Google Research and UNSW Sydney released GlucoFM, a self-supervised foundation model that splits a CGM trace into a slow physiological stream and a…
Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors
arXiv:2608.26175v1 Announce Type: cross Abstract: Extractive prompt compression promises to cut LLM inference costs by removing low-information tokens,…
AI News Brief Hourly Summary 2026-08-28 17h : 12 posts
12 posts published in the last hour 14:32Using Poly-Encoders for Computationally Efficient Automated Creativity Assessment 14:32Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models 14:32From Sound to Symptom: Real-Time Respiratory Signal Understanding for Conversational Healthcare Agents 14:32VFA:…
Using Poly-Encoders for Computationally Efficient Automated Creativity Assessment
arXiv:2608.26165v1 Announce Type: cross Abstract: Automated creativity assessment has been a long standing challenge, with traditional methods often being…
Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models
arXiv:2608.26161v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable capabilities in reasoning and…
From Sound to Symptom: Real-Time Respiratory Signal Understanding for Conversational Healthcare Agents
arXiv:2608.26163v1 Announce Type: cross Abstract: Cough events during live spoken conversations carry clinically valuable respiratory signals, yet…
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation
arXiv:2608.26155v1 Announce Type: cross Abstract: Multimodal large language models have advanced rapidly, yet most remain English-centric, as scaling…
The Local AI Stack for Productive SLMs
A practical framework for choosing the right tools at each layer of your local AI setup, from model serving to context retrieval.
Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation
arXiv:2608.26159v1 Announce Type: cross Abstract: Self-Generated Text Recognition (SGTR)–the ability of an LLM to identify its own outputs–poses risks…
Artificial Intelligence Models Can Predict and Collaboratively Modulate Human Memory Search
arXiv:2608.26152v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit unprecedented natural language generation and many text-based…
Syntax vs. Semantics: How Transformers Learn Deep Dependencies
arXiv:2608.26139v1 Announce Type: cross Abstract: Large Language Models demonstrate remarkable syntactic fluency, yet the optimization dynamics governing…
Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memes
arXiv:2608.26143v1 Announce Type: cross Abstract: Memes have turned out to be a powerful tool through which individuals share their ideas concerning…
Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation
arXiv:2608.26142v1 Announce Type: cross Abstract: Referring Expression Segmentation (RES) aims to generate pixel-wise segmentation masks from complex and…
Evaluating AI Generated Summaries for Cancer Patients
arXiv:2608.26154v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into digital health platforms to generate…
AI News Brief Hourly Summary 2026-08-28 16h : 13 posts
13 posts published in the last hour 13:33FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes 13:33WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution 13:33Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with…
FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
arXiv:2608.26129v1 Announce Type: cross Abstract: Scientific peer review datasets have trained AI systems exclusively on Computer Science and Machine…
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
arXiv:2608.27454v1 Announce Type: new Abstract: Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent…
Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales
arXiv:2608.26125v1 Announce Type: cross Abstract: Online hate against Muslim communities often appears in culturally coded, multilingual forms that evade…