5 papers
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
Yuval Ran-Milo, Yotam Alexander, Shahar Mendel +1
Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought…
Why Does Agentic Safety Fail to Generalize Across Tasks?
Yonatan Slutzky, Yotam Alexander, Tomer Slor +2
AI agents are increasingly deployed in multi-task settings, where the task to perform is specified at test time, and the agent must generalize to unseen tasks. A major concern in s…
Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
Yotam Alexander, Yonatan Slutzky, Yuval Ran-Milo +1
Conventional wisdom attributes the mysterious generalization abilities of overparameterized neural networks to gradient descent (and its variants). The recent volume hypothesis cha…
The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
Yonatan Slutzky, Yotam Alexander, Noam Razin +1
Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data. A recent class of neural network mode…
Revisiting Glorot Initialization for Long-Range Linear Recurrences
Noga Bar, Mariia Seleznova, Yotam Alexander +2
Proper initialization is critical for Recurrent Neural Networks (RNNs), particularly in long-range reasoning tasks, where repeated application of the same weight matrix can cause v…