Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction
Feiyang Ren, Shengtao Wen, Lingbing Guo +3
Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Predicting output lengths in ad…
cs.AI2026
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
Mingyu Yuan, Shengtao Wen, Lingbing Guo +2
The widespread circulation of abusive online content has increased the need for reliable moderation of Chinese social-media text. Existing Chinese benchmarks support label classifi…
cs.AI2026
Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing
Sheng Ren, Yadong Wang, Naiqiang Tan +7
Pre-norm is the standard normalization placement in modern Transformers because it facilitates joint optimization of full-depth models. We ask whether this preference persists when…