11 papers
Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher
Hongming Piao, Chi Liu, Mengzhuo Chen +5
Deep research and agent evolution serve as de-facto tasks for AI agents in real-world applications toward artificial general intelligence. The former enables autonomous retrieval a…
DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning
Hangui Lin, Yan Shu, Zhengyang Liang +6
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a leading paradigm for enhancing visual reasoning in Multimodal Large Language Models (MLLMs). However, existin…
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
Xiyu Ren, Zhaowei Wang, Yiming Du +11
Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and m…
SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Models
Bin Zhang, Yuxiao Ye, Guoqing Du +8
Large Language Models (LLMs) have emerged as a powerful tool in advancing the Text-to-SQL task, significantly outperforming traditional methods.Nevertheless, as a nascent research…
DALL: Data Labeling via Data Programming and Active Learning Enhanced by Large Language Models
Guozheng Li, Ao Wang, Shaoxiang Wang +4
Deep learning models for natural language processing rely heavily on high-quality labeled datasets. However, existing labeling approaches often struggle to balance label quality wi…
Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models
Yijun Yang, Lichao Wang, Jianping Zhang +3
The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, th…