6 papers
Song Aesthetics Evaluation with Multi-Stem Attention and Hierarchical Uncertainty Modeling
Yishan Lv, Jing Luo, Boyuan Ju +4
Music generative artificial intelligence (AI) is rapidly expanding music content, necessitating automated song aesthetics evaluation. However, existing studies largely focus on spe…
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang +195
General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-tho…
Reconstruction as a Bridge for Event-Based Visual Question Answering
Hanyue Lou, Jiayi Zhou, Yang Zhang +4
Integrating event cameras with Multimodal Large Language Models (MLLMs) promises general scene understanding in challenging visual conditions, yet requires navigating a trade-off b…
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Ailin Huang, Boyong Wu, Bruce Wang +142
Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such…
DeepSeek-V3 Technical Report
DeepSeek-AI, Aixin Liu, Bei Feng +195
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effec…