Ruqi Zhang

27 papers · 2016–2026 · 9 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (9) 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (12) 🗺️ Taxonomy Completionist (31) 🌍 Conference Polyglot (9) 👑 Triple Crown 🏆 Grand Slam 👥 Mega-Team (25) 🏆 Keyword Champion (3) 💎 Century Club (26) ⚡ Prolific Year (5) 🗃️ Keyword Collector (70) 🔥 Unstoppable (7)

Conferences

ICLR (6) ICML (5) NIPS (5) AISTATS (4) AAAI (3) ACL (1) EMNLP (1) ICCV (1) IJCAI (1)

Top co-authors

Bowen Lei (4) Bolian Li (4) Dongkuan Xu (3) Christopher De Sa (3) Andrew Gordon Wilson (3) Christopher M De Sa (2) Xinyu Luo (2) Dongyao Zhu (2) Yingzhen Li (2) Hengrong Du (2)

Keywords

markov chain monte carlo (9) discrete sampling (3) gradient-based sampling (3) langevin dynamics (3) large language model (3) variational inference (3) discrete distribution (3) bayesian inference (3) energy-based model (2) uncertainty quantification (2) gibbs sampling (2) graphical model (2) bayesian sampling (2) metropolis-hastings algorithm (2) convergence guarantee (2) chain-of-thought reasoning (1) kl divergence (1) mathematical reasoning (1) logical reasoning (1) few-shot learning (1)

Papers

Exploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange AAAI 2026

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner EMNLP 2025

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time ICLR 2025

Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization ICML 2025

Optimal Stochastic Trace Estimation in Generative Modeling AISTATS 2025

Controlled LLM Decoding via Discrete Auto-regressive Biasing ICLR 2025

Adaptive Draft-Verification for Efficient Large Language Model Decoding AAAI 2025

Scalable and Efficient Probabilistic Inference for Bayesian Deep Learning and Generative Modeling AAAI 2025

CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought ACL 2025

Entropy-MCMC: Sampling from Flat Basins with Ease ICLR 2024

Training Bayesian Neural Networks with Sparse Subspace Variational Inference ICLR 2024

Gradient-based Discrete Sampling with Automatic Cyclical Scheduling NIPS 2024

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI ICML 2024

Rethinking Data Distillation: Do Not Overlook Calibration ICCV 2023

DISCS: A Benchmark for Discrete Sampling NIPS 2023

Efficient Informed Proposals for Discrete Distributions via Newton’s Series Approximation AISTATS 2023

Calibrating the Rigged Lottery: Making All Tickets Reliable ICLR 2023

DP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inference ICML 2023

A Langevin-like Sampler for Discrete Distributions ICML 2022

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent NIPS 2022

Low-Precision Stochastic Gradient Langevin Dynamics ICML 2022

Meta-Learning Divergences for Variational Inference AISTATS 2021

Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning ICLR 2020

Asymptotically Optimal Exact Minibatch Metropolis-Hastings NIPS 2020

AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC AISTATS 2020

Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees NIPS 2019

Large Scale Sparse Clustering IJCAI 2016