Topic
manipulation
New AI Model Lets Robots Grasp Objects Like Humans Using RGB-D Data
Researchers introduce HUG, a flow-matching AI model that generates diverse human grasps for any object from a single RGB-D image. Trained on the 1M-HUGs egocentric dataset of 1 million frames from human grasp demonstrations, HUG outperforms state-of-the-art baselines by 23% and 34% on a challenging benchmark, enabling zero-shot grasping for multi-fingered robots.
IMPACTeen Dataset Provides New Resource for Detecting Manipulation in Teen Communication
Researchers have released IMPACTeen, a dataset of 1,021 textual social influence scenarios in adolescent contexts. Annotated by teenagers, parents, psychologists, communication experts, and teachers, it supports training AI models to detect manipulation, persuasion, and their consequences. The dataset, available in Polish and English, aims to advance research in social influence detection and language model safety.
EV-WM: Event-Verified World Models Boost Long-Horizon Robotic Manipulation for Industrial Automation
A research paper introduces EV-WM, a predicate-grounded verification framework for world-model planning in robotic manipulation. By decoding candidate futures into structured event states and scoring them on task-progress, semantic-consistency, physical-feasibility, and uncertainty, EV-WM makes long-horizon planning more interpretable and aligned with task goals. The approach shows promising results in navigation, deformable-object handling, and contact-sensitive tasks, suggesting potential for supply chain and logistics automation.
New Attack Forces Costly Model Usage in Multimodal LLM Cascades
A research paper introduces the Forced Deferral Attack (FDA), which manipulates confidence thresholds in multimodal large language model cascades, causing queries to be routed to more expensive strong models. The attack raises security concerns for enterprises deploying cost-optimized AI systems.