10 papers
RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory
Jingbo Ji, Lingyi Li, Xilong Cheng +4
LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply storing past experience, but rec…
A universal compression theory for lottery ticket hypothesis and neural scaling laws
Hong-Yi Wang, Di Luo, Tomaso Poggio +2
When training large-scale models, the performance typically scales with the number of parameters and the dataset size according to a slow power law. A fundamental theoretical and p…
Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model
Yizhou Xu, Pierfrancesco Beneventano, Isaac Chuang +1
A large body of theory and empirical work hypothesizes a connection between the flatness of a neural network's loss landscape during training and its performance. However, there ha…
Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning
Liu Ziyin, Yizhou Xu, Isaac Chuang
With the rapid discovery of emergent phenomena in deep learning and large language models, understanding their cause has become an urgent need. Here, we propose a rigorous entropic…
Proof of a perfect platonic representation hypothesis
Liu Ziyin, Isaac Chuang
In this note, we elaborate on and explain in detail the proof given by Ziyin et al. (2025) of the ``perfect" Platonic Representation Hypothesis (PRH) for the embedded deep linear n…
Topological Invariance and Breakdown in Learning
Yongyi Yang, Tomaso Poggio, Isaac Chuang +1
We prove that for a broad class of permutation-equivariant learning rules (including SGD, Adam, and others), the training process induces a bi-Lipschitz mapping between neurons and…