Ruiqi Zhang
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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (27) ποΈ Keyword Collector (66)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory
(7)
Deep Learning
(5)
Learning Types
(4)
Artificial Intelligence
(3)
Computer Vision
(3)
Reinforcement Learning
(3)
Architectures
(3)
Methods
(3)
Models
(3)
Mathematics & Optimization
(2)
Analysis
(2)
Learning Paradigms
(2)
Optimization
(2)
Natural Language Processing
(1)
Keywords
gradient descent
(3)
logistic regression
(2)
large language model
(2)
surface reconstruction
(2)
in-context learning
(2)
asymptotic normality
(2)
reinforcement learning
(2)
gaussian splatting
(1)
policy gradient
(1)
off-policy evaluation
(1)
perceptron algorithm
(1)
image compression
(1)
image reconstruction
(1)
variance reduction
(1)
point cloud
(1)
value function approximation
(1)
minimax optimality
(1)
covariate shift
(1)
importance sampling
(1)
question decomposition
(1)
Papers
Deep Inverse Shading: Consistent Albedo and Surface Detail Recovery via Generative Refinement
AAAI 2026
DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
CVPR 2026
Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
JMLR 2026
Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes
ICML 2025
Mitigating Ambiguities in 3D Classification with Gaussian Splatting
CVPR 2025
AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition
NAACL 2024
Fast Best-of-N Decoding via Speculative Rejection
NeurIPS 2024
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
NeurIPS 2024
Trained Transformers Learn Linear Models In-Context
JMLR 2024
Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
NeurIPS 2023
NDF: Neural Deformable Fields for Dynamic Human Modelling
ECCV 2022
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
ICML 2022
Optimal Estimation of Policy Gradient via Double Fitted Iteration
ICML 2022