Get started
Author

Hejia Geng

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks
2025 · Heng Zhou, Hejia Geng, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 7
PDF
Composing recurrent spiking neural networks using locally-recurrent motifs and risk-mitigating architectural optimization
2024 · Wenrui Zhang, Hejia Geng, et al. · Frontiers in Neuroscience · 7
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
2026 · Li, Xiangyi, Liu, Yimin, et al. · arXiv (Cornell University) · 3
PDF
HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds
2023 · Geng, Hejia, Li, Peng · arXiv (Cornell University) · 2
PDF
Khan-GCL: Kolmogorov–Arnold Network Based Graph Contrastive Learning with Hard Negatives
2026 · Zihu Wang, Boxun Xu, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention
2023 · Xu, Boxun, Geng, Hejia, et al. · arXiv (Cornell University) · 1
PDF
MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model
2026 · Ko, Brian, Wang, Han, et al. · arXiv (Cornell University)
PDF
ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics
2026 · Yu, Xiaohang, Geng, Hejia, et al. · arXiv (Cornell University)
PDF
What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories
2026 · Wu, Koutian, Huang, Zesen, et al. · arXiv (Cornell University)
PDF
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
2026 · Wu, Fang, Xing, Da, et al. · arXiv (Cornell University)
PDF
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
2026 · Geng, Hejia, Huang, Zesen, et al. · arXiv (Cornell University)
PDF
Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal
2026 · Mo, Yunxiang, Zhao, Donghao, et al. · arXiv (Cornell University)
PDF
MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves
2026 · Tan, Zihan, Sun, Leixin, et al. · arXiv (Cornell University)
PDF
Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
2026 · Lin, Bohan, Geng, Hejia, et al. · arXiv (Cornell University)
PDF
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
2026 · Tan, Zelin, Zhang, Yiqun, et al. · arXiv (Cornell University)
PDF
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-Language Models
2026 · Wang, Zihu, S, Karthik Somayaji N., et al. · arXiv (Cornell University)
PDF
Reading $\neq$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models
2026 · Zhou, Heng, Yu, Ao, et al. · arXiv (Cornell University)
PDF
Khan-GCL: Kolmogorov–Arnold Network Based Graph Contrastive Learning with Hard Negatives
2026 · Association for Artificial Intelligence 2026, Geng, Hejia, et al. · Underline Science Inc.
PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
2026 · Zelin Tan, Zhouliang Yu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Parthenon Law: A Self-Evolving Legal-Agent Framework
2026 · Hejia Geng, Yuxuan Liu · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
2026 · Zelin Tan, Hejia Geng, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems
2026 · Heng Zhou, Lian Zhang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
An Automated Pipeline for Provably Retrieval-Dependent Benchmark Construction over Dynamic Knowledge
2026 · Heng Zhou, Ao Yu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge
2025 · Zhou, Heng, Yu, Ao, et al. · arXiv (Cornell University)
PDF
Works count: 30
Citation count: 21
H-index: 3
I10-index:
Year
Topic
Type