12 papers
Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift
Zitong Huang, Gustavo Lucas Carvalho, Deqing Fu +1
We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is th…
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
Amin Banayeeanzade, Qingchuan Yang, Deqing Fu +6
High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for do…
Value-Aware Stochastic KV Cache Eviction for Reasoning Models
Ting-Yun Chang, Harvey Yiyun Fu, Deqing Fu +3
Reasoning models improve accuracy through extended chains of thought, but their long outputs create a memory and compute bottleneck. KV cache eviction methods reduce this cost by e…
Convergent Evolution: How Different Language Models Learn Similar Number Representations
Deqing Fu, Tianyi Zhou, Mikhail Belkin +2
Language models trained on natural text learn to represent numbers using periodic features with dominant periods at . In this paper, we identify a two-tiered hierarchy…
FoNE: Precise Single-Token Number Embeddings via Fourier Features
Tianyi Zhou, Deqing Fu, Mahdi Soltanolkotabi +2
Large Language Models (LLMs) typically represent numbers using multiple tokens, which requires the model to aggregate these tokens to interpret numerical values. This fragmentation…
Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
Qilin Ye, Deqing Fu, Robin Jia +1
Transformers often fail to learn generalizable algorithms, instead relying on brittle heuristics. Using graph connectivity as a testbed, we explain this phenomenon both theoretical…