Yuanxin Liu
25 papers · 2018–2026 · 11 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
π Conference Polyglot (11) π Academic Marathon (7) π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (5)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(52)
π£
Hot Topic Early Bird
π€
Dynamic Duo
(12)
π
Keyword Champion
(2)
π§¬
Topic Evolution
π
Grand Slam
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(88)
π
Trend Setter
π
Century Club
(23)
π₯
Unstoppable
(5)
β
The Questioner
Conferences
EMNLP (7)
ACL (4)
NIPS (3)
AAAI (2)
IJCAI (2)
IJCNLP (2)
CONLL (1)
ECCV (1)
ICLR (1)
ICML (1)
NAACL (1)
Top co-authors
Keywords
model compression
(6)
image captioning
(4)
visual question answering
(4)
knowledge distillation
(3)
multimodal learning
(3)
dataset bia
(2)
neural network pruning
(2)
video large language model
(2)
domain generalization
(2)
visual attention
(2)
transfer learning
(2)
sampling strategy
(2)
vision-language model
(2)
multimodal large language model
(2)
neural network optimization
(2)
model pruning
(2)
supervised fine-tuning
(2)
bert compression
(2)
question answering
(2)
hidden state knowledge
(2)
Papers
Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
ACL 2026
TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment
AAAI 2026
RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
EMNLP 2025
PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
ACL 2025
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
ICML 2025
Temporal Reasoning Transfer from Text to Video
ICLR 2025
VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
ECCV 2024
TempCompass: Do Video LLMs Really Understand Videos?
ACL 2024
Compressing and Debiasing Vision-Language Pre-Trained Models for Visual Question Answering
EMNLP 2023
FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation
NIPS 2023
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA
EMNLP 2022
A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
NIPS 2022
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models
EMNLP 2022
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
EMNLP 2022
Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training
NAACL 2022
Learning Class-Transductive Intent Representations for Zero-shot Intent Detection
IJCAI 2021
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
ACL 2021
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
IJCNLP 2021
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques
AAAI 2021
Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
NIPS 2019
Self-Adaptive Scaling for Learnable Residual Structure
CONLL 2019
Exploring and Distilling Cross-Modal Information for Image Captioning
IJCAI 2019
Ranking and Sampling in Open-Domain Question Answering
IJCNLP 2019
Ranking and Sampling in Open-Domain Question Answering
EMNLP 2019
simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions
EMNLP 2018