JH
Junlin He
cs.AIcs.CLcs.LGcs.RO
On Valency
published · living versionsW_ax2cmvsd·v1 · currentpublished
E0.5: From Reconstructive to Future-Predictive 3D Foundations for Robotic World-Action Modeling
with Era AI Lab Team, Jianhao Lai, Zhihao Zhan, Zhiquan Liao +22
1 version
W_j5d4kzyv·v1published
Preprints & journals
6 papers in the corpus · 2025–2026World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning2607.10630v1 · Tong Nie, Yuewen Mei, Junlin He et al.2026 · 0 citationsarXiv
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents2606.03678v2 · Tong Nie, Yuewen Mei, Yihong Tang et al.2026 · 0 citationsarXiv
MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation2606.01640v1 · Junlin He, Yihong Tang, Tong Nie et al.2026 · 0 citationsarXiv
Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization2605.29327v1 · Junlin He, Yihong Tang, Tong Nie et al.2026 · 0 citationsarXiv
ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving2603.15221v1 · Tong Nie, Yihong Tang, Junlin He et al.2026 · 0 citationsarXiv
Steerable Adversarial Scenario Generation through Test-Time Preference Alignment2509.20102v2 · Tong Nie, Yuewen Mei, Yihong Tang et al.2025 · 0 citationsThe Fourteenth International Conference on Learning Representations (ICLR 2026)
Career total: 6 works. 6 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.