Harvard University

university

Verified

http://www.harvard.edu

AI & ML interests

Artificial General Intelligence (AGI), Artificial Superintelligence (ASI), Uplift, Apotheosis

Recent Activity

Cohaerence authored a paper 2 days ago

Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol

Cohaerence submitted a paper 2 days ago

Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol

Cohaerence authored a paper about 2 months ago

Wigner's Friend as a Circuit: Inter-Branch Communication Witness Benchmarks on Superconducting Quantum Hardware

View all activity

Papers

Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling

MRI Super-Resolution with Deep Learning: A Comprehensive Survey

View all Papers

authored a paper 2 days ago

Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol

Paper • 2603.11382 • Published 6 days ago

submitted a paper to Daily Papers 2 days ago

Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol

Paper • 2603.11382 • Published 6 days ago

authored a paper about 2 months ago

Wigner's Friend as a Circuit: Inter-Branch Communication Witness Benchmarks on Superconducting Quantum Hardware

Paper • 2601.16004 • Published Jan 22 • 1

submitted a paper to Daily Papers about 2 months ago

Wigner's Friend as a Circuit: Inter-Branch Communication Witness Benchmarks on Superconducting Quantum Hardware

Paper • 2601.16004 • Published Jan 22 • 1

authored a paper 9 months ago

MIRIAD: Augmenting LLMs with millions of medical query-response pairs

Paper • 2506.06091 • Published Jun 6, 2025 • 11

authored a paper 12 months ago

Backpropagation training in adaptive quantum networks

Paper • 0903.4416 • Published Mar 25, 2009 • 1

authored 2 papers 12 months ago

Croissant: A Metadata Format for ML-Ready Datasets

Paper • 2403.19546 • Published Mar 28, 2024 • 1

AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons

Paper • 2503.05731 • Published Feb 19, 2025 • 3

authored 11 papers over 1 year ago

Are Large Language Models Post Hoc Explainers?

Paper • 2310.05797 • Published Oct 9, 2023

Post Hoc Explanations of Language Models Can Improve Language Models

Paper • 2305.11426 • Published May 19, 2023 • 1

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation

Paper • 2101.11718 • Published Jan 27, 2021

Black-Box Access is Insufficient for Rigorous AI Audits

Paper • 2401.14446 • Published Jan 25, 2024 • 3

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal

Paper • 2203.12574 • Published Mar 23, 2022

TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations

Paper • 2207.04154 • Published Jul 8, 2022

Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten

Paper • 2302.04288 • Published Feb 8, 2023

Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)

Paper • 2407.14937 • Published Jul 20, 2024 • 1

Measuring Fairness of Text Classifiers via Prediction Sensitivity

Paper • 2203.08670 • Published Mar 16, 2022

Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL

Paper • 2410.12491 • Published Oct 16, 2024 • 4

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Paper • 2409.12941 • Published Sep 19, 2024 • 25

authored a paper almost 2 years ago

Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Paper • 2404.05892 • Published Apr 8, 2024 • 40