17 papers
Magpie: Real-Time World Renderer for Interactive Games
Xiaoyu Zhan, Xinyu Wang, Xiaohong Zhang +6
Modern game development relies heavily on conventional graphics pipelines. High-quality visual content requires modeling, material authoring, animation, lighting, effects, and runt…
MoGeFlow: Flowing Through Motion Codebook Geometry for Text-to-Motion Generation
Pengcheng Fang, Tengjiao Sun, Xiaoyu Zhan +2
Vector-quantized tokenizers have become the dominant interface for text-to-motion generation, and the priors built on them treat motion codes as unordered categorical labels. We sh…
AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding
Yingxuan Ren, Yuxuan Lou, Yong Liu +4
Block-wise semi-autoregressive decoding is the standard inference paradigm for diffusion large language models (DLMs), but it imposes a strict dependency between blocks: the next b…
KV-Control: Parameter-Efficient K/V Injection for Trajectory-Controlled Text-to-Motion
Tengjiao Sun, Pengcheng Fang, Xiaoyu Zhan +4
Text-conditioned 3D human motion models now synthesize plausible motions from prompts, but practical animation and embodied-agent workflows rarely stop at text: a character may nee…
SO-Mamba: State-Ownership Mamba for Unrolled MRI Reconstruction
Pengcheng Fang, Hongli Chen, Fangfang Tang +3
Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State-space models such as Mamba…
SCAMP: Sparse-anchor Control is One Small Projection
Pengcheng Fang, Tengjiao Sun, Dongjie Fu +4
Authoring with a text-to-motion generator needs sparse anchors: chosen joints, at chosen frames, at given positions. Meeting them currently costs a conditioning branch trained for…
UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars
Xiaoyu Zhan, Xinyu Fu, Chenghao Yang +9
Speech-driven gestures and facial animations are fundamental to expressive digital avatars in games, virtual production, and interactive media. However, existing methods are either…
CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators
Pengcheng Fang, Hongli Chen, Yuxia Chen +3
Spectral token mixers based on Fourier transforms provide an efficient way to model global interactions in visual feature maps. Existing designs often either apply filter-wise spec…
Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
Jiaxin Liu, Ding Zhong, Yue Wang +6
Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wide range of multimodal reason…
Privileged Foresight Distillation: Zero-Cost Future Correction for World Action Models
Pengcheng Fang, Hongli Chen, Xiaohao Cai
World action models jointly predict future video and action during training, raising an open question about what role the future-prediction branch actually plays. A recent finding…
MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding
Pengcheng Fang, Yuxia Chen, Xiaohao Cai
Video temporal grounding (VTG) aims to localize the start and end timestamps of the event described by a given query within an untrimmed video. Despite the strong open-world video…
HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction
Pengcheng Fang, Hongli Chen, Guangzhen Yao +5
Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence. We present HiFi-MambaV2, a…
MotionDuet: Dual-Conditioned 3D Human Motion Generation with Video-Regularized Text Learning
Yi-Yang Zhang, Tengjiao Sun, Pengcheng Fang +4
3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work…
Diffusion-grounded VideoLLM for Entity-aware temoporal grounding
Pengcheng Fang, Yuxia Chen, Yong Wang +3
Precise temporal grounding requires distinguishing when a queried event occurs from when its participating entities are merely visible. We propose Diffusion-Grounded VideoLLM, whic…
GRASPTrack: Geometry-Reasoned Association via Segmentation and Projection for Multi-Object Tracking
Xudong Han, Pengcheng Fang, Yueying Tian +4
Multi-object tracking (MOT) in monocular videos is fundamentally challenged by occlusions and depth ambiguity, issues that conventional tracking-by-detection (TBD) methods struggle…
HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI Reconstruction
Hongli Chen, Pengcheng Fang, Yuxia Chen +6
Reconstructing high-fidelity MR images from undersampled k-space data remains a challenging problem in MRI. While Mamba variants for vision tasks offer promising long-range modelin…
MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation
Dongjie Fu, Tengjiao Sun, Pengcheng Fang +2
Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Nevertheless, jointly achieving high fidel…