12 papers
Show, Don't Tell: Morphing Latent Reasoning into Image Generation
Harold Haodong Chen, Xinxiang Yin, Wen-Jie Shu +6
Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation--a hallmark of human…
Human detectors are surprisingly powerful reward models
Kumar Ashutosh, XuDong Wang, Xi Yin +4
Video generation models have recently achieved impressive visual fidelity and temporal coherence. Yet, they continue to struggle with complex, non-rigid motions, especially when sy…
Enhancing Zero-Shot Time Series Forecasting in Off-the-Shelf LLMs via Noise Injection
Xingyou Yin, Ceyao Zhang, Min Hu +1
Large Language Models (LLMs) have demonstrated effectiveness as zero-shot time series (TS) forecasters. The key challenge lies in tokenizing TS data into textual representations th…
FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI
Yuhang Peng, Yizhou Pan, Xinning He +6
As embodied intelligence emerges as a core frontier in artificial intelligence research, simulation platforms must evolve beyond low-level physical interactions to capture complex,…
KPLM-STA: Physically-Accurate Shadow Synthesis for Human Relighting via Keypoint-Based Light Modeling
Xinhui Yin, Qifei Li, Yilin Guo +2
Image composition aims to seamlessly integrate a foreground object into a background, where generating realistic and geometrically accurate shadows remains a persistent challenge.…
HGC-Avatar: Hierarchical Gaussian Compression for Streamable Dynamic 3D Avatars
Haocheng Tang, Ruoke Yan, Xinhui Yin +5
Recent advances in 3D Gaussian Splatting (3DGS) have enabled fast, photorealistic rendering of dynamic 3D scenes, showing strong potential in immersive communication. However, in d…