Get started
Author

Juanzi Li

Observed name: Li, Juanzi
Institution: Tsinghua University
Observed institution: Tsinghua University
OpenAlex ID: A5146792151
GLM-5: from Vibe Coding to Agentic Engineering
2026 · GLM-5-Team, :, et al. · arXiv (Cornell University) · 6
PDF
From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features
2026 · Liu, Dewen, Li, Zixuan, et al. · arXiv (Cornell University)
PDF
CogEvol: Towards Efficient and Reliable Learning Environment Generation
2026 · Tu, Shangqing, Zhang-Li, Daniel, et al. · arXiv (Cornell University)
PDF
DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering
2026 · Wang, Xujia, Zhang, Yizhe, et al. · arXiv (Cornell University)
PDF
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
2026 · Meng, Weihan, Guo, Hongzhu, et al. · arXiv (Cornell University)
PDF
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs
2026 · Zhu, Kejian, Jin, Zhuoran, et al. · arXiv (Cornell University)
PDF
Where Steering Signals Come From: Activation Source Selection in Activation Steering
2026 · Ye, Jiaran, Ran, Lingxu, et al. · arXiv (Cornell University)
PDF
HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment
2026 · Zhao, Chuangxin, Shi, Boyan, et al. · arXiv (Cornell University)
PDF
An LMM for Precisely Grounding Elements in Documents
2026 · Lu, Yijian, Zhao, Chuangxin, et al. · arXiv (Cornell University)
PDF
EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning
2026 · Wang, Zhitong, Li, Songze, et al. · arXiv (Cornell University)
PDF
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
2026 · Wang, Xuekang, Hao, Zhuoyuan, et al. · arXiv (Cornell University)
PDF
WildReward: Learning Reward Models from In-the-Wild Human Interactions
2026 · Association for Computational Linguistics 2026, Hou, Lei, et al. · Underline Science Inc.
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
2026 · Association for Computational Linguistics 2026, Feng, Ling, et al. · Underline Science Inc.
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
2026 · Association for Computational Linguistics 2026, Hou, Lei, et al. · Underline Science Inc.
DeepPrune: Parallel Scaling without Inter-trace Redundancy
2026 · Association for Computational Linguistics 2026, Bai, Yushi, et al. · Underline Science Inc.
RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension
2026 · Association for Computational Linguistics 2026, Chen, Yelin, et al. · Underline Science Inc.
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
2026 · Lin, Nianyi, Zhang, Jiajie, et al. · arXiv (Cornell University)
PDF
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
2026 · Jing, Yi, Dai, Zao, et al. · arXiv (Cornell University)
PDF
StoryAlign: Evaluating and Training Reward Models for Story Generation
2026 · Xia, Haotian, Peng, Hao, et al. · arXiv (Cornell University)
PDF
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
2026 · V Team, Hong, Wenyi, et al. · arXiv (Cornell University)
PDF
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
2026 · Bai, Yushi, Dong, Qian, et al. · arXiv (Cornell University)
WildReward: Learning Reward Models from In-the-Wild Human Interactions
2026 · Peng, Hao, Qi, Yunjia, et al. · arXiv (Cornell University)
WildReward: Learning Reward Models from In-the-Wild Human Interactions
2026 · Peng, Hao, Qi, Yunjia, et al. · arXiv (Cornell University)
PDF
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
2026 · Zhang, Jiajie, Lv, Xin, et al. · arXiv (Cornell University)
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
2026 · Zhang, Jiajie, Lv, Xin, et al. · arXiv (Cornell University)
PDF
Works count: 27
Citation count: 7
H-index: 1
I10-index:
Year
Topic
Type