activity
20242026
collaborators

6 papers

cs.AI2026

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

Xin Cheng, Xingkai Yu, Chenze Shao +30

Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose lo…

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

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning

Wenkai Yang, Shuming Ma, Yankai Lin +1

Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning task…

cs.CL2025

DeepCritic: Deliberate Critique with Large Language Models

Wenkai Yang, Jingwen Chen, Yankai Lin +1

As Large Language Models (LLMs) are rapidly evolving, providing accurate feedback and scalable oversight on their outputs becomes an urgent and critical problem. Leveraging LLMs as…

cs.CL2025

Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization

Wenkai Yang, Shiqi Shen, Guangyao Shen +5

Superalignment, where humans act as weak supervisors for superhuman models, has become a crucial problem with the rapid development of Large Language Models (LLMs). Recent work has…

cs.CL2024

Distilling Rule-based Knowledge into Large Language Models

Wenkai Yang, Yankai Lin, Jie Zhou +1

Large language models (LLMs) have shown incredible performance in completing various real-world tasks. The current paradigm of knowledge learning for LLMs is mainly based on learni…