PPaperPicks

Ruqi Zhang

18 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Exploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange
  2. Adaptive Draft-Verification for Efficient Large Language Model Decoding
  3. CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought
  4. Controlled LLM Decoding via Discrete Auto-regressive Biasing
  5. Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion
  6. ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
  7. On Learning Closed-Loop Probabilistic Multi-Agent Simulator
  8. Optimal Stochastic Trace Estimation in Generative Modeling
  9. Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner
  10. Scalable and Efficient Probabilistic Inference for Bayesian Deep Learning and Generative Modeling
    AAAI 2025 · Ruqi Zhang
  11. Sherlock: Self-Correcting Reasoning in Vision-Language Models
  12. Stacey: Promoting Stochastic Steepest Descent via Accelerated ℓp-Smooth Nonconvex Optimization
  13. VERA: Variational Inference Framework for Jailbreaking Large Language Models
  14. Adaptive Planning with Generative Models under Uncertainty
  15. Entropy-MCMC: Sampling from Flat Basins with Ease
  16. Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
  17. Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
  18. Training Bayesian Neural Networks with Sparse Subspace Variational Inference