Profiles2024-2026
Jun Song
Alibaba Group
5Papers
0Last author
10Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers5
- ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data SynthesisAuthor 7 of 8ICLR 2026 · 24 citations
- Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual ReasoningAuthor 7 of 9ICLR 2026 · 7 citations
- How Foundational Skills Influence VLM-based Embodied Agents: A Native PerspectiveAuthor 9 of 10AAAI 2026 · 1 citation
- LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and LocatingAuthor 9 of 11ACL 2025
- GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image GenerationAuthor 5 of 6EMNLP 2024 · 10 citations
