14 papers
LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning
Xingjian Tao, Yiwei Wang, Yujun Cai +1
Multi-view spatial reasoning requires vision-language models to compare visual evidence across images, align object correspondences, and infer spatial relations over long visual co…
Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models
Boyan Han, Yiwei Wang, Yi Song +2
Diffusion large language models (dLLMs) offer bidirectional attention and parallel generation, enabling them to exploit global context and naturally support format-constrained task…
GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation
Sifan Li, Yujun Cai, Hongkai Chen +1
Generating structured, editable diagrams remains a significant challenge for contemporary large language models, despite their proficiency in general-purpose vector code generation…
How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
Entang Wang, Yiwei Wang, Aleksandra Bakalova +1
In-context learning (ICL) excels at new tasks from minimal examples, yet we still lack a mechanistic explanation of how few-shot prompts shape a model's function vector (FV)--a cau…
Mitigating Coordinate Prediction Bias from Positional Encoding Failures
Xingjian Tao, Yiwei Wang, Yujun Cai +3
While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, precise coordinate prediction remains a significant challenge, particularly as high-resolutio…
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Zhicheng Yang, Zhijiang Guo, Yinya Huang +6
Reinforcement Learning with Verifiable Reward (RLVR) is a powerful method for enhancing the reasoning abilities of Large Language Models, but its full potential is limited by a lac…