Multi-turn visual search agents answer questions about high-resolution images by iteratively deciding where to look. Reinforcement learning for these agents rewards only the final answer, leaving the search process unsupervised. Consequently, faulty routes in which the reasoning process is erroneous yet the final resul...
Zhangquan Chen, Yao-Xin Niu, Xiang An et al.· 0 citations
Spatial-OPSD, a label-free self-improvement framework that instead exploits spatial structure naturally available from perception and reconstruction tools, is introduced, achieving the highest average among the open models and the best results on three of five spatial reasoning benchmarks.
Zhen-Yu Liu, Zhangquan Chen, Ke-Yi Chen et al.· 0 citations
EviViT, a lightweight attachment that learns where a pretrained vision transformer should acquire detail, is introduced, a lightweight attachment that learns where a pretrained vision transformer should acquire detail without refitting.
Yao-Xin Niu, Zhangquan Chen, Yang Zhang et al.· 0 citations
Text-to-music language models begin with a choice usually made by default: how to tokenize music, and the ordering is clean and surprising: representation, not model size, is the binding variable for distributional fidelity.
Junhao Chen, Ming-Jin Chen, Jingjia Mao et al.· 1 citation
Editable 3D scene creation requires object instances and lights that can be inspected, moved, and imported into standard engines, yet existing single-image methods largely stop at room-scale geometry, baked/global illumination, or text-driven generation. We introduce Lumera (Light-aware Unified Engine-native Reconstruc...
This work presents the first system that, from a single illustration, generates all the structured information a Live2D runtime consumes: ordered RGBA layers, a deformation mesh per layer, and the parameter-driven keypose vertex offsets that make the character move.
Junhao Chen, Jingjia Mao, Dayong Li et al.· arXiv.org· 0 citations
D, a reference-guided renderer that extends Wan2.2 camera control from Plucker rays alone to a joint camera-plus-geometry interface and projects a neural 4D G-buffer from the animated mesh and injects it through a widened control adapter while preserving the pretrained image-to-video prior, supporting tracking+world-po...
Junhao Chen, Mingjin Chen, Henghaofan Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
