Qingnan Ren
5 papers · 2026–2026 · 2 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.
Top co-authors
Research topics
Keywords
policy optimization
(1)
reward model
(1)
advantage estimation
(1)
credit assignment
(1)
parametric memory
(1)
contrastive analysis
(1)
learning efficiency
(1)
large-scale training
(1)
large language model
(1)
self distillation
(1)
web retrieval
(1)
generative reward model
(1)
spectral constraint
(1)
deep research
(1)
maximal update parametrization
(1)
mup
(1)
videos
(1)
independent principle grm
(1)
policy gradient optimization
(1)
principle drift
(1)
Papers
ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning
EMNLP 2026
Controlled LLM Training on Spectral Sphere
ICML 2026
Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
EMNLP 2026
Unbiased Principles, Robust Rewards
ICML 2026
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
EMNLP 2026