Risultati della ricerca - Kaur, Simran
- Mostra 1 - 6 risultati su 6
-
1
How Does RL Post-training Induce Skill Composition? A Case Study on Countdown Autoría: Park, Simon, Kaur, Simran, Arora, Sanjeev
Pubblicazione 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
2
Incentive-Tuning: Understanding and Designing Incentives for Empirical Human-AI Decision-Making Studies Autoría: Kaur, Simran, Salimzadeh, Sara, Gadiraju, Ujwal
Pubblicazione 2026Fuente: arXivTipo de material: PreprintAcceso al recurso -
3
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning Autoría: Kaur, Simran, Park, Simon, Goyal, Anirudh, Arora, Sanjeev
Pubblicazione 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
4
Can Models Learn Skill Composition from Examples? Autoría: Zhao, Haoyu, Kaur, Simran, Yu, Dingli, Goyal, Anirudh, Arora, Sanjeev
Pubblicazione 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
5
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision Autoría: He, Yinghui, Kaur, Simran, Bhaskar, Adithya, Yang, Yongjin, Liu, Jiarui, Ri, Narutatsu, Fowl, Liam, Panigrahi, Abhishek, Chen, Danqi, Arora, Sanjeev
Pubblicazione 2026Fuente: arXivTipo de material: PreprintAcceso al recurso -
6
A Joint Search for the Electromagnetic Counterpart to the Gravitational-Wave Binary Black-Hole Merger Candidate S250328ae with the Dark Energy Camera and the Prime Focus Spectrogra... Autoría: Zhang, Haibin, Kokubo, Mitsuru, MacBride, Sean, McMahon, Isaac, Tominaga, Nozomu, Utsumi, Yousuke, Yoshida, Michitoshi, Morokuma, Tomoki, Tanaka, Masaomi, Arai, Akira, He, Wanqiu, Moritani, Yuki, Onodera, Masato, Passegger, Vera Maria, Tanaka, Ichi, Yabe, Kiyoto, Joseph, Lillian, Kaur, Simran, Bommireddy, Hemanth, Sherman, Nora, Herner, Kenneth, Diehl, H. Thomas, Soares-Santos, Marcelle
Pubblicazione 2025Fuente: arXivTipo de material: PreprintAcceso al recurso