6 papers · 1 filter
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
Tingyu Song, Mingxin Li, Yanzhao Zhang +5
MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing the same concepts but different attribute-object bindings. Yet…
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
Diandian Zhang, Tingyu Song, Lin Fu +2
We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated…
UEmbed: Unified Sparse and Dense Multimodal Embeddings
Tingyu Song, Mingxin Li, Yanzhao Zhang +5
Sparse retrieval underpins modern search systems, from web search to retrieval-augmented generation. Existing work has introduced Learned Sparse Retrieval (LSR) to push beyond exac…
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
Lin Fu, Zheyuan Yang, Yang Wang +3
We introduce VideoKR, the first large-scale training corpus specifically designed to strengthen knowledge- and reasoning-intensive video understanding. It comprises 315K video reas…
Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing
Tingyu Song, Yanzhao Zhang, Mingxin Li +6
Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the…
VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos
Tingyu Song, Tongyan Hu, Guo Gan +1
MLLMs have been widely studied for video question answering recently. However, most existing assessments focus on natural videos, overlooking synthetic videos, such as AI-generated…