Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Dynamic Latent Routing
Fangyuan Yu, Xin Su, Amir Abdullah
We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and pro…
cs.LG2026
Spectral Superposition: A Theory of Feature Geometry
Georgi Ivanov, Narmeen Oozeer, Shivam Raval +3
Neural networks represent more features than they have dimensions via superposition, forcing features to share representational space. Current methods decompose activations into sp…
cs.LG2025
Interpreting Learned Feedback Patterns in Large Language Models
Luke Marks, Amir Abdullah, Clement Neo +4
Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferen…