arXiv:2608.18931v1 Announce Type: cross Abstract: Test-time scaling (TTS) improves language model outputs by spending additional inference compute -…
Category: AI
A strengthening of the MCFL-ness of $O_2$
arXiv:2608.18813v1 Announce Type: cross Abstract: In the last years, a number of proofs of the fact that $O_2$ is a multiple context-free grammar (MCFG)…
Understanding Multilingual Medical ASR Adaptation Through Layer-Wise Analysis
arXiv:2608.18825v1 Announce Type: cross Abstract: Medical automatic speech recognition (MedASR) requires adaptation to specialised terminology, limited…
Do Large Language Models Hallucinate Electric Fata Morganas?
arXiv:2608.18816v1 Announce Type: cross Abstract: AI hallucinations – that is, outputs which are made up, cannot be verified, or contradict the source…
MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models
arXiv:2608.18827v1 Announce Type: cross Abstract: Reward function design remains a bottleneck in reinforcement learning. While large language models…
Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs
Three ~300M drafters bring speculative decoding to LFM2.5, delivering up to 3.18x faster decoding with identical greedy output.
Identifying Implicit Premises for Logical Reconstruction of Argument Graphs
arXiv:2608.18821v1 Announce Type: cross Abstract: The logical reconstruction of argument graphs from natural language text is challenging because of the…
Forgetting, plasticity, and co-observation: a third facet of continual learning
arXiv:2608.18803v1 Announce Type: cross Abstract: Efficient continual learning remains a fundamental challenge for deep neural networks. While…
Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study
arXiv:2608.18795v1 Announce Type: cross Abstract: Majority voting over multiple LLM samples is widely used to raise answer accuracy, yet its gain varies…
Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening
arXiv:2608.18759v1 Announce Type: cross Abstract: Fairness in medical imaging is commonly evaluated through subgroup performance metrics, yet it remains…