5 papers
Low Perplexity is Repetition: A One-Dimensional Self-Conditioning Attractor in Continuous Diffusion LMs
Shuai Zhang, Zijie Chen, Hongliang He +2
Continuous diffusion language models such as ELF report record-low generative perplexity (Gen-PPL). We find a catch: these models repeat far more than human text, and Gen-PPL rewar…
Improving Data and Reward Design for Scientific Reasoning in Large Language Models
Zijie Chen, Zhenghao Lin, Xiao Liu +3
Solving open-ended science questions remains challenging for large language models, particularly due to inherently unreliable supervision and evaluation. The bottleneck lies in the…
A2Eval: Agentic and Automated Evaluation for Embodied Brain
Shuai Zhang, Jiayu Hu, Zijie Chen +9
Current embodied VLM evaluation relies on static, expert-defined, manually annotated benchmarks that exhibit severe redundancy and coverage imbalance. This labor intensive paradigm…
Breaking the Data Barrier -- Building GUI Agents Through Task Generalization
Junlei Zhang, Zichen Ding, Chang Ma +4
Graphical User Interface (GUI) agents offer cross-platform solutions for automating complex digital tasks, with significant potential to transform productivity workflows. However,…
QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution
Zijie Chen, Zhanchao Zhou, Yu Lu +3
Solving NP-hard problems traditionally relies on heuristics, yet manually designing effective heuristics for complex problems remains a significant challenge. While recent advancem…