Song Li
13 papers · 2020–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🏃 Academic Marathon (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🐝 Cross-Pollinator (8)
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(8)
🏃
Academic Marathon
(5)
🏆
Grand Slam
💎
Century Club
(13)
🔥
Unstoppable
(6)
🗃️
Keyword Collector
(60)
Conferences
INTERSPEECH (6)
AAAI (1)
ACL (1)
ICLR (1)
ICML (1)
NIPS (1)
SEMEVAL (1)
WACV (1)
Top co-authors
Keywords
auxiliary-task learning
(2)
hierarchical model
(2)
legal text
(2)
multi-task learning
(2)
automatic speech recognition
(1)
speech separation
(1)
text classification
(1)
feature embedding
(1)
domain adaptation
(1)
image reconstruction
(1)
attention mechanism
(1)
semantic knowledge
(1)
keyword spotting
(1)
speaker embedding
(1)
image denoising
(1)
speaker verification
(1)
bayesian estimation
(1)
self-supervised learning
(1)
connectionist temporal classification
(1)
action recognition
(1)
Papers
Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection
ICLR 2025
CogMath: Assessing LLMs’ Authentic Mathematical Ability from a Human Cognitive Perspective
ICML 2025
Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients
NIPS 2024
MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research
INTERSPEECH 2024
Behavioral Recognition of Skeletal Data Based on Targeted Dual Fusion Strategy
AAAI 2024
EventPoint: Self-Supervised Interest Point Detection and Description for Event-Based Camera
WACV 2023
AntContentTech at SemEval-2023 Task 6: Domain-adaptive Pretraining and Auxiliary-task Learning for Understanding Indian Legal Texts
ACL 2023
AntContentTech at SemEval-2023 Task 6: Domain-adaptive Pretraining and Auxiliary-task Learning for Understanding Indian Legal Texts
SEMEVAL 2023
Spatial-aware Speaker Diarizaiton for Multi-channel Multi-party Meeting
INTERSPEECH 2022
An Integrated Framework for Two-Pass Personalized Voice Trigger
INTERSPEECH 2021
Real-Time End-to-End Monaural Multi-Speaker Speech Recognition
INTERSPEECH 2021
Automatic Error Correction for Speaker Embedding Learning with Noisy Labels
INTERSPEECH 2021
Improving Transformer-Based Speech Recognition with Unsupervised Pre-Training and Multi-Task Semantic Knowledge Learning
INTERSPEECH 2020