4 papers · 1 filter
P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing
Yong Zu, Ninghua Yang, Zezhong Tan +3
End-to-end full-page document parsing must preserve the content and structure of heterogeneous elements, yet otherwise accurate outputs can contain local errors and omissions. A si…
I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization
Yubo Zhang, Xinhong Ma, Zezhong Tan +1
Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is incorrect. Pr…
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Zhilin Huang, Hang Gao, Ziqiang Dong +6
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes…
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
Feng Zhang, Xinhong Ma, Ziqiang Dong +5
Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reasoning tasks. We first show that GRPO admi…