Profiles2024-2026
Kun Ding
MAIS
8Papers
0Last author
11Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers8
- Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token InteractionsAuthor 3 of 12ICML 2026 · 4 citations
- Beyond Counting: Evaluating Abstract and Emotional Reasoning in Vision-Language ModelsAuthor 6 of 8AAAI 2026
- Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference OptimizationAuthor 3 of 11NeurIPS 2025 · 38 citations
- Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and FilteringAuthor 7 of 9NeurIPS 2025 · 25 citations
- EvoVLMA: Evolutionary Vision-Language Model AdaptationAuthor 1 of 3ACM MM 2025 · 1 citation
- Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models StrongerAuthor 4 of 6ICML 2025
- UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic SegmentationAuthor 4 of 6ICLR 2025
- Weak Distribution Detectors Lead to Stronger Generalizability of Vision-Language Prompt TuningAuthor 1 of 6AAAI 2024 · 8 citations
