Harvard University

university

Verified

http://www.harvard.edu

AI & ML interests

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

Recent Activity

shgao submitted a paper 21 days ago

Qworld: Question-Specific Evaluation Criteria for LLMs

Cohaerence authored a paper about 1 month ago

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

Cohaerence submitted a paper about 1 month ago

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

View all activity

Papers

Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism

Qworld: Question-Specific Evaluation Criteria for LLMs

View all Papers

submitted a paper to Daily Papers 21 days ago

Qworld: Question-Specific Evaluation Criteria for LLMs

Paper • 2603.23522 • Published Mar 6 • 10

authored 9 papers about 1 month ago

Towards Principled Disentanglement for Domain Generalization

Paper • 2111.13839 • Published Nov 27, 2021

Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation

Paper • 2202.01336 • Published Feb 2, 2022

The Impact of Symbolic Representations on In-context Learning for Few-shot Reasoning

Paper • 2212.08686 • Published Dec 16, 2022

How Does Critical Batch Size Scale in Pre-training?

Paper • 2410.21676 • Published Oct 29, 2024

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning

Paper • 2506.10378 • Published Jun 12, 2025 • 2

EvoLM: In Search of Lost Language Model Training Dynamics

Paper • 2506.16029 • Published Jun 19, 2025

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Paper • 2507.15887 • Published Jul 19, 2025

Weight Decay Improves Language Model Plasticity

Paper • 2602.11137 • Published Feb 11 • 2

Scaling Reward Modeling without Human Supervision

Paper • 2603.02225 • Published Feb 11

authored a paper about 2 months ago

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Paper • 2602.15327 • Published Feb 17 • 3

submitted a paper to Daily Papers about 2 months ago

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Paper • 2602.15327 • Published Feb 17 • 3

submitted a paper to Daily Papers 2 months ago

Weight Decay Improves Language Model Plasticity

Paper • 2602.11137 • Published Feb 11 • 2

authored a paper 11 months ago

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference

Paper • 2505.19427 • Published May 26, 2025 • 11

authored 2 papers about 1 year 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 4 papers over 1 year ago

Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark

Paper • 2304.03279 • Published Apr 6, 2023 • 2

CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training

Paper • 2406.10670 • Published Jun 15, 2024 • 4

DataComp-LM: In search of the next generation of training sets for language models

Paper • 2406.11794 • Published Jun 17, 2024 • 55

Eliminating Position Bias of Language Models: A Mechanistic Approach

Paper • 2407.01100 • Published Jul 1, 2024 • 8