Haochen Zhang
15 papers · 2017–2026 · 11 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (34) π Conference Polyglot Β· Gold π£ Hot Topic Early Bird π Academic Marathon Β· Sprint
π
Renaissance Researcher
(6)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(75)
Venues
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory
(5)
Artificial Intelligence
(4)
Mathematics & Optimization
(4)
Optimization
(4)
Computer Vision
(3)
Deep Learning
(3)
Natural Language Processing
(3)
Reinforcement Learning
(3)
Application Areas
(3)
Core AI
(3)
Learning Types Β· Machine Learning
(3)
Methods
(3)
Applications
(2)
Learning Types Β· Deep Learning
(2)
Keywords
regret bound
(3)
sub-optimality gap
(2)
federated q-learning
(2)
large language model
(2)
communication cost
(2)
reference-advantage decomposition
(2)
domain adaptation
(1)
image generation
(1)
learning theory
(1)
knowledge distillation
(1)
chain-of-thought reasoning
(1)
sample complexity
(1)
vocabulary expansion
(1)
video super-resolution
(1)
personalized generation
(1)
action recognition
(1)
instruction tuning
(1)
task generalization
(1)
markov decision process
(1)
scene understanding
(1)
Papers
Conversational Image Generation: Towards Multi-Round Personalized Generation with Multi-Modal Language Models
WACV 2026
FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy
WACV 2026
Mortise: Auto-tuning Congestion Control to Optimize QoE via Network-Aware Parameter Optimization
NSDI 2026
Class-Conditioned Image Synthesis with Diffusion for Imbalanced Diabetic Retinopathy Grading
MICCAI 2025
CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems
ACL 2025
Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
ICLR 2025
Gap-Dependent Bounds for Federated Q-Learning
ICML 2025
Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition
ICLR 2025
Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory
AISTATS 2025
Jellyfish: Instruction-Tuning Local Large Language Models for Data Preprocessing
EMNLP 2024
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
NeurIPS 2023
Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective
ICCV 2021
On The Classification-Distortion-Perception Tradeoff
NeurIPS 2019
Two-Stream Action Recognition-Oriented Video Super-Resolution
ICCV 2019
From Decimation to Local Search and Back: A New Approach to MaxSAT
IJCAI 2017