Ximeng Sun
15 papers · 2019–2026 · 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (45) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(84)
Top co-authors
Research topics
Computer Vision
(9)
Deep Learning
(9)
Artificial Intelligence
(8)
Machine Learning
(8)
Core AI Β· Artificial Intelligence
(8)
Application Areas
(5)
Learning Types Β· Deep Learning
(5)
Processing
(5)
Analysis
(3)
Generation
(3)
Learning Types Β· Machine Learning
(3)
Techniques
(3)
Architectures
(2)
Core AI Β· Computer Vision
(2)
Models
(2)
Keywords
large language model
(4)
knowledge distillation
(3)
neural network
(3)
video understanding
(3)
adversarial learning
(2)
action recognition
(2)
zero-shot learning
(2)
vision-language model
(2)
video recognition
(2)
variational inference
(2)
model compression
(2)
question answering
(2)
structured prediction
(1)
computer vision
(1)
multi-task learning
(1)
domain adaptation
(1)
transfer learning
(1)
unsupervised learning
(1)
image generation
(1)
mathematical reasoning
(1)
Papers
CaptionQA: Is Your Caption as Useful as the Image Itself?
CVPR 2026
Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement Learning
ACL 2026
VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
CVPR 2026
Agent Laboratory: Using LLM Agents as Research Assistants
EMNLP 2025
Self-Taught Agentic Long Context Understanding
ACL 2025
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
CVPR 2025
Improved Techniques for Quantizing Deep Networks With Adaptive Bit-Widths
WACV 2024
Koala: Key Frame-Conditioned Long Video-LLM
CVPR 2024
DIME-FM : DIstilling Multimodal and Efficient Foundation Models
ICCV 2023
DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations
NeurIPS 2022
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition
ICCV 2021
Dynamic Network Quantization for Efficient Video Inference
ICCV 2021
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
NeurIPS 2020
TwoStreamVAN: Improving Motion Modeling in Video Generation
WACV 2020
Domain Agnostic Learning with Disentangled Representations
ICML 2019