9 accepted papers
While reinforcement learning (RL) has proven highly effective for general reasoning in vision-language models, its application to tasks requiring deep understanding of information-rich images and structured output generation remains underexplored. Chart-to-code generation exemplifies this challenge,…
Multimodal large language models are progressively advancing toward multimodal agents that can proactively execute tasks. Existing research on multimodal agents primarily targets either GUI or embodied scenarios, corresponding to interactions within 2D virtual world and 3D physical world, respective…
Reading text from images or scanned documents via OCR models has been a longstanding focus of researchers. Intuitively, text reading is perceived as a straightforward perceptual task, and existing work primarily focuses on constructing enriched data engineering to enhance SFT capabilities. In this w
Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI planning, which requires more sophisticated data collection. In reality, the exploration process of a CUA across apps/des…
In language-guided visual navigation, agents locate target objects in unseen environments using natural language instructions. For reliable navigation in unfamiliar scenes, agents should possess strong perception, planning, and prediction capabilities. Additionally, when agents revisit previously ex…
Recently, robotics has advanced significantly through the integration of larger models and large-scale datasets. However, challenges remain in applying these models to 3D spatial interactions and managing data collection costs. To address these issues, we propose the multimodal robotic manipulation…
Drones have been increasingly used in various domains, including ecological monitoring in forests. However, the endurance and noise of drones have limited their deployment to short flight missions above canopies. To address these limitations, we introduce ALBERO: a framework comprising a mechanical
In this letter, we propose a novel Grasp Pose Domain Adaptation Network (GPDAN) to achieve sim-to-real domain adaptation for 6-DoF grasp pose detection. The main task of GPDAN is to detect feasible 6-DoF grasp poses in cluttered scenes. A point-wise self-supervised domain classification module with
In this paper, we propose a novel Voting based Grasp Pose Network (VGPN) to detect 6-DoF grasps in cluttered scenes. The motivation of this paper is that local object geometry can provide useful clues about where the object can be grasped. Generated by the sampled seed points from raw point cloud, t…