7 papers
CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search
Xiaolong Sun, Qichao Wang, Hangyu Li +1
Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying visual support, conflate transi…
Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
Xiaolong Sun, Qichao Wang, Hangyu Li +1
Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon interaction. Existing methods…
UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation
Zeyang Liu, Le Wang, Sanping Zhou +4
Content-aware layout generation is a critical task in graphic design automation, focused on creating visually appealing arrangements of elements that seamlessly blend with a given…
Length Matters: Length-Aware Transformer for Temporal Sentence Grounding
Yifan Wang, Ziyi Liu, Xiaolong Sun +2
Temporal sentence grounding (TSG) is a highly challenging task aiming to localize the temporal segment within an untrimmed video corresponding to a given natural language descripti…
What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning
Yuchang Zhu, Huazhen Zhong, Qunshu Lin +6
With the remarkable generative capabilities of large language models (LLMs), using LLM-generated data to train downstream models has emerged as a promising approach to mitigate dat…
Moment Quantization for Video Temporal Grounding
Xiaolong Sun, Le Wang, Sanping Zhou +5
Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishin…
Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding
Xiaolong Sun, Liushuai Shi, Le Wang +4
Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable…