Subramanyam Sahoo

According to our database, Subramanyam Sahoo authored at least 19 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs.

Subramanyam Sahoo

CoRR, April, 2026

The Reasoning Trap - Logical Reasoning as a Mechanistic Pathway to Situational Awareness.

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

CoRR, March, 2026

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement.

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

CoRR, March, 2026

The Controllability Trap: A Governance Framework for Military AI Agents.

Subramanyam Sahoo

CoRR, March, 2026

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning.

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

CoRR, March, 2026

Policy myopia as a mechanism of gradual disempowerment in Post-AGI governance, Circa 2049.

Subramanyam Sahoo

CoRR, March, 2026

I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift.

Subramanyam Sahoo, Vinija Jain, Divya Chaudhary, Aman Chadha

CoRR, March, 2026

Dial E for Ethical Enforcement: institutional VETO power as a governance primitive.

Subramanyam Sahoo, Vinija Jain, Aman Chadha, Divya Chaudhary

CoRR, March, 2026

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation.

Mubashara Akhtar, Anka Reuel, Prajna Soni, Sanchit Ahuja, Pawan Sasanka Ammanamanchi, Ruchit Rawal, Vilém Zouhar, Srishti Yadav, Chenxi Whitehouse, Dayeon Ki, Jennifer Mickel, Leshem Choshen, Marek Suppa, Jan Batzner, Jenny Chim, Jeba Sania, Yanan Long, Hossein A. Rahmani, Christina Knight, Yiyang Nan, Jyoutir Raj, Yu Fan, Shubham Singh, Subramanyam Sahoo, Eliya Habba, Usman Gohar, Siddhesh Pawar, Robert Scholz, Arjun Subramonian, Jingwei Ni, Mykel J. Kochenderfer, Sanmi Koyejo, Mrinmaya Sachan, Stella Biderman, Zeerak Talat, Avijit Ghosh, Irene Solaiman

CoRR, February, 2026

2025

The Deepfake Detective: Interpreting Neural Forensics Through Sparse Features and Manifolds.

Subramanyam Sahoo, Jared Junkin

CoRR, December, 2025

The Double Life of Code World Models: Provably Unmasking Malicious Behavior Through Execution Traces.

Subramanyam Sahoo, Jared Junkin

CoRR, December, 2025

Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity.

Subramanyam Sahoo, Vinija Jain, Saanidhya Vats, Siddharth Mohapatra, Rui Min, Aman Chadha, Divya Chaudhary

CoRR, December, 2025

Position: The Complexity of Perfect AI Alignment - Formalizing the RLHF Trilemma.

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

CoRR, November, 2025

The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems.

Subramanyam Sahoo, Jared Junkin

CoRR, November, 2025

The Last Vote: A Multi-Stakeholder Framework for Language Model Governance.

Subramanyam Sahoo, Aditi Chhawacharia

CoRR, November, 2025

The Good, The Bad, and The Hybrid: A Reward Structure Showdown in Reasoning Models Training.

Subramanyam Sahoo

CoRR, November, 2025

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations.

Anka Reuel, Avijit Ghosh, Jenny Chim, Andrew Tran, Yanan Long, Jennifer Mickel, Usman Gohar, Srishti Yadav, Pawan Sasanka Ammanamanchi, Mowafak Allaham, Hossein A. Rahmani, Mubashara Akhtar, Felix Friedrich, Robert Scholz, Michael Alexander Riegler, Jan Batzner, Eliya Habba, Arushi Saxena, Anastassia Kornilova, Kevin Wei, Prajna Soni, Yohan Mathew, Kevin Klyman, Jeba Sania, Subramanyam Sahoo, Olivia Beyer Bruvik, Pouya Sadeghi, Sujata S. Goswami, Angelina Wang, Yacine Jernite, Zeerak Talat, Stella Biderman, Mykel J. Kochenderfer, Sanmi Koyejo, Irene Solaiman

CoRR, November, 2025

2024

Boardwalk Empire: How Generative AI is Revolutionizing Economic Paradigms.

Subramanyam Sahoo, Kamlesh Dutta

CoRR, 2024

DUNE: Decoding Unified Naive Bayes Explainability through Gaussian methods for a Heart Disease Diagnostic.

Subramanyam Sahoo, Kamlesh Dutta

Proceedings of the 15th International Conference on Computing Communication and Networking Technologies, 2024