8 papers
Scaling Latent Reasoning via Looped Language Models
Rui-Jie Zhu, Zixuan Wang, Kai Hua +30
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training…
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
Ahmed Masry, Juan A. Rodriguez, Tianyu Zhang +19
Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps vi…
Scope: Selective Cross-modal Orchestration of Visual Perception Experts
Tianyu Zhang, Suyuchen Wang, Chao Wang +5
Vision-language models (VLMs) benefit from multiple vision encoders, but naively stacking them yields diminishing returns while multiplying inference costs. We propose SCOPE, a Mix…
Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
Suyuchen Wang, Tianyu Zhang, Ahmed Masry +4
GUI grounding, the task of mapping natural-language instructions to pixel coordinates, is crucial for autonomous agents, yet remains difficult for current VLMs. The core bottleneck…
STRICT: Stress Test of Rendering Images Containing Text
Tianyu Zhang, Xinyu Wang, Lu Li +5
While diffusion models have revolutionized text-to-image generation with their ability to synthesize realistic and diverse scenes, they continue to struggle to generate consistent…
MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
Lu Li, Tianyu Zhang, Zhiqi Bu +7
Model merging has emerged as an effective approach to combine multiple single-task models into a multitask model. This process typically involves computing a weighted average of th…