11 citations · 16 across the 22 of their papers we have counts for
26 papers
AVC-Reward: Event-Centric Audio-Video Consistency Evaluation
Yuruo Wu, Kaihang Pan, Kai Shen +6
As joint audio-video generation models become more capable, they can generate audio-visual scenes exhibiting three forms of complexity: multi-event composition, multi-layer audio m…
Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training
Shuyuan Tu, Qi Tian, Yinming Huang +8
Natively training joint video-audio generation models at higher resolutions empowers them to learn richer visual details and sharper motion dynamics. However, full attention incurs…
VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation
Yinming Huang, Shuyuan Tu, Xi Yan +6
Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual…
Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents
Jiahe Ying, Wendong Bu, Kaihang Pan +6
Achieving virtual agents capable of automating tasks across diverse digital environments remains a pivotal challenge in Embodied AI. While Multimodal Large Language Models (MLLMs)…
SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness
Haiyi Qiu, Kaihang Pan, Jiacheng Li +3
Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image generation. However, these m…
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Kaihang Pan, Qi Tian, Jianwei Zhang +12
While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, the academic research community lags far behind: most of its model…
OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
Wendong Bu, Kaihang Pan, Yuze Lin +6
Large language models (LLMs) have unified diverse linguistic tasks within a single framework, yet such unification remains unexplored in human motion generation. Existing methods a…
WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing
Kaihang Pan, Weile Chen, Haiyi Qiu +6
Recent image editing models boast next-level intelligent capabilities, facilitating cognition- and creativity-informed image editing. Yet, existing benchmarks provide too narrow a…
Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
Zhaoyu Fan, Kaihang Pan, Mingze Zhou +7
Knowledge editing enables multimodal large language models (MLLMs) to efficiently update outdated or incorrect information. However, existing benchmarks primarily emphasize cogniti…
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
Wendong Bu, Yang Wu, Qifan Yu +10
As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations,…
FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL
Kaihang Pan, Wendong Bu, Yuruo Wu +7
Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featurin…
Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
Kaihang Pan, Yang Wu, Wendong Bu +9
Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation. However, these two capabilities remain largely independent, as if the…
Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
Bohan Wang, Zhongqi Yue, Fengda Zhang +15
We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design co…
On Path to Multimodal Generalist: General-Level and General-Bench
Hao Fei, Yuan Zhou, Juncheng Li +29
The Multimodal Large Language Model (MLLM) is currently experiencing rapid growth, driven by the advanced capabilities of LLMs. Unlike earlier specialists, existing MLLMs are evolv…
Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
Wang Lin, Liyu Jia, Wentao Hu +6
Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapol…
Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
Kaihang Pan, Wang Lin, Zhongqi Yue +6
Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each ta…
Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
Zhiqi Ge, Juncheng Li, Xinglei Pang +7
Digital agents are increasingly employed to automate tasks in interactive digital environments such as web pages, software applications, and operating systems. While text-based age…
STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
Haiyi Qiu, Minghe Gao, Long Qian +7
Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but st…
AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
Qifan Yu, Wei Chow, Zhongqi Yue +7
Instruction-based image editing aims to modify specific image elements with natural language instructions. However, current models in this domain often struggle to accurately execu…
Unified Generative and Discriminative Training for Multi-modal Large Language Models
Wei Chow, Juncheng Li, Qifan Yu +7
In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle…
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
Kaihang Pan, Zhaoyu Fan, Juncheng Li +6
The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and ex…
Auto-Encoding Morph-Tokens for Multimodal LLM
Kaihang Pan, Siliang Tang, Juncheng Li +6
For multimodal LLMs, the synergy of visual comprehension (textual output) and generation (visual output) presents an ongoing challenge. This is due to a conflicting objective: for…
Improving Vision Anomaly Detection with the Guidance of Language Modality
Dong Chen, Kaihang Pan, Guoming Wang +2
Recent years have seen a surge of interest in anomaly detection for tackling industrial defect detection, event detection, etc. However, existing unsupervised anomaly detectors, pa…
I3: Intent-Introspective Retrieval Conditioned on Instructions
Kaihang Pan, Juncheng Li, Wenjie Wang +7
Recent studies indicate that dense retrieval models struggle to perform well on a wide variety of retrieval tasks that lack dedicated training data, as different retrieval tasks of…