Shengzhuang Chen

12 papers A* 4Journal 7Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization.
CoRR
Shengzhuang Chen, Xu Ouyang, Michael Arthur Leopold Pearce, Thomas Hartvigsen, Jonathan Richard Schwarz
2025 J jnl
ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization.
Trans. Mach. Learn. Res.
Xu Ouyang, Shengzhuang Chen, Michael Arthur Leopold Pearce, Thomas Hartvigsen, Jonathan Richard Schwarz
2025 — conf
Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts.
ACL (1)
Shengzhuang Chen, Ying Wei, Jonathan Richard Schwarz
2025 J jnl
Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts.
CoRR
Shengzhuang Chen, Ying Wei, Jonathan Richard Schwarz
2025 A* conf
CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models.
ICLR
Shengzhuang Chen, Yikai Liao, Xiaoxiao Sun, Kede Ma, Ying Wei
2025 J jnl
CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models.
CoRR
Shengzhuang Chen, Yikai Liao, Xiaoxiao Sun, Kede Ma, Ying Wei
2025 J jnl
Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings.
CoRR
Andrew M. Bean, Nabeel Seedat, Shengzhuang Chen, Jonathan Richard Schwarz
2024 A* conf
Learning Where to Edit Vision Transformers.
NeurIPS
Yunqiao Yang, Long-Kai Huang, Shengzhuang Chen, Kede Ma, Ying Wei
2024 J jnl
Learning Where to Edit Vision Transformers.
CoRR
Yunqiao Yang, Long-Kai Huang, Shengzhuang Chen, Kede Ma, Ying Wei
2024 A* conf
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts.
ICML
Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz, Ying Wei
2024 J jnl
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts.
CoRR
Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz, Ying Wei
2023 A* conf
Secure Out-of-Distribution Task Generalization with Energy-Based Models.
NeurIPS
Shengzhuang Chen, Long-Kai Huang, Jonathan Richard Schwarz, Yilun Du, Ying Wei