage where the model learns to…

rohanpaul_ai's tweet image. New @nvidia  paper shows that teaching reasoning early during pretraining builds abilities that later fine-tuning cannot recover. 

Doing this early gives a 19% average boost on tough tasks after all post-training.

Pretraining is the long first stage where the model learns to…


Syeda Nahida Akter reposted

Nvidia presents RLP Reinforcement as a Pretraining Objective

_akhaliq's tweet image. Nvidia presents RLP

Reinforcement as a Pretraining Objective

Syeda Nahida Akter reposted

When should LLMs learn to reason—early in pretraining or late in fine-tuning?🤔 Front-Loading Reasoning, shows that injecting reasoning data early creates durable, compounding gains that post-training alone cannot recover Paper:tinyurl.com/3tzkemtp Blog:research.nvidia.com/labs/adlr/Syne…

shrimai_'s tweet image. When should LLMs learn to reason—early in pretraining or late in fine-tuning?🤔
Front-Loading Reasoning, shows that injecting reasoning data early creates durable, compounding gains that post-training alone cannot recover
Paper:tinyurl.com/3tzkemtp
Blog:research.nvidia.com/labs/adlr/Syne…

Syeda Nahida Akter reposted

New Nvidia paper introduces Reinforcement Learning Pretraining (RLP), a pretraining objective that rewards useful thinking before each next token prediction. On a 12B hybrid model, RLP lifted overall accuracy by 35% using 0.125% of the data. The big deal here is that it moves…

rohanpaul_ai's tweet image. New Nvidia paper introduces Reinforcement Learning Pretraining (RLP), a pretraining objective that rewards useful thinking before each next token prediction.

On a 12B hybrid model, RLP lifted overall accuracy by 35% using 0.125% of the data.

The big deal here is that it moves…

Syeda Nahida Akter reposted

💫 Introducing RLP: Reinforcement Learning Pretraining—information-driven, verifier-free objective that teaches models to think before they predict 🔥+19% vs BASE on Qwen3-1.7B 🚀+35% vs BASE on Nemotron-Nano-12B 📄Paper: github.com/NVlabs/RLP/blo… 📝Blog: research.nvidia.com/labs/adlr/RLP/

shrimai_'s tweet image. 💫 Introducing RLP: Reinforcement Learning Pretraining—information-driven, verifier-free objective that teaches models to think before they predict
 🔥+19% vs BASE on Qwen3-1.7B
 🚀+35% vs BASE on Nemotron-Nano-12B
📄Paper: github.com/NVlabs/RLP/blo…
 📝Blog: research.nvidia.com/labs/adlr/RLP/

Syeda Nahida Akter reposted

Are you ready for web-scale pre-training with RL ? 🚀 🔥 New paper: RLP : Reinforcement Learning Pre‑training We flip the usual recipe for reasoning LLMs: instead of saving RL for post‑training, we bring exploration into pretraining. Core idea: treat chain‑of‑thought as an…

ahatamiz1's tweet image. Are you ready for web-scale pre-training with RL ? 🚀

🔥 New paper: RLP : Reinforcement Learning Pre‑training

We flip the usual recipe for reasoning LLMs: instead of saving RL for post‑training, we bring exploration into pretraining.

Core idea: treat chain‑of‑thought as an…

Loading...

Something went wrong.


Something went wrong.