12 citations · 67 across the 68 of their papers we have counts for
11 papers · 2 filters
On the geometry and topology of representations: the manifolds of modular addition
Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer +4
The Clock and Pizza interpretations, associated with architectures differing in either uniform or learnable attention, were introduced to argue that different architectural designs…
Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations
Shuyuan Zhang, Zihan Wang, Xiao-Wen Chang +1
The integration of graphs with Goal-conditioned Hierarchical Reinforcement Learning (GCHRL) has recently gained attention, as intermediate goals (subgoals) can be effectively sampl…
RL Fine-Tuning Heals OOD Forgetting in SFT
Hangzhan Jin, Sitao Luan, Tianwei Ni +5
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remain…
Relative Trajectory Balance is equivalent to Trust-PCL
Tristan Deleu, Padideh Nouri, Yoshua Bengio +1
Recent progress in generative modeling has highlighted the importance of Reinforcement Learning (RL) for fine-tuning, with KL-regularized methods in particular proving to be highly…
Capacity-Constrained Continual Learning
Zheng Wen, Doina Precup, Benjamin Van Roy +1
Any agents we can possibly build are subject to capacity constraints, as memory and compute resources are inherently finite. However, comparatively little attention has been dedica…
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
Samin Yeasar Arnob, Zhan Su, Minseon Kim +6
Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstrea…