6 papers
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
Shengyi Wang, Niantong Li, Guangzheng Hu +27
Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM…
Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations
Yuxuan Yao, Haonan Sheng, Qingsong Lv +11
The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. Howev…
LoViC: Efficient Long Video Generation with Context Compression
Jiaxiu Jiang, Wenbo Li, Jingjing Ren +5
Despite recent advances in diffusion transformers (DiTs) for text-to-video generation, scaling to long-duration content remains challenging due to the quadratic complexity of self-…
Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
Yuxuan Yao, Han Wu, Mingyang Liu +5
Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage thei…
Molly: Making Large Language Model Agents Solve Python Problem More Logically
Rui Xiao, Jiong Wang, Lu Han +2
Applying large language models (LLMs) as teaching assists has attracted much attention as an integral part of intelligent education, particularly in computing courses. To reduce th…
CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration
Jiahui Gao, Renjie Pi, Tianyang Han +5
The deployment of multimodal large language models (MLLMs) has demonstrated remarkable success in engaging in conversations involving visual inputs, thanks to the superior power of…