7 papers · 1 filter
Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering
Hangrui Xu, Zhengxian Wu, Yunyao Yu +6
Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, existing retrieval pipelines p…
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
Wanli Li, Bowen Zhou, Yunyao Yu +4
Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchm…
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering
ZhengXian Wu, Hangrui Xu, Kai Shi +8
Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge. Most prior methods use a fixed retrieve-then-generate pip…
SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation
Yu Yu, Chen Lyu
With the remarkable progress of Code Large Language Models (Code LLMs) in achieving semantic correctness, execution efficiency has become an increasingly important dimension for ev…
Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation
Yu Yu, Zhihong Sun, Jia Li +8
Large Language Models (LLMs) are capable of generating syntactically correct and functionally complete programs, greatly streamlining software development. However, recent studies…
Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling
Yunyao Yu, Zhengxian Wu, Zhuohong Chen +6
In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for stable and effective learning. However,…
Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering
Zhuohong Chen, Zhenxian Wu, Yunyao Yu +6
Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts…