Sheng Cheng
13 papers · 2023–2026 · 8 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Gold πΊοΈ Taxonomy Completionist (36) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird ποΈ Keyword Collector (60)
π
Renaissance Researcher
(8)
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(9)
Deep Learning
(7)
Core AI
(6)
Models
(6)
Machine Learning
(5)
Application Areas
(4)
Learning Paradigms
(3)
Learning Types Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Computer Science
(2)
Computer Vision
(2)
Mathematics & Optimization
(2)
Optimization
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Keywords
diffusion model
(3)
in-context learning
(2)
large language model
(2)
text-to-image generation
(2)
contrastive learning
(2)
text-to-image diffusion
(2)
vision-language model
(2)
transfer learning
(1)
image captioning
(1)
domain generalization
(1)
question answering
(1)
document understanding
(1)
coreference resolution
(1)
bird's eye view
(1)
trajectory tracking
(1)
model fingerprinting
(1)
gradient descent
(1)
model predictive control
(1)
data augmentation
(1)
responsible ai
(1)
Papers
EROICA: Online Performance Troubleshooting for Large-scale Model Training
NSDI 2026
BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance
CVPR 2025
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
ICLR 2025
DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
AAAI 2025
Tool-Planner: Task Planning with Clusters across Multiple Tools
ICLR 2025
ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations
CVPR 2024
Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model
EMNLP 2024
Proto-MPC: An encoder-prototype-decoder approach for quadrotor control in challenging winds
L4DC 2024
SecCoder: Towards Generalizable and Robust Secure Code Generation
EMNLP 2024
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
NeurIPS 2024
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
CVPR 2024
Adversarial Bayesian Augmentation for Single-Source Domain Generalization
ICCV 2023
DiffTune$^+$: Hyperparameter-Free Auto-Tuning using Auto-Differentiation
L4DC 2023