9 papers · 1 filter
RegionReasoner: Region-Grounded Multi-Round Visual Reasoning
Wenfang Sun, Hao Chen, Yingjun Du +2
Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to…
Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
Zihui Gao, Ke Liu, Donny Y. Chen +5
Geometric foundation models show promise in 3D reconstruction. However, their progress is severely constrained by the scarcity of diverse, large-scale 3D annotations. While static-…
AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation
Jin-Chuan Shi, Binhong Ye, Tao Liu +6
Reconstructing dynamic hand-object interactions from monocular videos is critical for dexterous manipulation data collection and creating realistic digital twins for robotics and V…
CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
Wenxin Ma, Chenlong Wang, Ruisheng Yuan +6
Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, curr…
GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
Mingyu Liu, Zheng Huang, Xiaoyi Lin +6
Vision-language models demonstrate strong reasoning and planning abilities, yet grounding these predictions into precise robot actions remains a central challenge. Existing Vision-…
HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
Cong Chen, Ziyuan Huang, Cheng Zou +6
In this work, we present HieraTok, a novel multi-scale Vision Transformer (ViT)-based tokenizer that overcomes the inherent limitation of modeling single-scale representations. Thi…
Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
Canyu Zhao, Xiaoman Li, Tianjian Feng +3
We introduce Tinker, a versatile framework for high-fidelity 3D editing that operates in both one-shot and few-shot regimes without any per-scene finetuning. Unlike prior technique…
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
Hao Zhong, Muzhi Zhu, Zongze Du +6
Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution fra…
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
Muzhi Zhu, Hao Zhong, Canyu Zhao +9
Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information. It is a critical component of effic…