Jun Song
23 papers · 2024–2026 · 7 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 (46) π Conference Polyglot Β· Silver π¬ Deep Specialist (10) π€ Dynamic Duo (16)
ποΈ
Keyword Collector
(110)
β‘
Prolific Year Β· Prolific
π
Renaissance Researcher
(7)
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(17)
Core AI Β· Artificial Intelligence
(17)
Deep Learning
(10)
Machine Learning
(10)
Models
(6)
Computer Vision
(5)
Learning Types Β· Machine Learning
(5)
Application Areas
(4)
Learning Types Β· Deep Learning
(4)
Reinforcement Learning
(3)
Architectures
(3)
Methods
(3)
Optimization & Theory
(3)
Natural Language Processing
(2)
Core AI Β· Computer Vision
(2)
Keywords
vision-language model
(8)
reinforcement learning
(5)
video understanding
(4)
multimodal large language model
(3)
benchmark evaluation
(3)
image generation
(3)
multimodal learning
(3)
vision transformer
(2)
visual question answering
(2)
video large language model
(2)
token compression
(2)
mobile agent
(2)
large vision-language model
(2)
direct preference optimization
(1)
preference learning
(1)
dataset creation
(1)
action recognition
(1)
object recognition
(1)
policy optimization
(1)
factuality evaluation
(1)
Papers
AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
CVPR 2026
Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
AAAI 2026
DeepPhy: Benchmarking Agentic VLMs on Physical Reasoning
AAAI 2026
GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
CVPR 2026
Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
AAAI 2026
How Foundational Skills Influence VLM-based Embodied Agents: A Native Perspective
AAAI 2026
InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning
ACL 2026
LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid
AAAI 2026
MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
AAAI 2026
Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
ACL 2026
SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation
CVPR 2026
Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
CVPR 2026
Unified Thinker: A General Reasoning Core for Image Generation
ACL 2026
ViT$^3$: Unlocking Test-Time Training in Vision
CVPR 2026
CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
ICCV 2025
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
ACL 2025
POI Recommendation via Multi-Objective Adversarial Imitation Learning
AAAI 2025
RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
CVPR 2025
See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models
ACL 2025
Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
EMNLP 2025
Demystify Mamba in Vision: A Linear Attention Perspective
NeurIPS 2024
Enhancing Sufficient Dimension Reduction via Hellinger Correlation
ICML 2024
GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation
EMNLP 2024