arxiv arXiv cs.AI · 52d ago · research

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

from English

OneCanvas enables 3D scene understanding in Vision-Language Models by aggregating patch features onto a panoramic canvas using 3D world coordinates. It achieves state-of-the-art results on SQA3D and VSI-Bench, with strong generalization on SPBench, using significantly less training compute than prior methods.

Importance 3/3 Beats a top-lab benchmark New feature vs. leaders arXiv cs.AI Google DeepMind Mistral AI OpenAI AI agents Multimodal Reasoning models

Read original

arxiv arXiv cs.AI · 51d ago · 2 views

Dual-Agent Framework for Cross-Model Verified Translation

A dual-agent framework converts natural-language experiment protocols into executable commands for robotic lab platforms. It uses a Parser Agent and a rule-based mapping engine to translate protocols, with a heterogeneous LLM Validation Agent ensuring accuracy and triggering self-correction. The framework successfully enables end-to-end autonomous execution of microplate-based experiments like the Bradford assay.

arxiv arXiv cs.LG · 52d ago

ViGOS: Decoupling Perception and Reasoning in Multimodal On-Policy Self-Distillation

ViGOS introduces a visually grounded on-policy self-distillation framework for multimodal large language models. It decouples perception and reasoning by using an image-only teacher for visual descriptions and a reasoning teacher for final outputs, reducing reliance on text-only references. This approach improves image-grounded performance across multiple vision-language benchmarks.

arxiv arXiv cs.AI · 52d ago

ThinkDeception: Interpretable Multimodal Deception Detection Framework

ThinkDeception introduces a progressive reinforcement learning framework that enables interpretable multimodal deception detection. It leverages a step-by-step annotated Chain of Thought dataset and proposes Visual-Audio Consistency Group Relative Policy Optimization with a dynamic curriculum, enhancing reasoning quality and outperforming existing methods on mainstream benchmarks.

arxiv arXiv cs.AI · 53d ago

WEQA: Wearable Health Question Answering with Query-Adaptive Agentic Reasoning

WEQA introduces a query-adaptive agent framework that combines language models with specialized wearable data analysis tools. It outperforms LLM and agentic baselines by 24% in accuracy and demonstrates improved usefulness and clinical soundness in expert and user evaluations.

arxiv arXiv cs.AI · 53d ago

LEADS: Agentic Discovery of Hybrid Models for Cardiac Electrophysiology

LEADS proposes a framework that uses an LLM agent to discover hybrid cardiac electrophysiology models through an iterative reasoning-and-action loop. It formulates domain knowledge as a structured action space, enabling physically grounded, interpretable, and numerically stable model designs, outperforming both human-designed and other LLM-based approaches on synthetic and real cardiac data.