Jin Song Dong
13 papers · 2022–2026 · 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (27) 🌍 Conference Polyglot · Silver 🏆 Grand Slam ⚡ Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(68)
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI · Artificial Intelligence
(8)
Computer Vision
(4)
Machine Learning
(4)
Deep Learning
(3)
Core Methods
(3)
Analysis
(2)
Learning Types
(2)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Application Areas
(1)
Core AI · Computer Vision
(1)
Domain-Specific
(1)
Generation
(1)
Learning Paradigms
(1)
Keywords
large language model
(4)
formal methods
(2)
label noise detection
(1)
data poisoning
(1)
embedding space
(1)
self-supervised learning
(1)
multimodal learning
(1)
model debugging
(1)
code generation
(1)
lane detection
(1)
autonomous driving
(1)
video understanding
(1)
fine-grained classification
(1)
deep learning
(1)
knowledge distillation
(1)
few-shot learning
(1)
gradient descent
(1)
generalization error
(1)
event detection
(1)
representation learning
(1)
Papers
CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
ACL 2026
Failures to Surface Harmful Contents in Video Large Language Models
AAAI 2026
Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation
AAAI 2026
Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications
ACL 2026
Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach
CVPR 2026
$F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
ICLR 2025
Clustering Properties of Self-Supervised Learning
ICML 2025
Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision
ICML 2025
Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods
ICML 2025
On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models
NeurIPS 2023
Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective
NeurIPS 2022
DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training
AAAI 2022
Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training
IJCAI 2022