arXiv:2608.12299v1 Announce Type: cross Abstract: Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable…
Author: script
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
arXiv:2608.12307v1 Announce Type: cross Abstract: Recent work on distillation transfers the capabilities of large models to smaller ones often by updating…
Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence
arXiv:2608.12290v1 Announce Type: cross Abstract: Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation,…
Redistribution-based Cost Inference Improves Sparse Safe Offline RL
arXiv:2608.12306v1 Announce Type: cross Abstract: Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors…
Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages
arXiv:2608.12278v1 Announce Type: cross Abstract: Artificial intelligence tools for education and language support are increasingly framed as scalable…
Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
arXiv:2608.12273v1 Announce Type: cross Abstract: LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection…
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
arXiv:2608.12253v1 Announce Type: cross Abstract: Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language…
How OneAdvanced deployed over 50 AI agents on UK-sovereign AWS
Learn how OneAdvanced, a UK enterprise software provider, built a UK-sovereign AI platform by self-hosting Llama 4 Maverick and Llama Guard 4 on Amazon…
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
arXiv:2608.12246v1 Announce Type: cross Abstract: Evaluating security vulnerability detection tools requires benchmark datasets with…
Putting sign language AI into users’ hands
Introducing sign-language-to-text (SL2T), our breakthrough model powering new sign language features for Deaf and hard of hearing users.