2 citations · 8 across the 46 of their papers we have counts for
6 papers · 1 filter
JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
Zheyuan Zhang, Suyu Ye, Nakul Agarwal +5
World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during…
Minimally Invasive Steering of Language Models
Taha Entesari, Jingyu Zhang, Daniel Khashabi +1
Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the…
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Zheyuan Zhang, Alvin Zhang, Daniel Khashabi +1
Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we introduce long-horizon memoriz…
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
Arda Uzunoglu, Alvin Zhang, Daniel Khashabi
Weak-to-strong generalization studies how to improve a strong student using supervision from a weaker teacher when reliable labels are scarce. We view this primarily as a data sele…
Genomic Next-Token Predictors are In-Context Learners
Nathan Breslow, Aayush Mishra, Mahler Revsine +3
In-context learning (ICL) -- the capacity of a model to infer and apply abstract patterns from examples provided within its input -- has been extensively studied in large language…
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Aayush Mishra, Daniel Khashabi, Anqi Liu
Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapt…