Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Soumik Mukhopadhyay

Soumik Mukhopadhyay

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1AI×1Vision×1

Frequent co-authors

Eric Zhu1×
Abhinav Shrivastava1×

Research Timeline

2026
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

This paper proposes two strategies to improve feedback efficiency of reinforcement learning from human feedback (RLHF) in diffusion models.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CVEmpiricalRecentJul 8, 2026

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay

This paper proposes two strategies to improve feedback efficiency of reinforcement learning from human feedback (RLHF) in diffusion models.

View →