Ruqi Zhang

papers

218

total citations

papers (11)

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

ICML 2024arXiv

citations

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

ICLR 2025arXiv

citations

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent

NEURIPS 2022arXiv

citations

Adaptive Draft-Verification for Efficient Large Language Model Decoding

AAAI 2025arXiv

citations

Sherlock: Self-Correcting Reasoning in Vision-Language Models

NEURIPS 2025arXiv

citations

Entropy-MCMC: Sampling from Flat Basins with Ease

ICLR 2024arXiv

citations

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

COLM 2025arXiv

citations

DISCS: A Benchmark for Discrete Sampling

NEURIPS 2023

citations

Ruqi Zhang

papers (11)

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

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

Cascade Reward Sampling for Efficient Decoding-Time Alignment

Asymptotically Optimal Exact Minibatch Metropolis-Hastings

Rethinking Data Distillation: Do Not Overlook Calibration

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent

Adaptive Draft-Verification for Efficient Large Language Model Decoding

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Entropy-MCMC: Sampling from Flat Basins with Ease

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

DISCS: A Benchmark for Discrete Sampling

papers (11)

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

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

Cascade Reward Sampling for Efficient Decoding-Time Alignment

Asymptotically Optimal Exact Minibatch Metropolis-Hastings

Rethinking Data Distillation: Do Not Overlook Calibration

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent

Adaptive Draft-Verification for Efficient Large Language Model Decoding

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Entropy-MCMC: Sampling from Flat Basins with Ease

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

DISCS: A Benchmark for Discrete Sampling