René's URL Explorer Experiment


Title: Rishabh Agarwal – Google Brain

Description: Rishabh Agarwal's Personal Website'

Mail addresses
rishabhagarwal.467@gmail.com

direct link

Domain: agarwl.github.io

NoneIE=edge
google-site-verificationCg8yLhyulyPuQaGVyOIGr3OPgS6NDLSjOB8GbgKRrSY

Links:

Abouthttps://agarwl.github.io/
Researchhttps://agarwl.github.io/research
Rishabh Agarwalhttps://agarwl.github.io/
About https://agarwl.github.io/
Researchhttps://agarwl.github.io/research
Periodic Labshttps://periodic.com/
Metahttps://x.com/agarwl_/status/1960034048698388795
Google DeepMindhttps://deepmind.google/
outstanding paper awardhttps://agarwl.github.io/rliable/
On-policy Distillation for LLMshttps://arxiv.org/abs/2306.13649
[Recording]https://youtu.be/GH4JCdAAUYg?si=x402PwhBpJ2SAJo0
The Hitchhiker’s Guide to Frontier Reinforcement Learning https://agarwl.github.io/images/research/iclr_spot_talk_v2.pdf
[Recording] https://www.youtube.com/watch?v=RBZx-BKKdG8
The Art of Scaling Reinforcement Learning Computehttps://drive.google.com/file/d/1kM25WYGKEkzE55DhN35Mqw_eO3ObEoi9/view
[Recording]https://www.youtube.com/watch?v=nXQE1DsPm2c
The Bitter Lesson for RL: Verification as the Key to Reasoning LLMs https://drive.google.com/file/d/1xd9gPMakWhKl5JlcQqrAIN7gVoxNsS5M/view
[Podcast @ Youtube] https://www.youtube.com/watch?v=O1AR4iL30mg
Post-Training Distillation of LLMs https://drive.google.com/file/d/1xMohjQcTmQuUd_OiZ3hB1r47WB1WM3Am/view
RL, Reasoning, and Verifiers. https://drive.google.com/file/d/1komQ7s9kPPvDx_8AxTh9A6tlfJA0j6dR/view
BBFhttps://arxiv.org/abs/2305.19452
Scaling RL Computehttps://www.notion.so/The-Art-of-Scaling-Reinforcement-Learning-Compute-for-LLMs-28c2af1d07f3801ebc70e6b2bc9102fd
DistillSpechttps://arxiv.org/abs/2310.08461
V-STaRhttps://arxiv.org/abs/2402.06457
Stop Regressinghttps://arxiv.org/abs/2403.03950
Generative RMshttps://arxiv.org/abs/2408.15240
RL Generalizationhttps://arxiv.org/abs/2203.00543
Asynchronous RL for LLMshttps://arxiv.org/abs/2410.18252
Speculative KD https://arxiv.org/abs/2410.11325
Compute-Optimal STaR / KD / W2S https://arxiv.org/abs/2408.16737
Offline Model Selectionhttps://arxiv.org/abs/2302.00141
Advantage for PRMs https://arxiv.org/abs/2410.08146
Dormant Neuronshttps://arxiv.org/abs/2302.12902
RL+Verifiershttps://arxiv.org/abs/2505.04842
Thinking Machines blog posthttps://thinkingmachines.ai/blog/on-policy-distillation/
On-policy Distillation of LLMshttps://arxiv.org/abs/2306.13649
Delta Podcast https://www.youtube.com/watch?v=6PUuitJNoJE
Generative Verifiers https://arxiv.org/abs/2408.15240
SCoRE https://arxiv.org/abs/2409.12917
Speculative KDhttps://arxiv.org/abs/2410.11325
Async RLHFhttps://arxiv.org/abs/2410.18252
Inference-aware RL for LLMs https://arxiv.org/abs/2412.15287
Inference Time LLM Algorithms https://cmu-l3.github.io/neurips2024-inference-tutorial/
agarwl_ https://twitter.com/agarwl_
agarwl https://github.com/agarwl/
agarwl https://www.linkedin.com/in/agarwl
https://scholar.google.ca/citations?user=aH8AJu4AAAAJ&hl=en

Viewport: width=device-width, initial-scale=1

URLs of crawlers that visited me.