13 papers
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
Xuzheng Yang, Jun Ling, Tao Huang +2
We tackle the challenging yet underexplored task of Generalized Referring Expression Comprehension (GREC), which requires a model to localize the object described by a textual expr…
GOTS: Greedy Orthogonal Token Selection for High-Resolution Vision-Language Models
Jun Ling, Tao Huang, Junzhuo Liu +2
Modern vision-language models (VLMs) increasingly rely on dynamic or high-resolution visual encoding, producing thousands of visual tokens that substantially increase downstream la…
Structured Self-Consistency:A Multi-Task Evaluation of LLMs on VirtualHome
Jiaqi Xu, Tao Huang, Kai Zhang
Embodied AI requires agents to understand goals, plan actions, and execute tasks in simulated environments. We present a comprehensive evaluation of Large Language Models (LLMs) on…
Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark
Pan Wang, Yang Liu, Guile Wu +23
4D spatial intelligence involves perceiving and processing how objects move or change over time. Humans naturally possess 4D spatial intelligence, supporting a broad spectrum of sp…
Distilling Cross-Modal Knowledge via Feature Disentanglement
Junhong Liu, Yuan Zhang, Tao Huang +2
Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-m…
Learning to Expand Images for Efficient Visual Autoregressive Modeling
Ruiqing Yang, Kaixin Zhang, Zheng Zhang +2
Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often su…
ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation
Kaixin Zhang, Ruiqing Yang, Yuan Zhang +2
Visual Autoregressive (VAR) models enable efficient image generation via next-scale prediction but face escalating computational costs as sequence length grows. Existing static pru…
Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
Ziyuan Huang, DanDan Zheng, Cheng Zou +13
Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in dis…
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
Inclusion AI, :, Bowen Ma +73
We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which on…
Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
Jun Ling, Yao Qi, Tao Huang +8
In this work, we address the task of table image to LaTeX code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inpu…
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…
Promoting CNNs with Cross-Architecture Knowledge Distillation for Efficient Monocular Depth Estimation
Zhimeng Zheng, Tao Huang, Gongsheng Li +1
Recently, the performance of monocular depth estimation (MDE) has been significantly boosted with the integration of transformer models. However, the transformer models are usually…
Diverse and Tailored Image Generation for Zero-shot Multi-label Classification
Kaixin Zhang, Zhixiang Yuan, Tao Huang
Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless,…