arXiv:2608.21209v1 Announce Type: new Abstract: The rise of agentic AI enables LLMs to access diverse user data, raising critical privacy concerns. Prior…
CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models
arXiv:2608.21060v1 Announce Type: new Abstract: Pathology foundation models (PFMs) are increasingly used as general-purpose backbones, yet existing…
Can Legal AI Know When It Is Wrong? And Do Students Know When It Is?
arXiv:2608.21089v1 Announce Type: new Abstract: Integrating Large Language Models (LLMs) into the Indian judiciary promises access to justice but…
When Trust Meets Truth: Trust-Truth Separability in LLM-as-Judge
arXiv:2608.21097v1 Announce Type: new Abstract: LLM-as-Judge systems can produce multi-dimensional evaluations, such as trustworthiness, reliability, and…
XPENG Robotics Raises $900M+ First Round at $6.3B+ Valuation
XPENG’s robotics business has entered share purchase agreements with investors to raise more than US$900 million at a post-money valuation above US$6.3…
Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda
arXiv:2608.21107v1 Announce Type: new Abstract: Large Language Models (LLMs) are moving from code completion toward repository-scale agents that retrieve…
Kids outlearn AI—and we still don’t know why
People have been talking to each other for at least 100,000 years, as best we can tell. And in all that time, there has been only one thing in the world…
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
arXiv:2608.21100v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make…
AI News Brief Hourly Summary 2026-08-24 13h : 14 posts
14 posts published in the last hour 10:33Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflicts 10:33Don’t Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents 10:33Belief Without Behavior: Measuring the Translation of Theory of Mind into…
Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflicts
arXiv:2608.21044v1 Announce Type: new Abstract: Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model…
Don’t Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
arXiv:2608.21027v1 Announce Type: new Abstract: LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use,…
Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models
arXiv:2608.20975v1 Announce Type: new Abstract: Effective social interaction requires agents to translate mental state inferences into coordinated…
When AI Reads Between the Lines: OCR vs. VLMs
Can machines truly understand documents, or have they simply become more effective at extracting information from them? With traditional OCR, an error can…
Evaluating Large Language Model Performance on International Maritime Dangerous Goods Code Compliance
arXiv:2608.21036v1 Announce Type: new Abstract: The transport of dangerous goods by sea is a high-consequence activity governed by the International…
Cerebras unveils CS-4 with double the performance on the same chip
Cerebras has introduced its CS-4 AI accelerator, which CEO Andrew Feldman calls the fastest system in the industry. The article Cerebras unveils CS-4 with…
The Cost of a Physics Prior Is Bounded by the Ablation Gap
arXiv:2608.21059v1 Announce Type: new Abstract: Shape-constrained and physics-informed learning reports an accuracy cost of enforcing a prior and treats…
Generalizing Soft Tissue Deformation and Force Prediction Across Material Stiffness and Geometry
arXiv:2608.20967v1 Announce Type: new Abstract: Accurate soft tissue simulation is essential for surgical training, pre-operative planning, and haptic…
TreeWY: Speculative Verification for Gated DeltaNet Hybrids
arXiv:2608.20961v1 Announce Type: new Abstract: Modern open models are hybrids: most layers are linear-attention (Gated DeltaNet, GDN) layers carrying a…