Bohan Wang
22 papers · 2020–2025 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Renaissance Researcher (7) π Interdisciplinary Bridge π Conference Polyglot (9) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (39)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(9)
π
Keyword Champion
(4)
β‘
Prolific Year
(5)
π
Century Club
(22)
β
The Questioner
ποΈ
Keyword Collector
(89)
π₯
Unstoppable
(6)
Conferences
NIPS (7)
ICLR (5)
CVPR (3)
EMNLP (2)
COLT (1)
ICCV (1)
ICML (1)
INTERSPEECH (1)
UAI (1)
Top co-authors
Research topics
Keywords
adam optimizer
(4)
neural network
(3)
gradient descent
(3)
generalization bound
(3)
learning rate
(2)
action recognition
(1)
feature learning
(1)
learning theory
(1)
object detection
(1)
scene classification
(1)
video generation
(1)
video synthesis
(1)
preference learning
(1)
attention mechanism
(1)
semantic segmentation
(1)
privacy preservation
(1)
model architecture
(1)
principal component analysis
(1)
computer graphics
(1)
convergence analysis
(1)
Papers
TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes
ICLR 2025
AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training
EMNLP 2025
BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training
EMNLP 2025
Synthetic Video Enhances Physical Fidelity in Video Synthesis
ICCV 2025
Physically Compatible 3D Object Modeling from a Single Image
NIPS 2024
Learning Multi-Dimensional Human Preference for Text-to-Image Generation
CVPR 2024
DiGress: Discrete Denoising diffusion for graph generation
ICLR 2023
Regularization of Polynomial Networks for Image Recognition
CVPR 2023
Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions
COLT 2023
$\mathcal{O}$-GNN: incorporating ring priors into molecular modeling
ICLR 2023
Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions
NIPS 2023
Closing the gap between the upper bound and lower bound of Adam's iteration complexity
NIPS 2023
On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training
NIPS 2023
ALO-VC: Any-to-any Low-latency One-shot Voice Conversion
INTERSPEECH 2023
Creating Training Sets via Weak Indirect Supervision
ICLR 2022
Does Momentum Change the Implicit Regularization on Separable Data?
NIPS 2022
Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms
UAI 2021
Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD
NIPS 2021
End-to-End Human Object Interaction Detection With HOI Transformer
CVPR 2021
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
ICML 2021
See More for Scene: Pairwise Consistency Learning for Scene Classification
NIPS 2021
Piecewise linear activations substantially shape the loss surfaces of neural networks
ICLR 2020