17 citations · 42 across the 15 of their papers we have counts for
6 papers · 1 filter
TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition
Ningyuan Xi, Hao Xu, Hongsheng Xin +1
Large language models (LLMs) have made remarkable progress in reasoning tasks, largely driven by post-training paradigms, especially reinforcement learning with verifiable rewards…
Verifier-Backed Hard Problem Generation for Mathematical Reasoning
Yuhang Lai, Jiazhan Feng, Yee Whye Teh +1
Large Language Models (LLMs) demonstrate strong capabilities for solving scientific and mathematical problems, yet they struggle to produce valid, challenging, and novel problems -…
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Xuan Yang, Jiayu Liu, Yuhang Lai +3
Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated…
Linear Dynamics in the RLVR Training of Large Language Models
Tianle Wang, Jiayu Liu, Zhongyuan Wu +4
Reinforcement learning with verifiable rewards (RLVR) has driven significant performance gains in reasoning-oriented large language models (LLMs), yet its internal training dynamic…
Learning Instance-Specific Augmentations by Capturing Local Invariances
Ning Miao, Tom Rainforth, Emile Mathieu +4
We introduce InstaAug, a method for automatically learning input-specific augmentations from data. Previous methods for learning augmentations have typically assumed independence b…
Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
Wenxian Shi, Hao Zhou, Ning Miao +1
Deep generative models are commonly used for generating images and text. Interpretability of these models is one important pursuit, other than the generation quality. Variational a…