Sheng Liu
28 papers · 2020–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Academic Marathon (5) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (8) π Cross-Pollinator (10)
π
Cross-Pollinator
(10)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(54)
π
Grand Slam
π
Century Club
(23)
β‘
Prolific Year
(6)
ποΈ
Keyword Collector
(121)
π₯
Unstoppable
(6)
Conferences
AAAI (6)
CVPR (6)
ICML (4)
NIPS (4)
ICLR (3)
ACL (2)
AISTATS (1)
EMNLP (1)
ICCV (1)
Top co-authors
Keywords
label noise
(4)
contrastive learning
(3)
deep neural network
(3)
representation learning
(2)
early learning
(2)
self-supervised learning
(2)
large language model
(2)
noisy label
(2)
semi-supervised learning
(2)
metric learning
(1)
image restoration
(1)
image generation
(1)
image retrieval
(1)
hyperparameter optimization
(1)
benchmark evaluation
(1)
sparse recovery
(1)
temporal modeling
(1)
noisy label learning
(1)
iterative optimization
(1)
sampling strategy
(1)
Papers
ViLL-E: Video LLM Embeddings for Retrieval
ACL 2026
OctoTools: A Multi-Agent Framework with Extensible Tools for Complex Reasoning
ACL 2026
SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation
AAAI 2026
Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry Network
AAAI 2026
SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal Reasoning
AAAI 2026
Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks
EMNLP 2025
OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition
AAAI 2025
OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems
AAAI 2025
Data Reconstruction Attacks and Defenses: A Systematic Evaluation
AISTATS 2025
Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering
ICLR 2025
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
ICLR 2025
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
ICML 2024
TFG: Unified Training-Free Guidance for Diffusion Models
NIPS 2024
In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
ICML 2024
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning
CVPR 2023
PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
ICCV 2023
LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization
CVPR 2023
Avoiding spurious correlations via logit correction
ICLR 2023
Adaptive Early-Learning Correction for Segmentation From Noisy Annotations
CVPR 2022
Are All Losses Created Equal: A Neural Collapse Perspective
NIPS 2022
Deep Probability Estimation
ICML 2022
Robust Training under Label Noise by Over-parameterization
ICML 2022
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
CVPR 2022
On Learning Contrastive Representations for Learning With Noisy Labels
CVPR 2022
Depth-Guided Sparse Structure-From-Motion for Movies and TV Shows
CVPR 2022
OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning
AAAI 2022
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
NIPS 2021
Early-Learning Regularization Prevents Memorization of Noisy Labels
NIPS 2020