Jingxuan He
13 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
๐ Renaissance Researcher (6) ๐ Conference Polyglot (6) ๐งญ Keyword Pioneer ๐ Cross-Pollinator (6) ๐ Interdisciplinary Bridge
๐
Renaissance Researcher
(6)
๐
Grand Slam
๐
Triple Crown
โ
The Questioner
๐
Century Club
(13)
โก
Prolific Year
(6)
Conferences
ICML (7)
NIPS (2)
AAAI (1)
ICLR (1)
IJCAI (1)
WACV (1)
Top co-authors
Keywords
contrastive learning
(2)
code generation
(2)
benchmark evaluation
(1)
multi-task learning
(1)
feature learning
(1)
transfer learning
(1)
domain adaptation
(1)
weakly supervised learning
(1)
distribution shift
(1)
program analysis
(1)
projected gradient descent
(1)
adversarial attack
(1)
diffusion model
(1)
synthetic datum
(1)
low-rank adaptation
(1)
video editing
(1)
test generation
(1)
software testing
(1)
code agent
(1)
bug fixing
(1)
Papers
Position: Formal Mathematical ReasoningโA New Frontier in AI
ICML 2025
Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing
IJCAI 2025
Mind the Gap: A Practical Attack on GGUF Quantization
ICML 2025
Black-Box Adversarial Attacks on LLM-Based Code Completion
ICML 2025
BaxBench: Can LLMs Generate Correct and Secure Backends?
ICML 2025
Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation
WACV 2024
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
NIPS 2024
Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation
AAAI 2024
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
ICLR 2024
Instruction Tuning for Secure Code Generation
ICML 2024
Exploiting LLM Quantization
NIPS 2024
On Distribution Shift in Learning-based Bug Detectors
ICML 2022
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer
ICML 2021