Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition

Author

Prabhu Rangaraju

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#small language model Open access Oct 2026

A Small Language Model Does Not Reliably Exhibit Classic Decision Biases: A Preregistered Null Result in Qwen3-1.7B

Preregistered null result: a five-bias pilot battery (framing, conjunction fallacy, anchoring, endowment effect, cognitive reflection) run on Qwen3-1.7B-Instruct under CPU-only inference fails the preregistered 3-of-5 pass gate (2/5). Inference-only irrationality levers increase miscalibration. One-command reproduction...

Prabhu Rangaraju · 0 citations
#graph neural networks Open access Oct 2026

Forget Gradient Surgery: A Characterization of Projected Gradient Descent for Graph Edge Unlearning

Preprint of the paper 'Forget Gradient Surgery: A Characterization of Projected Gradient Descent for Graph Edge Unlearning' (submitted to TMLR). Machine unlearning for graph neural networks is complicated by message passing: deleting an edge from the adjacency matrix does not erase what the parameters learned from it,...

Prabhu Rangaraju · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.