A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Kaleido introduces a family of generative models for photorealistic, unified object- and scene-level neural rendering by treating 3D as a sequence-to-sequence problem.
Unknown
This paper critically examines the relationship between neural scaling laws and the role of theory in machine learning science.
Unknown
A study quantifying neural scaling laws for Robot Foundation Models to guide data and model scaling in robotics.
Unknown
The paper applies large-N field theory to derive neural scaling laws and proposes solvable models that go beyond the ridgeless limit.
Unknown
The paper argues that implicit bias in learning dynamics controls neural scaling laws during training, linking growth to scaling behavior from perceptrons to deep networks.
Unknown
Proposes a universal compression theory linking the lottery ticket hypothesis and neural scaling laws, showing how compression can significantly improve scaling laws.
Unknown
An empirical study showing how text quality interventions reshape neural scaling laws for LLMs, affecting performance projection and resource planning.
Unknown
The paper derives a solvable attention mechanism that enables precise characterization of neural scaling laws for linear self-attention.
Unknown
A statistical and approximation theory framework predicting neural scaling laws for transformers on intrinsically low-dimensional data, quantifying data and model scaling exponents.
Unknown
Investigates neural scaling laws for the ERM minimizer in the teacher-student setting beyond the random features regime, focusing on feature learning.
Chen An, Fei Huang, Jun Zhang, et al.
Proposes a training-free method to extend the context window of large language models beyond their pretraining length without additional training.
Unknown
This paper shows that Process Reward Models can generalize from mathematical reasoning to code, enhancing LLM reasoning in test-time scaling across domains.