Zhanhui Kang
25 papers · 2021–2026 · 9 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 ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (54) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🤝
Dynamic Duo
(20)
👥
Mega-Team · Squad
⚡
Prolific Year · Prolific
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
🌈
Renaissance Researcher
(5)
🗃️
Keyword Collector
(134)
Top co-authors
Research topics
Artificial Intelligence
(17)
Core AI · Artificial Intelligence
(17)
Machine Learning
(16)
Deep Learning
(13)
Natural Language Processing
(10)
Learning Types · Machine Learning
(9)
Learning Types · Deep Learning
(8)
Application Areas
(6)
Architectures
(6)
Resources & Methods
(6)
Models
(5)
Optimization & Theory
(4)
Computer Vision
(3)
Applications
(2)
Core AI · Computer Vision
(2)
Keywords
multimodal learning
(3)
multimodal large language model
(3)
large language model
(3)
visual reasoning
(2)
neural network
(2)
adversarial attack
(2)
mixture of expert
(2)
state space model
(2)
sequential recommendation
(2)
vision-language model
(2)
parameter efficiency
(2)
transformer architecture
(2)
visual question answering
(2)
diffusion model
(2)
evaluation benchmark
(2)
data augmentation
(2)
preference learning
(1)
sequence modeling
(1)
transfer learning
(1)
model security
(1)
Papers
Beyond Ranking: Fine-Grained Diagnostics and Self-Improvement for MLLMs
ACL 2026
TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model
AAAI 2026
Autonomy-of-Experts Models
ICML 2025
Continuous Speech Tokenizer in Text To Speech
NAACL 2025
Enhancing Contrastive Learning Inspired by the Philosophy of “The Blind Men and the Elephant”
AAAI 2025
Exploring Forgetting in Large Language Model Pre-Training
ACL 2025
Frozen Language Models Are Gradient Coherence Rectifiers in Vision Transformers
AAAI 2025
HMoE: Heterogeneous Mixture of Experts for Language Modeling
EMNLP 2025
Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
ICCV 2025
Language Models “Grok” to Copy
NAACL 2025
Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
ACL 2025
PhD: A ChatGPT-Prompted Visual Hallucination Evaluation Dataset
CVPR 2025
QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
NAACL 2025
Scaling Laws for Floating–Point Quantization Training
ICML 2025
Sparsifying Mamba
EMNLP 2025
The Security Threat of Compressed Projectors in Large Vision-Language Models
EMNLP 2025
DINGO: Towards Diverse and Fine-Grained Instruction-Following Evaluation
AAAI 2024
LightVLP: A Lightweight Vision-Language Pre-training via Gated Interactive Masked AutoEncoders
COLING 2024
Plug-In Diffusion Model for Sequential Recommendation
AAAI 2024
SeeDRec: Sememe-based Diffusion for Sequential Recommendation
IJCAI 2024
Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
AAAI 2024
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
EMNLP 2023
TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities
ACL 2023
An Anchor-based Relative Position Embedding Method for Cross-Modal Tasks
EMNLP 2022
TexSmart: A System for Enhanced Natural Language Understanding
ACL 2021