Varad Pimpalkhute's picture

1 5 1

Varad Pimpalkhute

DaoistKalki

·

https://nightlessbaron.github.io/

AI & ML interests

Few-shot learning, generalization, multi-modality

Recent Activity

upvoted a paper 23 days ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

upvoted a paper about 1 month ago

The Path Not Taken: RLVR Provably Learns Off the Principals

liked a model 4 months ago

LLM360/K2-Think

View all activity

Organizations

upvoted a paper 23 days ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published about 1 month ago • 93

upvoted a paper about 1 month ago

The Path Not Taken: RLVR Provably Learns Off the Principals

Paper • 2511.08567 • Published Nov 11, 2025 • 33

liked a model 4 months ago

LLM360/K2-Think

Text Generation • 33B • Updated Nov 19, 2025 • 741 • 364

upvoted 2 papers 6 months ago

Critiques of World Models

Paper • 2507.05169 • Published Jul 7, 2025 • 25

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Paper • 2506.14965 • Published Jun 17, 2025 • 49

upvoted an article 9 months ago

Article

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Mar 17, 2025

•

348

authored a paper over 1 year ago

SoftQE: Learned Representations of Queries Expanded by LLMs

Paper • 2402.12663 • Published Feb 20, 2024

updated a model over 3 years ago

DaoistKalki/upside_down_detector

Updated Apr 6, 2022