Paper Feed

Highlighting research I find interesting and think may deserve more attention (as of 05/04/26).

Training and Generalization

Synthetic Data for any Differentiable Target
Tristan Thrush, Sung Min Park, Herman Brunborg, [...], Tatsunori Hashimoto (2026)
Evidence on AI R&D Progress from NanoGPT
Manish Shetty (2026)
When do spectral gradient updates help in deep learning?
Damek Davis, Dmitriy Drusvyatskiy (2026)
Too Sharp, Too Sure: When Calibration Follows Curvature
Alessandro Morosini, Matea Gjika, Tomaso Poggio, Pierfrancesco Beneventano (2026)
Revisiting the Past: Data Unlearning with Model State History
Keivan Rezaei, Mehrdad Saberi, Abhilasha Ravichander, Soheil Feizi (2026)
Chunky Post-Training: Data Driven Failures of Generalization
Seoirse Murray, Allison Qi, Timothy Qian, John Schulman, Collin Burns, Sara Price (2026)

Model Internals

Mechanisms of Introspective Awareness
Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey (2026)
Introspection Adapters: Training LLMs to Report Their Learned Behaviors
Keshav Shenoy, Li Yang, Abhay Sheshadri, [...], Rowan Wang (2026)
Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
Ishaq Aden-Ali, Noah Golowich, Allen Liu, Abhishek Shetty, Ankur Moitra, Nika Haghtalab (2026)
Subliminal Steering: Stronger Encoding of Hidden Signals
George Morgulis, John Hewitt (2026)
Disentangling MLP Neuron Weights in Vocabulary Space
Asaf Avrahamy, Yoav Gur-Arieh, Mor Geva (2026)
Learning to Recall with Transformers Beyond Orthogonal Embeddings
Nuri Mert Vural, Alberto Bietti, Mahdi Soltanolkotabi, Denny Wu (2026)
Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
Fabrizio Boncoraglio, Vittorio Erba, Emanuele Troiani, [...], Lenka Zdeborova (2026)

Alignment

Security and Control

AI Economics and Forecasting