collaborators

6 papers

math.NT2026

ABC implies that Ramanujan's tau function misses almost all primes

David Kurniadi Angdinata, Evan Chen, Chris Cummins +21

Lehmer conjectured that Ramanujan's tau-function never vanishes. In a related direction, a folklore conjecture asserts that infinitely many primes arise as absolute values of Raman…

cs.LG2025

ProofOptimizer: Training Language Models to Simplify Proofs without Human Demonstrations

Alex Gu, Bartosz Piotrowski, Fabian Gloeckle +2

Neural theorem proving has advanced rapidly in the past year, reaching IMO gold-medalist capabilities and producing formal proofs that span thousands of lines. Although such proofs…

cs.CL2025

Continual Learning via Sparse Memory Finetuning

Jessy Lin, Luke Zettlemoyer, Gargi Ghosh +4

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where u…

cs.CL2025

Detecting Prefix Bias in LLM-based Reward Models

Ashwin Kumar, Yuzi He, Aram H. Markosyan +2

Reinforcement Learning with Human Feedback (RLHF) has emerged as a key paradigm for task-specific fine-tuning of language models using human preference data. While numerous publicl…

cs.LG2025

What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces

Jordi Armengol-Estapé, Quentin Carbonneaux, Tianjun Zhang +8

Code generation and understanding are critical capabilities for large language models (LLMs). Thus, most LLMs are pretrained and fine-tuned on code data. However, these datasets ty…

cs.CV2025

With Great Backbones Comes Great Adversarial Transferability

Erik Arakelyan, Karen Hambardzumyan, Davit Papikyan +4

Advances in self-supervised learning (SSL) for machine vision have improved representation robustness and model performance, giving rise to pre-trained backbones like \emph{ResNet}…