AI Research Highlights

Adriana Aida, Walida Amer, Katarina Bankovic et al.

Introduces Cortex 2.0, a world model for industrial robotics that plans over futures rather than reacting to observations. Enables reliable long-horizon robotic manipulation across changing conditions.

Nattavudh Powdthavee

LLMs detect fraud better than humans and resist investor bias, challenging assumptions about AI limitations. This means AI advisors could be more reliable in high-stakes financial decisions.

Jingyi Zheng, Tianyi Hu, Yule Liu et al.

Creates the first benchmark dataset for detecting covert advertisements on social media, addressing a critical gap in content moderation and enabling better evaluation of multimodal AI systems.

Tianle Zhang, Zhihao Yuan, Dafeng Chi et al.

Introduces JoyAI-RA, a vision-language-action foundation model that enhances robotic autonomy through improved generalization across diverse robotic embodiments and tasks.

Ryo Tamura, Haruhiko Morito, Yuna Oikawa et al.

Demonstrates LLMs can guide high-throughput experiments for phase diagram construction, significantly accelerating materials discovery workflows.

Jan-Philipp Schmidt

Presents ActuBench, a multi-agent LLM pipeline for generating and evaluating actuarial reasoning tasks, enabling automated, curriculum-aligned assessment item creation and validation.

Yilun Liu, Chunguang Zhao, Mengyao Piao et al.

Comprehensive benchmark evaluating LLM multilingual and multicultural capabilities with deep cultural analysis, essential for developing globally competent AI systems.

Yupeng Zheng, Xiang Li, Songen Gu et al.

Presents a lightweight VLA model with world knowledge integration for efficient robot manipulation, enhancing spatial reasoning and task execution in compact robotic systems.

Mikko Lempinen, Joni Kemppainen, Niklas Raesalmi

Provides a modular framework for identifying and evaluating AI security vulnerabilities, helping developers build more robust and safer AI systems in critical applications.

Yuxuan Xue, Ruofan Liang, Egor Zakharov et al.

Presents GeoRelight, a unified framework for joint geometrical relighting and 3D reconstruction using diffusion transformers, improving physical consistency and reducing error accumulation in single-image relighting.

Peng Peng, Weiwei Lin, Wentai Wu et al.

Proposes HaS, a speculative retrieval method that accelerates RAG systems by leveraging homology-aware caching, reducing latency without accuracy loss in large-scale knowledge retrieval.

Vasundra Srinivasan

Proposes stateless decision memory for regulated enterprise AI agents. Enables scalable, auditable, and compliant long-horizon decision-making in sensitive domains.

Aimin Zhang, Jiajing Guo, Fuwei Jia et al.

Presents EvoAgent, an evolvable LLM agent framework with structured skill learning and hierarchical delegation that enables continuous capability improvement through user feedback and multi-agent collaboration.

William Scarbro, Ravi Mangal

Provides safety shielding for autonomous agents with imperfect perception, using confidence intervals to block potentially unsafe actions.

An T. Le, Vien Ngo

Presents AAC, a differentiable landmark compressor for ALT heuristics that guarantees admissibility by design, enabling reliable pathfinding without calibration or convergence requirements.