13 papers
RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning
Kunwang Zheng, Xinyu Sun, Yu Cao +7
Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the rubric carries and gives no GR…
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Yan Yu, Zhengxi Lu, Yizhou Liu +8
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-le…
TTPO: Test-Time Policy Optimization
Aozhe Wang, Zhengxi Lu, Jianze Wang +8
Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large l…
DaViNCi: A Dataset Towards Outdoor Vision-and-Language Navigation with Continuous Actions and Dynamic Elements
Zihao Xie, Pingrui Lai, Yitong Wu +1
Vision-and-Language Navigation (VLN) has progressively expanded from indoor to outdoor environments. However, existing outdoor VLN datasets still rely on fixed discrete topological…
SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning
Jianze Wang, Kunwang Zheng, Ying Liu +5
Test-time reinforcement learning (TTRL) enables language models to self-evolve at inference time without labeled feedback. Existing methods rely on answer voting and therefore do n…
SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning
Yucheng Deng, Pingrui Lai, Xinhai Li +5
Vision-and-Language Navigation in continuous environments requires agents to understand the spatial structure of previously unseen environments in order to follow language instruct…
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Xiangyu Zhao, Junming Lin, Tianhao Liang +11
While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reas…
MFH: Marrying Frequency Domain with Handwritten Mathematical Expression Recognition
Huanxin Yang, Qiwen Wang
Handwritten mathematical expression recognition (HMER) suffers from complex formula structures and character layouts in sequence prediction. In this paper, we incorporate frequency…
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
Xiangyu Zhao, Peiyuan Zhang, Kexian Tang +10
Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in…
Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition
Xinyu Xi, Hua Yang, Shentai Zhang +3
Maritime Multi-Scene Recognition is crucial for enhancing the capabilities of intelligent marine robotics, particularly in applications such as marine conservation, environmental m…
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang +10
Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human prefe…
MCSD: An Efficient Language Model with Diverse Fusion
Hua Yang, Duohai Li, Shiman Li
Transformers excel in Natural Language Processing (NLP) due to their prowess in capturing long-term dependencies but suffer from exponential resource consumption with increasing se…
Deciphering Oracle Bone Language with Diffusion Models
Haisu Guan, Huanxin Yang, Xinyu Wang +5
Originating from China's Shang Dynasty approximately 3,000 years ago, the Oracle Bone Script (OBS) is a cornerstone in the annals of linguistic history, predating many established…