Guanbo Wang
4 papers · 2022–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ACL (1)
EMNLP (1)
ICLR (1)
INTERSPEECH (1)
Top co-authors
Keywords
model compression
(1)
data augmentation
(1)
chain-of-thought reasoning
(1)
confidence calibration
(1)
automatic speech recognition
(1)
connectionist temporal classification
(1)
early stopping
(1)
acoustic model
(1)
vision-language model
(1)
hybrid architecture
(1)
large reasoning model
(1)
reasoning efficiency
(1)
reasoning compression
(1)
reinforcement fine-tuning
(1)
embodied planning
(1)
confidence injection
(1)
length reduction
(1)
confidence-guided learning
(1)
on-policy reinforcement learning
(1)
wavvec 2.0
(1)
Papers
On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning
ACL 2026
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
EMNLP 2025
CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning
ICLR 2023
The THUEE System Description for the IARPA OpenASR21 Challenge
INTERSPEECH 2022