arXiv AI
PSGAgent: Enhancing MLLMs' Dynamic Visual Perception for Panoptic Scene Graph Generation via Agentic Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 25
Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
arXiv AI
Sep 28
Skip the Talk, Re-Focus on Vision: Latent Reasoning for Reasoning Segmentation in Multimodal Large Language Models
The paper introduces LIRSeg, a method that replaces explicit Chain-of-Thought reasoning in multimodal large language models with a compact set of learnable latent tokens for reasoning segmentation. LIRSeg is trained in two stages—spatial alignment and GRPO—while employing extreme-advantage sampling, decoupled exploration-stability updates, and latent diversity amplification to enhance token informativeness. Experiments show that LIRSeg improves segmentation accuracy and reasoning efficiency, achieving significant gIoU gains over the VisionReasoner baseline and reducing reasoning tokens by about 16×.
arXiv AI
Jun 4
CR-Seg: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation
arXiv:2606. 03564v2 Announce Type: replace-cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning.
arXiv AI
Jun 2
LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models
arXiv:2603. 00171v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by actively exploring image details.
arXiv AI
Jun 3
\textsc{CR-Seg}: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation
arXiv:2606. 03564v1 Announce Type: cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning.
arXiv AI
Jun 16
Thinking with Visual Grounding
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.