Jingtao Li
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
On the Limits of Token Reduction for Efficient Unified Vision Language Training
The paper analyzes token reduction for efficient unified VLM training, finding that while task-specific acceleration saves computation, it destroys the mutual performance gains achieved through joint optimization.
Highlighted terms show continued research focus across papers