4 papers · 1 filter
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Tencent WorkBuddy Bench Team, Siqi Cai, Shaopeng Chen +35
We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model lea…
Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Haiyang Yu, Yuchuan Wu, Fan Shi +18
Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and unders…
Post-Completion Learning for Language Models
Xiang Fei, Siqi Wang, Shu Wei +5
Current language model training paradigms typically terminate learning upon reaching the end-of-sequence (<eos>) token, overlooking the potential learning opportunities in the post…
Advancing Sequential Numerical Prediction in Autoregressive Models
Xiang Fei, Jinghui Lu, Qi Sun +6
Autoregressive models have become the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlo…