Lei Ji
28 papers · 2019–2026 · 11 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 ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (51) π Conference Polyglot Β· Gold π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Diamond π£ Hot Topic Early Bird
π€
Dynamic Duo
(15)
π§
Keyword Pioneer
π
Grand Slam
π§¬
Topic Evolution
π¬
Deep Specialist
(10)
π
Renaissance Researcher
(7)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(129)
Venues
Top co-authors
Research topics
Artificial Intelligence
(17)
Core AI
(17)
Computer Vision
(12)
Machine Learning
(12)
Deep Learning
(10)
Natural Language Processing
(9)
Learning Types Β· Machine Learning
(6)
Processing
(6)
Application Areas
(5)
Applications
(5)
Learning Types Β· Deep Learning
(5)
Core Methods
(4)
Generation
(4)
Architectures
(3)
Domain-Specific
(3)
Keywords
video understanding
(7)
multimodal learning
(5)
instructional video
(3)
large language model
(3)
video captioning
(2)
video question answering
(2)
chest x-ray
(2)
contrastive learning
(2)
vision-language model
(2)
visual reasoning
(2)
language modeling
(1)
commonsense knowledge
(1)
chain-of-thought reasoning
(1)
visual question answering
(1)
image generation
(1)
knowledge distillation
(1)
human-object interaction
(1)
attention mechanism
(1)
sequence labeling
(1)
cross-modal learning
(1)
Papers
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training
ACL 2026
Too Long, Do Re-weighting for Efficient LLM Reasoning Compression
ACL 2026
Explore the Reasoning Capability of LLMs in the Chess Testbed
NAACL 2025
Generative Prompt Internalization
NAACL 2025
Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling
ICML 2025
ToolGen: Unified Tool Retrieval and Calling via Generation
ICLR 2025
AssistGUI: Task-Oriented PC Graphical User Interface Automation
CVPR 2024
Exploring Diffusion Time-steps for Unsupervised Representation Learning
ICLR 2024
HORIZON: High-Resolution Semantically Controlled Panorama Synthesis
AAAI 2024
Voila-A: Aligning Vision-Language Models with User's Gaze Attention
NeurIPS 2024
CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding
ACL 2023
EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images
NeurIPS 2023
KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization
ACL 2023
MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering
CVPR 2023
Learning Temporal Video Procedure Segmentation From an Automatically Collected Large Dataset
WACV 2022
NΓWA: Visual Synthesis Pre-training for Neural visUal World creAtion
ECCV 2022
Trace Controlled Text to Image Generation
ECCV 2022
Control Image Captioning Spatially and Temporally
ACL 2021
GEM: A General Evaluation Benchmark for Multimodal Tasks
ACL 2021
Hashing based Efficient Inference for Image-Text Matching
ACL 2021
Hierarchical Context-aware Network for Dense Video Event Captioning
ACL 2021
Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering
NeurIPS 2021
A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos
EMNLP 2020
Functionality Discovery and Prediction of Physical Objects
AAAI 2020
GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis
EMNLP 2020
Segment-Then-Rank: Non-Factoid Question Answering on Instructional Videos
AAAI 2020
Dense Procedure Captioning in Narrated Instructional Videos
ACL 2019
Knowledge Aware Semantic Concept Expansion for Image-Text Matching
IJCAI 2019