8 papers
CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation
Xintao Wang, Heng Wang, Yifei Zhang +9
Role-playing language agents (RPLAs) have emerged as promising applications of large language models (LLMs). However, simulating established characters presents a challenging task…
HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving
Qiang Li, Yingwenqi Jiang, Tuoxi Li +17
Realistic and controllable simulation is critical for advancing end-to-end autonomous driving, yet existing approaches often struggle to support novel view synthesis under large vi…
SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference
Wenxun Wang, Shuchang Zhou, Wenyu Sun +2
Transformers have shown remarkable performance in both natural language processing (NLP) and computer vision (CV) tasks. However, their real-time inference speed and efficiency are…
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
Ailin Huang, Bingxin Li, Bruce Wang +73
Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate na…
InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models
Shuchang Zhou, Jiwei Wei, Shiyuan He +5
Prompt tuning has become a popular strategy for adapting Vision-Language Models (VLMs) to zero/few-shot visual recognition tasks. Some prompting techniques introduce prior knowledg…
Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model
Haoyang Huang, Guoqing Ma, Nan Duan +51
We present Step-Video-TI2V, a state-of-the-art text-driven image-to-video generation model with 30B parameters, capable of generating videos up to 102 frames based on both text and…