10 papers
HaloBlock: Faster and Better Decoding for Diffusion Large Language Models
Zhaohui Zheng, Chenhang He, Jinrui Zhang +2
Diffusion large language models (dLLMs) have attracted increasing research attention due to their bidirectional attention and arbitrary order decoding. However, there are two issue…
Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
Xin Jin, Huanqia Cai, Zhen Li +9
Reward models are central to text-to-image post-training, but visual preference is subjective and better represented as a distribution over rubric scores than as a deterministic sc…
DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation
Xifeng Xue, Xiaokang Wang, Zirui Li +2
Recent vision token pruning methods effectively preserve model performance under moderate token budgets but become unstable under ultra-low token budget. Our analysis shows that as…
DEL: Digit Entropy Loss for Numerical Learning of Large Language Models
Zhaohui Zheng, Chenhang He, Shihao Wang +3
Number prediction stands as a fundamental capability of large language models (LLMs) in mathematical problem-solving and code generation. The widely adopted maximum likelihood esti…
CrystaL: Spontaneous Emergence of Visual Latents in MLLMs
Yang Zhang, Danyang Li, Yuxuan Li +4
Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain…
Test-Time Computing for Referring Multimodal Large Language Models
Mingrui Wu, Hao Chen, Jiayi Ji +5
We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained r…
VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
Zhong-Yu Li, Ruoyi Du, Juncheng Yan +6
Recent progress in diffusion models significantly advances various image generation tasks. However, the current mainstream approach remains focused on building task-specific models…
Multi-Token Enhancing for Vision Representation Learning
Zhong-Yu Li, Yu-Song Hu, Bo-Wen Yin +1
Vision representation learning, especially self-supervised learning, is pivotal for various vision applications. Ensemble learning has also succeeded in enhancing the performance a…
PR-MIM: Delving Deeper into Partial Reconstruction in Masked Image Modeling
Zhong-Yu Li, Yunheng Li, Deng-Ping Fan +1
Masked image modeling has achieved great success in learning representations but is limited by the huge computational costs. One cost-saving strategy makes the decoder reconstruct…
Towards RAW Object Detection in Diverse Conditions
Zhong-Yu Li, Xin Jin, Boyuan Sun +2
Existing object detection methods often consider sRGB input, which was compressed from RAW data using ISP originally designed for visualization. However, such compression might los…