Get started
Author

Zhengzhong Liu

Self-drafting with Uno on a mixture of experts: serving and training an adapter for Gemma 4 26B A4B
2026 · Sahoo, Subham Sekhar, Chen, Lingjie, et al. · arXiv (Cornell University)
PDF
Toward a First-Principles Update Geometry for the Language-Model Head
2026 · Somasundaram, Aditya, Guille-Escuret, Charles, et al. · arXiv (Cornell University)
PDF
Jais 2: A Family of Arabic-Centric Open Large Language Models
2026 · Anwar, Mohamed, Freihat, Abed Alhakim, et al. · arXiv (Cornell University)
PDF
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
2026 · Kong, Lingjing, Liu, Xin, et al. · arXiv (Cornell University)
PDF
Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models
2026 · Association for Computational Linguistics 2026, Gu, Yi, et al. · Underline Science Inc.
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
2026 · Dong, Daize, Chen, Junlin, et al. · arXiv (Cornell University)
PDF
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
2026 · Deng, Mingkai, Hou, Jinyu, et al. · arXiv (Cornell University)
PDF
GQA-μP: The maximal parameterization update for grouped query attention
2026 · Chickering, Kyle R., Wang, Huijuan, et al. · arXiv (Cornell University)
PDF
EMO: Frustratingly Easy Progressive Training of Extendable MoE
2026 · Jin, Linghao, Shi, Chufan, et al. · arXiv (Cornell University)
PDF
CocoaBench: Evaluating Unified Digital Agents in the Wild
2026 · CocoaBench Team, Hao, Shibo, et al. · arXiv (Cornell University)
PDF
World Reasoning Arena
2026 · PAN Team, Gao, Qiyue, et al. · arXiv (Cornell University)
PDF
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
2026 · Cheng, Zhoujun, Xie, Yutao, et al. · arXiv (Cornell University)
PDF
LAPS: A Length-Aware-Prefill LLM Serving System
2026 · She, Jianshu, Li, Zonghang, et al. · arXiv (Cornell University)
PDF
Works count: 13
Citation count:
H-index:
I10-index:
Year
Topic
Type