Souradip Chakraborty

@souradipchakr18

Postdoc at @MIT CSAIL @nlp_mit Research: #RL, #Posttraining, #Alignment #RLVR Past: CS PhD @umdcs @ml_umd SR @GoogleResearch #JPMC #Walmart

following
followers

An invitation to discuss reinforcement learning during a San Francisco visit

The poster said they planned to attend the Simons workshop during the week of October 6, 2026.

3 Sources, 14d ago, updated 14d ago

Could Jev be learning a value function?

A post explores whether predicting task success could help calibrate fast decisions and signal when deeper reasoning is needed.

2 Sources, 19d ago, first seen 19d ago

Prompt interference and single-shot accuracy in inference-aware fine-tuning

A post announcing a paper’s acceptance at NeurIPS 2026 points to “prompt interference” as an explanation for why inference-aware fine-tuning often hurts accuracy on a single attempt.

1 Source, 26d ago, first seen 26d ago

Featured in

An invitation to discuss reinforcement learning during a San Francisco visit

Could Jev be learning a value function?

Prompt interference and single-shot accuracy in inference-aware fine-tuning

Featured in

An invitation to discuss reinforcement learning during a San Francisco visit

Could Jev be learning a value function?

Prompt interference and single-shot accuracy in inference-aware fine-tuning