7 papers
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
Bo-Wen Zhang, Junwei He, Wen Wang +5
The paper introduces CoRT, a method that uses counterfactual replay to assign token-level credit in rubric-guided reinforcement learning for language models, improving credit alloc…
Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
Wanru Zhao, Yihong Chen, Yuzhi Tang +6
Data curation is a critical yet under-explored area in large language model (LLM) training. Existing methods, such as data selection and mixing, operate in an offline paradigm, det…
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
Jialin Yang, Dongfu Jiang, Lipeng He +17
As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce Struct…
Aesthetic Assessment of Chinese Handwritings Based on Vision Language Models
Chen Zheng, Yuxuan Lai, Haoyang Lu +3
The handwriting of Chinese characters is a fundamental aspect of learning the Chinese language. Previous automated assessment methods often framed scoring as a regression problem.…
VideoScore2: Think before You Score in Generative Video Evaluation
Xuan He, Dongfu Jiang, Ping Nie +21
Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-…
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers
Weiming Ren, Wentao Ma, Huan Yang +3
State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations,…