Jun Song

Venues

Frequent coauthors

Papers

1. Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
   AAAI 2026 ·

   Yinchao Ma

   DBLP profile ↗ORCID search ↗
2. DeepPhy: Benchmarking Agentic VLMs on Physical Reasoning
   AAAI 2026 ·

   Xinrun Xu

   DBLP profile ↗ORCID search ↗
3. Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal Language
   ACL 2026 ·

   Peijie Wang

   DBLP profile ↗ORCID search ↗
4. Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
   AAAI 2026 ·

   Xuyang Liu

   DBLP profile ↗ORCID search ↗
5. How Foundational Skills Influence VLM-based Embodied Agents: A Native Perspective
   AAAI 2026 ·

   Bo Peng

   DBLP profile ↗ORCID search ↗
6. InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning
   ACL 2026 ·

   Qihang Ai

   DBLP profile ↗ORCID search ↗
7. LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid
   AAAI 2026 ·

   Yipeng Zhang

   DBLP profile ↗ORCID search ↗
8. MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
   AAAI 2026 ·

   Junpeng Ma

   DBLP profile ↗ORCID search ↗
9. MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding
   WSDM 2026 ·

   Daoze Zhang

   DBLP profile ↗ORCID search ↗
10. Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
    ACL 2026 ·

    Jihao Gu

    DBLP profile ↗ORCID search ↗
11. Unified Thinker: A General Reasoning Core for Image Generation
    ACL 2026 ·

    Sashuai Zhou

    DBLP profile ↗ORCID search ↗
12. CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
    ICCV 2025 ·

    Peng Chen

    DBLP profile ↗ORCID search ↗
13. LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
    ACL 2025 ·

    Chao Deng

    DBLP profile ↗ORCID search ↗
14. Magnus: A Holistic Approach to Data Management for Large-Scale Machine Learning Workloads
    VLDB 2025 · Jun Song
15. POI Recommendation via Multi-Objective Adversarial Imitation Learning
    AAAI 2025 ·

    Zhenglin Wan

    DBLP profile ↗ORCID search ↗
16. RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
    CVPR 2025 ·

    Tianyu Yu

    DBLP profile ↗ORCID search ↗
17. See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models
    ACL 2025 ·

    Jihao Gu

    DBLP profile ↗ORCID search ↗
18. Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
    EMNLP 2025 ·

    Jihao Gu

    DBLP profile ↗ORCID search ↗
19. Demystify Mamba in Vision: A Linear Attention Perspective
    NeurIPS 2024 ·

    Dongchen Han

    DBLP profile ↗ORCID search ↗
20. Enhancing Sufficient Dimension Reduction via Hellinger Correlation
    ICML 2024 ·

    Seungbeom Hong

    DBLP profile ↗ORCID search ↗
21. GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation
    EMNLP 2024 ·

    Shihao Cai

    DBLP profile ↗ORCID search ↗