Junpeng Ma

8 papers · 2024–2026 · 5 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 ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (18) ⚡ Prolific Year · Productive

Venues

CVPR (4) AAAI (1) ACL (1) EMNLP (1) ICML (1)

Top co-authors

Jun Song (4) Shanghang Zhang (4) Qiang Zhou (3) Zhibin Wang (3) Sashuai Zhou (3) Bo Zheng (3) Yue Cao (3) Guanghao Li (2) Xin Gao (2) Cheng Yu (2)

Research topics

Deep Learning (6) Models (5) Artificial Intelligence (4) Core AI (4) Learning Types (4) Computer Vision (3) Machine Learning (3) Application Areas (3) Processing (2) Natural Language Processing (1) Generation (1) Resources & Methods (1)

Keywords

video understanding (3) visual token (2) video large language model (2) image generation (2) reinforcement learning (2) representation alignment (1) vision-language model (1) text-to-image generation (1) reward model (1) latent representation (1) chain-of-thought reasoning (1) multimodal large language model (1) frame selection (1) parameter quantization (1) inference acceleration (1) continual adaptation (1) long-form video (1) video-language model (1) posterior collapse (1) knowledge distillation (1)

Papers

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding CVPR 2026 MacTok: Robust Continuous Tokenization for Image Generation CVPR 2026 MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs AAAI 2026 SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation CVPR 2026 Unified Thinker: A General Reasoning Core for Image Generation ACL 2026 SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference ICML 2025 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models EMNLP 2025 Cloud-Device Collaborative Learning for Multimodal Large Language Models CVPR 2024