2 citations · 3 across the 8 of their papers we have counts for
8 papers
MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models
Yue Wu, Changyuan Wang, Zixuan Wang +2
Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution heterogeneity and disparate outli…
Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Shiyi Zhang, Yiji Cheng, Tiankai Hang +8
Unified multi-modal understanding/generative models have shown improved image editing performance by incorporating fine-grained understanding into their Chain-of-Thought (CoT) proc…
ChatUMM: Robust Context Tracking for Conversational Interleaved Generation
Wenxun Dai, Zhiyuan Zhao, Yule Zhong +12
Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent…
RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models
Bowen Zhang, Yiji Cheng, Chunyu Wang +6
We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image. Existing methods fail to capture intricate details such as hairstyles which we tackle in this…
ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
Zifeng Gao, Guanxing Lu, Tianxing Chen +5
Diffusion models have been verified to be effective in generating complex distributions from natural images to motion trajectories. Recent diffusion-based methods show impressive p…
MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
Wenxun Dai, Ling-Hao Chen, Jingbo Wang +3
This work introduces MotionLCM, extending controllable motion generation to a real-time level. Existing methods for spatial-temporal control in text-conditioned motion generation s…
GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
Bowen Zhang, Yiji Cheng, Jiaolong Yang +5
We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling. Existing radiance representations either requ…
Plan, Posture and Go: Towards Open-World Text-to-Motion Generation
Jinpeng Liu, Wenxun Dai, Chunyu Wang +3
Conventional text-to-motion generation methods are usually trained on limited text-motion pairs, making them hard to generalize to open-world scenarios. Some works use the CLIP mod…