Get started
Author

Hoang Phan

Observed name: Phan, Hoang
OpenAlex ID: A5107946575
Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
2025 · Hoang Phan, Lam Tran, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 1
PDF
Unveiling Concept Attribution in Diffusion Models
2025 · Nguyen Hung-Quang, Hoang Phan, et al. · neural information processing systems · 1
Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs
2026 · Nguyen, Tien-Phat, Nguyen, Truong, et al. · arXiv (Cornell University)
PDF
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
2026 · Phan, Hoang, Huynh, Dat, et al. · arXiv (Cornell University)
PDF
Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
2026 · Phan, Hoang, Pham, Minh, et al. · arXiv (Cornell University)
PDF
Sharpening Tax in Post-Training
2026 · Oh, Changdae, Zeng, Qi, et al. · arXiv (Cornell University)
PDF
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models
2026 · Association for Computational Linguistics 2026, Bi, Shengjie, et al. · Underline Science Inc.
Decoding the Critique Mechanism in Large Reasoning Models
2026 · Phan, Hoang, Nguyen, Quang H., et al. · arXiv (Cornell University)
PDF
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models
2026 · Hoang Phan, Xianjun Yang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales
2025 · Shikai Qiu, Charlie Chen, et al. · neural information processing systems
PDF
Controllable Prompt Tuning For Balancing Group Distributional Robustness
2024 · Phan, Hoang, Wilson, Andrew Gordon, et al. · arXiv (Cornell University)
PDF
Works count: 13
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type