papers

Publications (13)

cs.CL2026

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…

cs.CL2025

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…

cs.DC2025

P/D-Device: Disaggregated Large Language Model between Cloud and Devices

Yibo Jin, Yixu Xu, Yue Chen +27

Serving disaggregated large language models has been widely adopted in industrial practice for enhanced performance. However, too many tokens generated in decoding phase, i.e., occ…

cs.CV2026

Seeing Isn't Orienting: A Cognitively Informed Hierarchical Benchmark for Object Orientation in MLLMs

Nazia Tasnim, Keanu Nichols, Yuting Yan +4

Humans develop object orientation understanding progressively, from recognizing which way an object faces to reasoning about orientations across multiple objects. Yet existing visi…

cs.CV2024

Deep Learning for Video Anomaly Detection: A Review

Peng Wu, Chengyu Pan, Yuting Yan +3

Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. As a long-standing task in the field of computer vision, VAD has witnesse…

cs.AI2026

Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model

Minghao Wu, Yuting Yan, Zhenyang Cai +9

Sepsis management in the ICU requires sequential treatment decisions under rapidly evolving patient physiology. Although large language models (LLMs) encode broad clinical knowledg…

cs.CL2024

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

DeepSeek-AI, Aixin Liu, Bei Feng +154

We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which…

cond-mat.mes-hall2023

Self-powered programmable van der Waals photodetectors with nonvolatile semi-floating gate

Fan Liu, Xi Lin, Yuting Yan +3

Tunable photovoltaic photodetectors are of significant relevance in the fields of programmable and neuromorphic optoelectronics. However, their widespread adoption is hindered by i…

cs.DC2026

RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference

Jiarui Wang, Huichao Chai, Yuanhang Zhang +38

Real-time recommender systems execute multi-stage cascades (retrieval, pre-processing, fine-grained ranking) under strict tail-latency SLOs, leaving only tens of milliseconds for r…

cond-mat.mes-hall2023

Approaching the robust linearity in dual-floating van der Waals photodiode

Jinpeng Xu, Xiaoguang Luo, Xi Lin +9

Two-dimensional (2D) material photodetectors have gained great attention as potential elements for optoelectronic applications. However, the linearity of the photoresponse is often…

cs.CV2026

Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets

Peng Wu, Yuting Yan, Guansong Pang +4

Event-based vision, characterized by low redundancy, focus on dynamic motion, and inherent privacy-preserving properties, naturally fits the demands of video anomaly detection (VAD…

cs.CL2026

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

DeepSeek-AI, Anyi Xu, Bangcai Lin +315

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…

cs.CL2025

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…