9 papers
PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation
Zhe Zhu, Yiheng Zhang, Peng Li +9
Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies, but existing approaches typi…
OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
Qinglin Ye, Zhiyuan Gu, Jingjie Xia +6
Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers a promising direction, but suffers from two issues…
ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields
Yiheng Zhang, Yiming Wang, Kaiyan Zhao +3
Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment, yet its hard-clipping mechanism and unconstrained alternatives (e.g., SPO) sit at two extreme…
Anon: Extrapolating Adaptivity Beyond SGD and Adam
Yiheng Zhang, Kaiyan Zhao, Shaowu Wu +5
Adaptive optimizers such as Adam and non-adaptive methods like SGD exhibit distinct generalization capabilities across different architectures. Prior tunable optimizers attempt to…
Corrective Diffusion Language Models
Shuibai Zhang, Fred Zhangzhi Peng, Yiheng Zhang +2
While Diffusion Language Models (DLMs) are theoretically well-suited for iterative refinement due to their non-causal structure, they often fail to reliably revise incorrect tokens…
HVAdam: A Full-Dimension Adaptive Optimizer
Yiheng Zhang, Shaowu Wu, Yuanzhuo Xu +4
Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However, they often generalize worse th…
FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
Tingrui Shen, Yiheng Zhang, Chen Tang +6
Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practi…
LSS3D: Learnable Spatial Shifting for Consistent and High-Quality 3D Generation from Single-Image
Zhuojiang Cai, Yiheng Zhang, Meitong Guo +2
Recently, multi-view diffusion-based 3D generation methods have gained significant attention. However, these methods often suffer from shape and texture misalignment across generat…
PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data
Zhe Zhu, Le Wan, Rui Xu +6
Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-wo…