Chengru Song
8 papers · 2022–2025 · 6 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 · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(19)
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(3)
Deep Learning
(3)
Natural Language Processing
(3)
Architectures
(3)
Learning Types
(3)
Computer Vision
(2)
Application Areas
(2)
Core AI
(2)
Generation · Natural Language Processing
(2)
Optimization & Theory
(2)
Processing
(2)
Core Methods
(1)
Generation · Computer Vision
(1)
Learning Paradigms
(1)
Keywords
neural architecture search
(2)
audio source separation
(2)
multi-task learning
(2)
video captioning
(1)
text generation
(1)
multimodal learning
(1)
code generation
(1)
neural network optimization
(1)
importance sampling
(1)
feature interaction
(1)
diffusion model
(1)
deep neural network
(1)
language model
(1)
foundation model
(1)
controllable generation
(1)
text-to-video generation
(1)
inference acceleration
(1)
gradient variance
(1)
visual tokenizer
(1)
discrete tokenization
(1)
Papers
VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation
ACL 2025
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs
COLING 2024
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
ICLR 2024
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
ICML 2024
MaskFusion: Feature Augmentation for Click-Through Rate Prediction via Input-adaptive Mask Fusion
ICLR 2023
PA&DA: Jointly Sampling Path and Data for Consistent NAS
CVPR 2023
Conformer Space Neural Architecture Search for Multi-Task Audio Separation
Interspeech 2022
WA-Transformer: Window Attention-based Transformer with Two-stage Strategy for Multi-task Audio Source Separation
Interspeech 2022