Jingyao Li
13 papers · 2023–2026 · 7 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 ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (30) π Conference Polyglot Β· Silver π€ Dynamic Duo (10) ποΈ Keyword Collector (65)
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(7)
Core AI
(7)
Deep Learning
(6)
Application Areas
(5)
Natural Language Processing
(3)
Learning Types Β· Machine Learning
(3)
Models
(3)
Resources & Methods
(3)
Computer Vision
(2)
Core Methods
(2)
Generation
(2)
Learning Types Β· Deep Learning
(2)
Optimization & Theory
(2)
Processing
(2)
Keywords
attention mechanism
(2)
length extrapolation
(2)
large language model
(2)
image generation
(2)
image editing
(2)
vision-language model
(2)
multimodal large language model
(2)
transformer architecture
(2)
data valuation
(1)
ensemble learning
(1)
benchmark evaluation
(1)
text-to-image generation
(1)
video understanding
(1)
efficient computing
(1)
image-text pair
(1)
cross-modal learning
(1)
synthetic data
(1)
language model
(1)
question answering
(1)
feature map
(1)
Papers
CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
AAAI 2026
DreamOmni2: Multimodal Instruction-based Generation and Editing
CVPR 2026
Unlocking Token Rewards via Training-Free Reward Attribution
CVPR 2026
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation
ACL 2025
DreamOmni: Unified Image Generation and Editing
CVPR 2025
Logits-Based Finetuning
EMNLP 2025
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
ICCV 2025
Mixture-of-Scores: Robust Image-Text Data Valuation via Three Lines of Code
ICCV 2025
QuickLLaMA: Query-aware Inference Acceleration for Large Language Models
COLING 2025
VisionZip: Longer is Better but Not Necessary in Vision Language Models
CVPR 2025
DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
NeurIPS 2024
MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
NeurIPS 2024
Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need
CVPR 2023