conftrace_

Yuheng Zhao

4 papers · 2026–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

OSDI (2) COLT (1) NSDI (1)

Top co-authors

Wei Gao (3) Tianyuan Wu (3) Ju Huang (3) Wei Wang (3) Dakai An (3) Siran Yang (3) Lunxi Cao (3) Jiamang Wang (3) Shaopan Xiong (3) Lin Qu (3)

Research topics

Artificial Intelligence (2) Computer Science (2) Core AI (2) Systems (2) Deep Learning (1) Machine Learning (1) Reinforcement Learning (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Methods (1) Optimization & Theory (1)

Keywords

reinforcement learning (2) multi-task learning (1) online learning (1) convex optimization (1) dynamic regret (1) resource allocation (1) parameter-free algorithm (1) regret bound (1) gradient variation (1) mixture of expert (1) gpu utilization (1) cluster scheduling (1) large language model (1) reward computation (1) agentic reinforcement learning (1) tail batching (1) rollout scheduling (1) job placement (1) round-robin scheduling (1) disaggregated infrastructure (1)

Papers

Gradient-Variation Regret Bounds for Unconstrained Online Learning COLT 2026 RollArt: Disaggregated Multi-Task Agentic RL Training at Scale OSDI 2026 RollPacker: Taming Long-Tail Rollouts for RL Post-Training with Tail Batching NSDI 2026 Weave: Efficient Co-Scheduling for Disaggregated RL Post-Training OSDI 2026