arXiv:2608.15621v1 Announce Type: new Abstract: Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and…
Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds
arXiv:2608.15619v1 Announce Type: new Abstract: Emotion recognition from text keeps improving on benchmarks, yet whether an accuracy ceiling has been…
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
arXiv:2608.15600v1 Announce Type: new Abstract: The widespread circulation of abusive online content has increased the need for reliable moderation of…
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
arXiv:2608.15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are…
Argumentation for Common Ground: Finding Zones of Possible Agreement between Individuals in Conflict
arXiv:2608.15634v1 Announce Type: new Abstract: How can common ground between societies in conflict be identified when citizens’ acceptability of peace…
AI News Brief Hourly Summary 2026-08-18 18h : 14 posts
14 posts published in the last hour 15:33Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling 15:33ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search 15:33Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM…
Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling
arXiv:2608.15565v1 Announce Type: new Abstract: Experience-learning agents for optimization modeling improve by storing verified skills, but existing…
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search
arXiv:2608.15546v1 Announce Type: new Abstract: Most LLM-based automated algorithm design methods optimize a designated component within a human-specified…
Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
arXiv:2608.15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the…
Edcafe AI Review: The Teacher Tool That’ll Save Your Sunday
Ask any teacher what actually eats their time, and it’s rarely the hours in front of students. It’s everything that happens before and after: building a…
When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction
arXiv:2608.15592v1 Announce Type: new Abstract: Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and…
Perplexity’s Free Airtel Year Ends, and Its India Revenue Climbs
Perplexity’s year-long bet on free access in India is starting to show its return. The AI search company’s in-app revenue in the country rose roughly 60%…
From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM
arXiv:2608.15580v1 Announce Type: new Abstract: Reliable endoscopic polyp reporting requires integrating quantitative lesion sizing, standardized Paris…
Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation
arXiv:2608.15510v1 Announce Type: new Abstract: Chart-to-code generation requires a model to read the fine-grained visual details of a chart and write…
From Contexts to Values: Context-Dependent Defeat in Abstract Argumentation
arXiv:2608.15536v1 Announce Type: new Abstract: In value-based argumentation, an audience’s ordering of values decides which attacks succeed as defeats.…
Dynamic Multi-Byte Prediction With Hierarchical Language Models
arXiv:2608.15454v1 Announce Type: new Abstract: Byte-level hierarchical language models (LMs) have recently emerged as a robust alternative to their…
EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints
arXiv:2608.15502v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high…
OpenAI president urges enterprises to hasten AI security defences
OpenAI president and co-founder Greg Brockman warns that enterprise security teams face a compressed timeline to adopt AI defences. Brockman has published…