JG
Jingchu Gai
cs.LGcs.AIcs.DMcs.CRcs.DScs.GTcs.MAmath.COstat.ML
On Valency
published · living versionsW_xmfazpnx·v1 · currentpublished
Understanding the Benefits of Scaffolds through Computational Separations
with Adam Block, Andrej Risteski
1 version
Preprints & journals
10 papers in the corpus · 2024–2026Understanding the Benefits of Scaffolds through Computational Separations2610.27157v1 · Jingchu Gai, Adam Block, Andrej Risteski2026 · 0 citationsarXivon Valency
When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon2606.30445v1 · Huaqing Zhang, Jingchu Gai, Juno Kim et al.2026 · 0 citationsarXiv
Understanding and Mitigating Premature Confidence for Better LLM Reasoning2605.24396v2 · Jingchu Gai, Guanning Zeng, Christina Baek et al.2026 · 0 citationsarXiv
Lossless Anti-Distillation Sampling2605.18829v2 · Zibo Diao, Jingchu Gai, Xinyue Ai et al.2026 · 0 citationsarXiv
Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation2605.03125v2 · Jingchu Gai, Laixi Shi2026 · 0 citationsarXiv
Towards Solving the Gilbert-Pollak Conjecture via Large Language Models2601.22365v3 · Yisi Ke, Tianyu Huang, Yankai Shu et al.2026 · 0 citationsarXiv
Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning2511.19942v2 · Jingchu Gai, Guanning Zeng, Huaqing Zhang et al.2025 · 0 citationsarXiv
Homomorphism Expressivity of Spectral Invariant Graph Neural Networks2503.00485v1 · Jingchu Gai, Yiheng Du, Bohang Zhang et al.2025 · 0 citationsICLR 2025 Oral
Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning2409.20067v3 · Laixi Shi, Jingchu Gai, Eric Mazumdar et al.2024 · 0 citationsarXiv
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness2401.08514v1 · Bohang Zhang, Jingchu Gai, Yiheng Du et al.2024 · 3 citationsarXiv
Career total: 10 works. 10 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.