12 papers
Organize Primitives into Semantic Parts: Reinforcement Reasoning for 3D Segmentation
Xiaoming Gong, Ruoyu Wu, Zhenhong Sun +5
Primitive-based 3D segmentation offers a compact and explicit alternative to dense surface prediction, naturally supporting structural abstraction and boundary localization. Howeve…
Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization
Xinhao Yang, Wenhao Wu, Ning Lv +5
3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-grained behavioral specificati…
P2Voxel: Pyramid Pivot Voxelization for 3D Mesh Tokenization
Zhenhong Sun, Haozhe Liu, Yifu Wang +6
Triangle meshes provide explicit and accurate surface geometry, yet their irregular topology connectivity makes 3D mesh tokenization a geometric sampling problem: how to sample and…
Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decomposition
Ruoyu Wu, Zhenhong Sun, Xiaoming Gong +5
Accurate 3D part decomposition requires separating shapes into structurally meaningful components with precise boundaries while preserving articulation seams and thin attachments.…
Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs
Zhenhong Sun, Hanqing Zhao, Yatao Bian +7
Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive LLMs, offering efficient generation through block-wise progressive unmasking. Howe…
Social Structure Matters in 3D Human-Human Interaction Generation
Zhongju Wang, Beier Wang, Yatao Bian +6
Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-driven 3D human-human interactio…
3DXTalker: Unifying Identity, Lip Sync, Emotion, and Spatial Dynamics in Expressive 3D Talking Avatars
Zhongju Wang, Zhenhong Sun, Beier Wang +4
Audio-driven 3D talking avatar generation is increasingly important in virtual communication, digital humans, and interactive media, where avatars must preserve identity, synchroni…
StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics
Bingliang Li, Zhenhong Sun, Jiaming Bian +6
Storyboarding is a core skill in visual storytelling for film, animation, and games. However, automating this process requires a system to achieve two properties that current appro…
Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation
Jinmei Liu, Haoru Li, Zhenhong Sun +6
Reinforcement learning (RL) has emerged as a paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and…
Hierarchical and Step-Layer-Wise Tuning of Attention Specialty for Multi-Instance Synthesis in Diffusion Transformers
Chunyang Zhang, Zhenhong Sun, Zhicheng Zhang +5
Text-to-image (T2I) generation models often struggle with multi-instance synthesis (MIS), where they must accurately depict multiple distinct instances in a single image based on c…
Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
Shilin Zhang, Zican Hu, Wenhao Wu +7
Offline meta-RL usually tackles generalization by inferring task beliefs from high-quality samples or warmup explorations. The restricted form limits their generality and usability…
T-S2S: Training-free Triplet Tuning for Sketch to Scene Synthesis in Controllable Concept Art Generation
Zhenhong Sun, Yifu Wang, Yonhon Ng +4
2D concept art generation for 3D scenes is a crucial yet challenging task in computer graphics, as creating natural intuitive environments still demands extensive manual effort in…