3 papers
cs.CL2026
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
Wei Liu, Hongkai Liu, Zhiying Deng +2
LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the target vector to multiple pr…
stat.ML2025
Rao-Blackwellised Reparameterisation Gradients
Kevin H. Lam, Thang D. Bui, George Deligiannidis +1
Latent Gaussian variables have been popularised in probabilistic machine learning. In turn, gradient estimators are the machinery that facilitates gradient-based optimisation for m…
cs.CL2025
Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents
Dongjun Lee, Juyong Lee, Kyuyoung Kim +4
Recent advances in large language models (LLMs) have led to a growing interest in developing LLM-based agents for automating web tasks. However, these agents often struggle with ev…