24 papers
Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design
Yuxuan Yang, Xiaotong Mao, Jingyao Wang
Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences. While rec…
Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting
Xingyu Zhang, Jingyao Wang, Xin Yu +4
Time series forecasting often suffers from over-smoothing, especially when future dynamics are multi-modal. Forecasts may follow the coarse trend of the observed future, but fail t…
GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios
Ke Hu, Shutong Ding, Panxin Tao +2
Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous-control tasks. Among them,…
Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
Jingyao Wang, Peizheng Guo, Wenwen Qiang +4
Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coupled to final correctness and pay…
CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models
Huijie Guo, Jingyao Wang, Lingyu Si +3
Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-diffi…
On the Plasticity and Stability for Post-Training Large Language Models
Wenwen Qiang, Ziyin Gu, Jiahuan Zhou +4
Training stability remains a critical bottleneck for Group Relative Policy Optimization (GRPO), often manifesting as a trade-off between reasoning plasticity and general capability…