15 posts published in the last hour 19:32Graphical Design of Interpretable Architectures 19:32SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution 19:32Adobe Firefly adds AI audio tools and Google’s Gemini Omni Flash 19:32Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets 19:32Google gives…
Graphical Design of Interpretable Architectures
arXiv:2608.18936v1 Announce Type: cross Abstract: Designing, implementing, and comparing interpretable architectures requires a formal language to…
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
arXiv:2608.18933v1 Announce Type: cross Abstract: Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software…
Adobe Firefly adds AI audio tools and Google’s Gemini Omni Flash
Adobe is making three AI audio tools broadly available in Firefly. Generate Music, Generate Speech, and Generate Sound Effects create royalty-free music,…
Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets
arXiv:2608.18907v1 Announce Type: cross Abstract: Small-scale image classification is often limited by the scarcity of training data. Generative data…
Google gives publishers a new way to fight AI-driven traffic losses
Google is giving publishers a new button that lets readers make them a preferred source across Search, Discover, and Google News, potentially boosting…
SMTrap: Cost-Effective DoS Attacks Against Large Reasoning Models via SMT Conflict Guidance
arXiv:2608.18921v1 Announce Type: cross Abstract: Existing LRM-DoS methods rely heavily on model feedback to synthesize attack queries, requiring either…
Runlayer, Rippling drop lawsuits. But the brouhaha is still a cautionary tale for founders.
Runlayer and Rippling have dropped their lawsuits. No money was paid. Rippling celebrated by releasing a competing product.
Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
arXiv:2608.18931v1 Announce Type: cross Abstract: Test-time scaling (TTS) improves language model outputs by spending additional inference compute -…
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…
AI News Brief Hourly Summary 2026-08-20 21h : 18 posts
18 posts published in the last hour 18:32Forgetting, plasticity, and co-observation: a third facet of continual learning 18:32Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study 18:32Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening…
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…