5 citations · 10 across the 16 of their papers we have counts for
11 papers · 1 filter
Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics
Changho Shin, David Alvarez-Melis
Curriculum learning is governed by several coupled design choices---how difficulty is defined, how examples are ordered, how much exposure each level receives, and how quickly trai…
Bridging Compute- and Data-Optimal Pretraining
Tian Qin, Kimia Hamidieh, David Alvarez-Melis
Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than th…
RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training
Rachit Bansal, Clara Mohri, Tian Qin +2
The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status quo by training a LLM from…
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
Jing Huang, Daniel Wurgaft, Rachit Bansal +6
Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling already suggests that a larger mo…
Reliable and Responsible Foundation Models: A Comprehensive Survey
Xinyu Yang, Junlin Han, Rishi Bommasani +49
Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), a…
Can Interpretation Predict Behavior on Unseen Data?
Victoria R. Li, Jenny Kaufmann, Tian Qin +3
Interpretability research often predicts model responses to targeted mechanistic interventions. But can we predict responses to unseen input data? We propose and demonstrate this a…
To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning
Tian Qin, David Alvarez-Melis, Samy Jelassi +1
Recent advancements in large language models (LLMs) have significantly improved their reasoning abilities, particularly through techniques involving search and backtracking. Backtr…
Random Scaling of Emergent Capabilities
Rosie Zhao, Tian Qin, David Alvarez-Melis +2
Language models famously improve under a smooth scaling law, but some specific capabilities exhibit sudden breakthroughs in performance. Advocates of "emergence" view these capabil…
Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
Tian Qin, Naomi Saphra, David Alvarez-Melis
Early in training, LMs can behave like n-gram models, but eventually they often learn tree-based syntactic rules and generalize hierarchically out of distribution (OOD). We study t…
Transfer RL via the Undo Maps Formalism
Abhi Gupta, Ted Moskovitz, David Alvarez-Melis +1
Transferring knowledge across domains is one of the most fundamental problems in machine learning, but doing so effectively in the context of reinforcement learning remains largely…
Game-Theoretic Interpretability for Temporal Modeling
Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola
Interpretability has arisen as a key desideratum of machine learning models alongside performance. Approaches so far have been primarily concerned with fixed dimensional inputs emp…