Shengyu Feng
9 papers · 2020–2026 · 7 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 ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (26) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π£ Hot Topic Early Bird
π
Grand Slam
π₯
Mega-Team Β· Squad
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI Β· Artificial Intelligence
(6)
Deep Learning
(3)
Machine Learning
(3)
Mathematics & Optimization
(3)
Reinforcement Learning
(3)
Methods
(3)
Optimization
(3)
Computer Vision
(2)
Analysis
(2)
Learning Types Β· Deep Learning
(2)
Learning Types Β· Machine Learning
(2)
Natural Language Processing
(1)
Architectures
(1)
Core AI Β· Computer Vision
(1)
Keywords
reinforcement learning
(3)
large language model
(3)
combinatorial optimization
(2)
video understanding
(2)
imitation learning
(2)
offline reinforcement learning
(1)
policy evaluation
(1)
deep reinforcement learning
(1)
multimodal learning
(1)
policy iteration
(1)
attention mechanism
(1)
visual grounding
(1)
object tracking
(1)
instruction following
(1)
sequential monte carlo
(1)
branch and bound
(1)
scene graph
(1)
simulated annealing
(1)
regularization
(1)
langevin dynamics
(1)
Papers
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
ACL 2026
CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization
AAAI 2026
Regularized Langevin Dynamics for Combinatorial Optimization
ICML 2025
SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch
AAAI 2025
Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
ICLR 2025
Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs
WACV 2023
Batch Reinforcement Learning Through Continuation Method
ICLR 2021
Coreference by Appearance: Visually Grounded Event Coreference Resolution
EMNLP 2021
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
NeurIPS 2020