Scholar
Linchao Zhu (朱霖潮)
Google Scholar ID: 9ZukE28AAAAJ
Zhejiang University
Citations & Impact
Citations
7,924
H-index
47
i10-index
91
Publications
20
Co-authors
46
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Paper 'Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space' accepted at ICML 2025
- Paper 'DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving' accepted at NeurIPS 2025
- Paper '3DID: Direct 3D Inverse Design with Physics-Aware Optimization' accepted at NeurIPS 2025
- Paper 'FlexSelect: Flexible Token Selection for Efficient Long Video Understanding' accepted at NeurIPS 2025
- Paper 'Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks' accepted at NeurIPS 2025
- Paper 'MuTIS: Enhancing Reasoning Efficiency through Multi Turn Intervention Sampling in Reinforcement Learning' accepted at EMNLP 2025
- Paper 'Learning from reference answers: Versatile language model alignment without binary human preference data' published on arXiv
- Paper 'Mc-bench: A benchmark for multi-context visual grounding in the era of mllms' accepted at ICCV 2025
- Paper 'From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment' accepted at ICCV 2025
- Paper 'Detecting and mitigating hallucination in large vision language models via fine-grained ai feedback' accepted at AAAI 2025
- Paper 'VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft' accepted at ACL Findings 2024
- Paper 'FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models' accepted at ACL Findings 2024
- AAAI 2025 New Faculty Highlights
- 1st Place – MABe 2022 Behaviour Representation Learning (Mouse Triplets & Ant-beetle Groups Tracks), CVPR 2022
- 2nd Place – Evoked Emotion from Videos Challenge, CVPR 2021
- 1st Place – EPIC-Kitchen Action Recognition 2020
- 1st Place – EPIC-Kitchen Action Recognition 2019
- ActivityNet Trimmed Action Recognition Competition, 2017
- Google YouTube8M Video Classification Competition, 2017
Background
- Assistant Professor at the College of Computer Science and Technology, Zhejiang University
- Research focuses on developing AI systems that simulate and understand the physical world by integrating physics-informed machine learning and computational reasoning
- Aims to create intelligent simulators for complex phenomena—from materials to fluids
- Combines neural models that learn physical dynamics from multimodal data with LLM reasoning engines capable of complex calculations, time-series analysis, and mathematical problem-solving
- Goal is to build an AI agent that functions as an autonomous computational scientist—capable of perceiving the physical world and reasoning mathematically about its underlying principles
