Haiyuan Wan
Orcid: 0009-0009-4021-6555
According to our database1,
Haiyuan Wan authored at least 15 papers
between 2025 and 2026.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2026
LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory.
CoRR, May, 2026
Efficient Tensor Offloading Based on CXL Memory Pool for Extreme Scale Deep Learning.
IEEE Trans. Computers, April, 2026
CoRR, February, 2026
SDFLoRA: Selective Decoupled Federated LoRA for Privacy-preserving Fine-tuning with Heterogeneous Clients.
CoRR, January, 2026
CoRR, January, 2026
CxlRatioOpt : A Predictive Optimizer for Performance Trade-offs in CXL-Tiered Memory.
Proceedings of the IEEE International Symposium on Circuits and Systems, 2026
Deep Research Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026
2025
Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks.
CoRR, November, 2025
PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent System.
CoRR, September, 2025
From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning.
CoRR, September, 2025
HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?
CoRR, September, 2025
DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks.
CoRR, September, 2025
Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025