Siran Yang
5 papers · 2025–2026 · 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
⭐
Rising Star
(5)
Top co-authors
Research topics
Keywords
reinforcement learning
(2)
multi-task learning
(1)
action recognition
(1)
multimodal learning
(1)
resource allocation
(1)
distributed training
(1)
straggler mitigation
(1)
mixture of expert
(1)
game ai
(1)
pipeline parallelism
(1)
head-of-line blocking
(1)
gpu utilization
(1)
cluster scheduling
(1)
embodied intelligence
(1)
large language model
(1)
reward computation
(1)
large model training
(1)
agentic reinforcement learning
(1)
tail batching
(1)
rollout scheduling
(1)
Papers
Attack of the Bubbles: Straggler-Resilient Pipeline Parallelism for Large Model Training
NSDI 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
CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
ICCV 2025