6 papers
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
Guozhen Zhang, Xuerui Qiu, Yutao Cui +11
Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDR…
What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
Jiaping Lin, Fei Shen, Junzhe Li +4
Existing training-free approaches for GUI grounding often rely on multiple inference runs, such as iterative cropping or candidate aggregation, to identify target elements. Despite…
HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding
Xuerui Qiu, Yutao Cui, Guozhen Zhang +10
Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for gener…
dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
Arnav Shah, Junzhe Li, Parsa Idehpour +7
Genomic foundation models have the potential to decode DNA syntax, yet face a fundamental tradeoff in their input representation. Standard fixed-vocabulary tokenizers fragment biol…
ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents
Xiaoce Wang, Guibin Zhang, Junzhe Li +3
Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce co…
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
Junzhe Li, Yutao Cui, Tao Huang +8
Although GRPO substantially enhances flow matching models in human preference alignment of image generation, methods such as FlowGRPO and DanceGRPO still exhibit inefficiency due t…