Peng Shu
10 papers · 2025–2026 · 4 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 ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (28) 🌍 Conference Polyglot · Bronze ⭐ Rising Star (10) 🗃️ Keyword Collector (55)
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(5)
💎
Century Club · Bronze
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(7)
Machine Learning
(4)
Learning Types
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Applications
(3)
Computer Vision
(2)
Reinforcement Learning
(2)
Methods
(2)
Models
(2)
Processing
(2)
Knowledge & Reasoning
(1)
Application Areas
(1)
Learning Paradigms
(1)
Keywords
reinforcement learning
(3)
multi-agent system
(2)
retrieval-augmented generation
(2)
curriculum reinforcement learning
(2)
video understanding
(1)
image editing
(1)
adversarial learning
(1)
parameter-efficient transfer learning
(1)
information retrieval
(1)
sponsored search
(1)
generative model
(1)
vision-language model
(1)
text prompt
(1)
zero-shot generalization
(1)
video moderation
(1)
semantic consistency
(1)
fine-grained understanding
(1)
subject identity
(1)
spatial grounding
(1)
text-to-image generation
(1)
Papers
ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring
ACL 2026
Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection
AAAI 2026
Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation
CVPR 2026
Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection
AAAI 2026
ℛ3: Advertisement Compliance ℛectification via Group-ℛelative Experience Extractor and Curriculum ℛeinforcement
ACL 2026
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
ACL 2026
SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification
ACL 2026
Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA
ACL 2026
RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning
EMNLP 2025
Real-time Ad Retrieval via LLM-generative Commercial Intention for Sponsored Search Advertising
EMNLP 2025