The Year in AI Papers
The year/Labs/DeepSeek

Research lab

DeepSeek

Open model research focused on reasoning, efficient architectures, coding, mathematics, and multimodal systems.

Papers
8
Citations
1.1K
Official code
5

8 papers from DeepSeek

01

Research paper

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

DSpark is a speculative decoding framework that combines a semi-autoregressive draft model with confidence-scheduled verification to accelerate LLM inference. The draft model uses a parallel backbone (based on DFlash) to generate tokens in one pass, followed by a lightweight sequential head (Markov or RNN) to model inter-token dependencies, mitigating…

Xin Cheng, Xingkai Yu, Chenze Shao, Jiashi Li, et al.
Published
Jul 2026
Citations
12
Code
6.9K stars
Read summary Original
02

arXiv.org

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

DualPath is an inference system that addresses the storage I/O bottleneck in multi-turn, agentic LLM inference under prefill-decode (PD) disaggregation. In such workloads, KV-Cache hit rates are high (≥95%), making KV-Cache loading from external storage the dominant performance factor. Existing systems load KV-Cache only into prefill engines, saturating…

Yongtong Wu, Shaoyuan Chen, Yinmin Zhong, Rilin Huang, et al.
Published
Feb 2026
Citations
10
Code
Not linked
Read summary Original
03

arXiv.org

DeepSeek-OCR 2: Visual Causal Flow

DeepSeek-OCR 2 introduces DeepEncoder V2, a novel vision encoder that replaces the CLIP component with a compact LLM (Qwen2-0.5B) to enable causal reordering of visual tokens, mimicking human visual scanning. The encoder uses a dual attention mask: bidirectional for visual tokens and causal for learnable query tokens, allowing queries to attend to all…

Haoran Wei, Yaofeng Sun, Yukun Li
Published
Jan 2026
Citations
53
Code
3.2K stars
Read summary Original
04

Annual Meeting of the Association for Computational Linguistics

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

The paper introduces Engram, a conditional memory module that augments Mixture-of-Experts (MoE) large language models with static N-gram lookup tables, providing a complementary sparsity axis to conditional computation. Engram uses hashed N-gram embeddings with tokenizer compression, multi-head hashing, and context-aware gating to retrieve static knowledge…

Xin Cheng, Rui Tian, Wangding Zeng, Damai Dai, et al.
Published
Jan 2026
Citations
63
Code
4.6K stars
Read summary Original
05

arXiv.org

mHC: Manifold-Constrained Hyper-Connections

The paper introduces Manifold-Constrained Hyper-Connections (mHC), a framework that addresses training instability and scalability issues in Hyper-Connections (HC) by projecting residual connection matrices onto the Birkhoff polytope (doubly stochastic matrices) using the Sinkhorn-Knopp algorithm. This restores the identity mapping property, ensuring norm…

Zhenda Xie, Yixuan Wei, Huanqi Cao, Chenggang Zhao, et al.
Published
Dec 2025
Citations
65
Code
Not linked
Read summary Original
06

arXiv.org

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

DeepSeek-V3.2 introduces three key innovations to close the gap with closed-source models: DeepSeek Sparse Attention (DSA) reduces computational complexity from O(L^2) to O(Lk) while preserving long-context performance; a scalable reinforcement learning (RL) framework with a post-training compute budget exceeding 10% of pre-training cost enables…

DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, et al.
Published
Dec 2025
Citations
671
Code
Not linked
Read summary Original
07

arXiv.org

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

DeepSeekMath-V2 is a large language model for natural-language theorem proving, built on DeepSeek-V3.2-Exp-Base, that achieves self-verifiable mathematical reasoning. The authors argue that final-answer rewards are insufficient because correct answers do not guarantee correct reasoning and are inapplicable to theorem proving. They train a verifier using…

Zhihong Shao, Yuxiang Luo, Chengda Lu, Z. Z. Ren, et al.
Published
Nov 2025
Citations
60
Code
1.6K stars
Read summary Original
08

arXiv.org

DeepSeek-OCR: Contexts Optical Compression

DeepSeek-OCR is a vision-language model that explores optical compression of long contexts by mapping text to images and decoding them back to text. It consists of DeepEncoder, a novel vision encoder with low activation and high compression, and a DeepSeek3B-MoE decoder. On the Fox benchmark, it achieves 97% OCR precision at compression ratios under 10x,…

Haoran Wei, Yaofeng Sun, Yukun Li
Published
Oct 2025
Citations
159
Code
24K stars
Read summary Original