activity
20242026
collaborators

8 papers

cs.AI2026

Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions

Matthew Riemer, Tommaso Tosato, Amin Memarian +4

This position paper argues that AI agents with chain-of-thought reasoning capabilities are predisposed to exhibit collusive behavior and should be required to obtain behavioral cer…

cs.LG2026

Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention

Parviz Haggi-Mani, Irina Rish

Using the language of Wilsonian renormalization group theory (RG), we treat the Transformer's attention mechanism as a perturbation of the trained MLP residual-stack fixed point an…

cs.LG2026

Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks

Parviz Haggi-Mani, Irina Rish

The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing treatments remain qualitative:…

cs.LG2026

Unified Neural Scaling Laws

Ethan Caballero, Priyank Jaini, David Krueger +1

We present a functional form (that we refer to as a Unified Neural Scaling Law (UNSL)) that accurately models and extrapolates the scaling behaviors of deep neural networks as mult…

cs.LG2025

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models

Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer +6

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and…

cs.LG2025

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

Arnav Kumar Jain, Harley Wiltzer, Jesse Farebrother +3

In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Traditionally, IRL is treated as an adversaria…