5 papers
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging
Jie Cao, Zhenxuan Fan, Zhuonan Wang +8
Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT metho…
IPS: In-Prompt Process Supervision for Short Video Content Moderation
Mingchao Liu, Yu Sun, Ruixiao Sun +5
Multimodal large language models (MLLMs) are effective at capturing the semantics of short video content; however, they often fail to attend to the policy-specific details required…
GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
Zhaofen Wu, Hanrong Zhang, Fulin Lin +9
To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current uni…
When Rules Fall Short: Agent-Driven Discovery of Emerging Content Issues in Short Video Platforms
Chenghui Yu, Hongwei Wang, Junwen Chen +5
Trends on short-video platforms evolve at a rapid pace, with new content issues emerging every day that fall outside the coverage of existing annotation policies. However, traditio…
Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance
Zixuan Wang, Yu Sun, Hongwei Wang +6
Short video platforms are evolving rapidly, making the identification of inappropriate content increasingly critical. Existing approaches typically train separate and small classif…