Get started
Author

Pengfei Zhou

ReLiB-100k: a real-world 100k-scale dataset and comprehensive benchmark for capacity estimation of retired lithium-ion batteries
2026 · Yunlong Liu, Pengfei Zhou, et al. · Data Mining and Knowledge Discovery · 1
LOGIV: Graph-Verified Execution with Causal Local Repair for Long-Horizon Robot Tasks
2026 · Lu, Enqiao, Xie, Yuxiang, et al. · arXiv (Cornell University)
PDF
AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers
2026 · Xu, Bin, Zhang, Mo, et al. · arXiv (Cornell University)
PDF
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
2026 · Tang, Weidong, Wang, Ruiheng, et al. · arXiv (Cornell University)
PDF
AI for Games in the Foundation Model Era
2026 · Luo, Meng, Li, Yanlin, et al. · arXiv (Cornell University)
PDF
Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs
2026 · Liang, Haiji, Zhou, Pengfei, et al. · arXiv (Cornell University)
PDF
SpikeOPD: Stable On-Policy Distillation for Autoregressive Spiking Language Models
2026 · Lu, Enqiao, Yu, Xingrui, et al. · arXiv (Cornell University)
PDF
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
2026 · Zhou, Pengfei, Wang, Hexin, et al. · arXiv (Cornell University)
PDF
$τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
2026 · Cai, Xiaowei, Cai, Yunuo, et al. · arXiv (Cornell University)
PDF
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
2026 · Liang, Shuo, Ma, Yixing, et al. · arXiv (Cornell University)
PDF
SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks
2026 · Yu, Tao, Qu, Yifei, et al. · arXiv (Cornell University)
PDF
Improving Generalization Robustness of Multimodal RLVR
2026 · Zhou, Pengfei, Tang, Zhiwei, et al. · arXiv (Cornell University)
PDF
MAIC: Multimodal Alignment at Instance and Cluster levels for vision–language data pruning
2026 · Zhaopan Xu, Ziheng Qin, et al. · Displays
Unified Hallucination Fuzzing for Multimodal Large Language Models
2026 · Zhou, Pengfei, Song, Jiajun, et al. · arXiv (Cornell University)
PDF
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
2026 · Zhou, Pengfei, Tang, Zhiwei, et al. · arXiv (Cornell University)
PDF
Calibration Is Not Control: Intervention Value for LLM-Agent Oversight
2026 · Zhang, Chubin, Wan, Zhenglin, et al. · arXiv (Cornell University)
PDF
Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents
2026 · Zhang, Chubin, Wan, Zhenglin, et al. · arXiv (Cornell University)
PDF
Self-Evolving Time-Series Agent: Automatic Architecture Creation Based on Large Language Models
2026 · Zhou, Pengfei, Liang, Junli, et al. · Zenodo (CERN European Organization for Nuclear Research)
AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding
2026 · Ren, Yingxuan, Lou, Yuxuan, et al. · arXiv (Cornell University)
PDF
GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs
2026 · Association for Computational Linguistics 2026, Hou, Yueling, et al. · Underline Science Inc.
$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation
2026 · Zhou, Pengfei, Chen, Shengcong, et al. · arXiv (Cornell University)
PDF
SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering
2026 · Liang, Junli, Zhou, Pengfei, et al. · arXiv (Cornell University)
PDF
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
2026 · Tong Bai, Zhenglin Wan, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Works count: 26
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type