Paper
Hub
搜索
Toggle language
Vikrant Varma
~Vikrant_Varma1
5
论文总数
2.5
年均投稿
5.4
平均评分
接收情况
2
/
5
会议分布
ICLR
2
NeurIPS
2
ICML
1
发表论文 (5 篇)
2025
2 篇
7.0
3
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
ICML 2025
Poster
4.3
4
Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
ICLR 2025
Rejected
2024
3 篇
5.0
4
Explaining grokking through circuit efficiency
ICLR 2024
Rejected
4.3
3
Challenges with unsupervised LLM knowledge discovery
NeurIPS 2024
Rejected
6.5
4
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
NeurIPS 2024
Poster
合作者 (17)
RS
Rohin Shah
4 篇
JK
Janos Kramar
3 篇
ZK
Zachary Kenton
2 篇
SF
Sebastian Farquhar
2 篇
AC
Arthur Conmy
2 篇
NN
Neel Nanda
2 篇
SR
Senthooran Rajamanoharan
2 篇
TL
Tom Lieberum
2 篇
查看全部 17 位合作者