Fanhu Zeng
8 papers · 2025–2026 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (18) ⭐ Rising Star (8) ❓ The Questioner
⚡
Prolific Year · Productive
Top co-authors
Research topics
Deep Learning
(5)
Machine Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Learning Types · Machine Learning
(3)
Computer Vision
(2)
Models
(2)
Optimization & Theory
(2)
Natural Language Processing
(1)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Learning Paradigms · Machine Learning
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Types · Deep Learning
(1)
Keywords
instruction tuning
(2)
prompt learning
(2)
multimodal large language model
(2)
large multimodal model
(2)
catastrophic forgetting
(1)
benchmark evaluation
(1)
few-shot learning
(1)
image generation
(1)
video generation
(1)
knowledge distillation
(1)
code generation
(1)
visual reasoning
(1)
image compression
(1)
context modeling
(1)
state space model
(1)
data heterogeneity
(1)
out-of-distribution detection
(1)
vision-language model
(1)
classifier-free guidance
(1)
mechanistic interpretability
(1)
Papers
Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
CVPR 2026
TR-DQ: Time-Rotation Diffusion Quantization
AAAI 2026
ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs’ Capability via Chart Editing
ACL 2025
Federated Continual Instruction Tuning
ICCV 2025
HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model
ACL 2025
Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection
ICLR 2025
MambaIC: State Space Models for High-Performance Learned Image Compression
CVPR 2025
ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt
EMNLP 2025