Junpeng Ma
5 papers · 2024–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌈
Renaissance Researcher
(5)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
ACL (1)
CVPR (1)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
video large language model
(2)
video understanding
(2)
image generation
(1)
knowledge distillation
(1)
continual adaptation
(1)
multimodal large language model
(1)
parameter quantization
(1)
inference acceleration
(1)
video language model
(1)
visual token
(1)
token compression
(1)
visual token pruning
(1)
adapter-based learning
(1)
pixel-level feedback
(1)
segment-level modeling
(1)
marginal gain
(1)
token-level optimization
(1)
frame compression
(1)
task-agnostic reasoning
(1)
model compression
(1)
Papers
MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
AAAI 2026
Unified Thinker: A General Reasoning Core for Image Generation
ACL 2026
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
EMNLP 2025
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
ICML 2025
Cloud-Device Collaborative Learning for Multimodal Large Language Models
CVPR 2024