Search AEX CONTINUUM

Titles, abstracts, authors, keywords and DOIs across all five collections.

PreprintsShort CommunicationNot peer reviewed

Speculative Decoding Under Memory Constraints

Version 1 · 5 November 2026 · 10.xxxx/ctm.pp.2026.0009

Speculative decoding accelerates generation by letting a small draft model propose tokens that a larger model verifies, but the draft model competes with the target model for scarce memory on edge devices. We characterise the trade-off between draft-model size, speed-up and memory footprint, and propose a draft that shares the target model's embedding table and lower layers. The shared draft reduces extra memory from 11% to 3% of the target model and retains 88% of the speed-up of an independent draft.

Abstract PDF 437 1210 cited

PreprintsShort CommunicationNot peer reviewed

Cheap Reward Models for Small-Scale RLHF Experiments

Jonas Berg, Anders Holm

Version 1 · 29 October 2026 · 10.xxxx/ctm.pp.2026.0008

Preference-based fine-tuning is expensive to study because reward models are large. We show that a reward model distilled to 1% of the size of the original recovers 94% of its ranking accuracy on held-out preference pairs, and that policies trained against the small model transfer to the large one with a modest loss. The result lowers the cost of reward-modelling experiments for groups with limited compute.

Abstract PDF 1,480 5120 cited

PreprintsShort CommunicationNot peer reviewed

Calibrated Uncertainty in Retrieval-Augmented Generation

Amélie Roussel, Tomás Ibarra

Version 2 (updated) · 5 June 2026 · 10.xxxx/ctm.pp.2026.0001

Retrieval-augmented generation grounds answers in retrieved documents, yet models remain over-confident when the retrieved evidence is irrelevant or contradictory. We propose a lightweight confidence estimator that combines the generator's token probabilities with a retrieval-agreement score, and calibrate it with temperature scaling on a small validation set. On three question-answering datasets the estimator lowers expected calibration error from 0.19 to 0.06 and enables selective answering: abstaining on the 20% least confident questions raises accuracy from 71% to 84%. The method needs no model retraining.

Abstract PDF 2,718 9043 cited