Kaixuan Huang
17 papers · 2020–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Renaissance Researcher (5) π Interdisciplinary Bridge π Conference Polyglot (6) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (18)
πΊοΈ
Taxonomy Completionist
(18)
π§
Keyword Pioneer
π
Triple Crown
π
Grand Slam
π€
Dynamic Duo
(11)
ποΈ
Keyword Collector
(54)
β‘
Prolific Year
(6)
β
The Questioner
π
Century Club
(17)
Conferences
NIPS (6)
ICML (4)
ICLR (3)
EMNLP (2)
AAAI (1)
IJCAI (1)
Top co-authors
Keywords
distribution estimation
(2)
deep reinforcement learning
(2)
neural tangent kernel
(1)
adversarial robustness
(1)
mathematical reasoning
(1)
direct preference optimization
(1)
sample complexity
(1)
low-rank matrix
(1)
deep learning theory
(1)
policy learning
(1)
language model alignment
(1)
theoretical analysis
(1)
markov chain
(1)
reward function
(1)
score approximation
(1)
convergence analysis
(1)
score estimation
(1)
diffusion model
(1)
bandit optimization
(1)
sample efficiency
(1)
Papers
Deep Reinforcement Learning for Efficient and Fair Allocation of Healthcare Resources
IJCAI 2025
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
EMNLP 2025
Temporal Consistency for LLM Reasoning Process Error Identification
EMNLP 2025
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
ICLR 2025
MATH-Perturb: Benchmarking LLMsβ Math Reasoning Abilities against Hard Perturbations
ICML 2025
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
ICML 2025
Visual Adversarial Examples Jailbreak Aligned Large Language Models
AAAI 2024
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
ICML 2024
A Theoretical Perspective for Speculative Decoding Algorithm
NIPS 2024
Deep Reinforcement Learning for Cost-Effective Medical Diagnosis
ICLR 2023
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
ICML 2023
Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
NIPS 2023
Fast Federated Learning in the Presence of Arbitrary Device Unavailability
NIPS 2021
Going Beyond Linear RL: Sample Efficient Neural Function Approximation
NIPS 2021
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
NIPS 2021
On the Convergence of FedAvg on Non-IID Data
ICLR 2020
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective
NIPS 2020