Sangwoo Kang
4 papers · 2025–2026 · 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.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
reinforcement learning
(3)
group relative policy optimization
(2)
code generation
(1)
inference acceleration
(1)
expert routing
(1)
parallel decoding
(1)
adaptive decoding
(1)
self-speculative decoding
(1)
token generation
(1)
denoising trajectory
(1)
layer embedding
(1)
diffusion large language model
(1)
masked diffusion language model
(1)
model compression
(1)
answer-guided generation
(1)
policy optimization
(1)
Papers
AG-GRPO: Answer-Guided GRPO for Masked Diffusion Language Models
ACL 2026
TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs
ACL 2026
Exploration-Driven Reinforcement Learning for Expert Routing Improvement in Mixture-of-Experts Language Models
EMNLP 2025
FractalLLM: Lossless Self-Speculative Decoding with Layer Embedded Self-Compression
EMNLP 2025