Chakraborty's picture

2

Chakraborty

souradip24

·

https://souradip-chakraborty.github.io/

AI & ML interests

Reinforcement Learning, Machine Learning, NLP

Recent Activity

upvoted a paper about 10 hours ago

Transfer Q Star: Principled Decoding for LLM Alignment

updated a model 2 months ago

souradip24/dpo-merged-vllm-r4-r3

published a model 2 months ago

souradip24/dpo-merged-vllm-r4-r3

View all activity

Organizations

Papers 10

arxiv:2504.01931

arxiv:2503.12575

arxiv:2501.03486

arxiv:2411.18688

models 3

souradip24/dpo-merged-vllm-r4-r3

3B • Updated Apr 7 • 10

souradip24/dpo-llama-3.2-3b-set2-samp500-pref100

3B • Updated Mar 30 • 1

souradip24/dpo-llama-3.2-3b-set1-pref100

3B • Updated Mar 28 • 2

datasets 0

None public yet