1.4k citations · 1.7k across the 34 of their papers we have counts for
35 papers
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
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…
A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
Kairong Luo, Haodong Wen, Shengding Hu +5
Training large models is both resource-intensive and time-consuming, making it crucial to understand the quantitative relationship between model performance and hyperparameters. In…
EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents
Zhili Cheng, Yuge Tu, Ran Li +9
Multimodal Large Language Models (MLLMs) have shown significant advancements, providing a promising future for embodied agents. Existing benchmarks for evaluating MLLMs primarily u…
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
Jinyi Hu, Shengding Hu, Yuxuan Song +6
Autoregressive and diffusion models have achieved remarkable progress in language models and visual generation, respectively. We present ACDiT, a novel Autoregressive blockwise Con…
DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models
Ranchi Zhao, Zhen Leng Thai, Yifan Zhang +6
The performance of Large Language Models (LLMs) is substantially influenced by the pretraining corpus, which consists of vast quantities of unsupervised data processed by the model…
Stuffed Mamba: Oversized States Lead to the Inability to Forget
Yingfa Chen, Xinrong Zhang, Shengding Hu +3
Recent advancements in recurrent architectures, such as Mamba and RWKV, have showcased strong language capabilities. Unlike transformer-based models, these architectures encode all…
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
Yuan Yao, Tianyu Yu, Ao Zhang +20
The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the nex…
States Hidden in Hidden States: Implicit Discrete State Representations Emerge in LLMs' Hidden States
Junhao Chen, Shengding Hu, Zhiyuan Liu +1
Large Language Models (LLMs) exhibit emergent abilities that may reveal aspects of their internal mechanisms. We study one such capability: directly performing extended sequences o…
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
Xinrong Zhang, Yingfa Chen, Shengding Hu +6
As large language models (LLMs) increasingly permeate daily lives, there is a growing demand for real-time interactions that mirror human conversations. Traditional turn-based chat…
LEGENT: Open Platform for Embodied Agents
Zhili Cheng, Zhitong Wang, Jinyi Hu +7
Despite advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), their integration into language-grounded, human-like embodied agents remains incomplete, hi…
UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs
Chaoqun He, Renjie Luo, Shengding Hu +7
Evaluation is pivotal for refining Large Language Models (LLMs), pinpointing their capabilities, and guiding enhancements. The rapid development of LLMs calls for a lightweight and…
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Shengding Hu, Yuge Tu, Xu Han +22
The burgeoning interest in developing Large Language Models (LLMs) with up to trillion parameters has been met with concerns regarding resource efficiency and practical expense, pa…
Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition
Yufei Huang, Shengding Hu, Xu Han +2
Recent studies have uncovered intriguing phenomena in deep learning, such as grokking, double descent, and emergent abilities in large language models, which challenge human intuit…
Bench: Extending Long Context Evaluation Beyond 100K Tokens
Xinrong Zhang, Yingfa Chen, Shengding Hu +8
Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. Despi…
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
Chaoqun He, Renjie Luo, Yuzhuo Bai +11
Recent advancements have seen Large Language Models (LLMs) and Large Multimodal Models (LMMs) surpassing general human capabilities in various tasks, approaching the proficiency le…
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models
Chenyang Song, Xu Han, Zhengyan Zhang +8
Activation sparsity refers to the existence of considerable weakly-contributed elements among activation outputs. As a prevalent property of the models using the ReLU activation fu…
Predicting Emergent Abilities with Infinite Resolution Evaluation
Shengding Hu, Xin Liu, Xu Han +9
The scientific scale-up of large language models (LLMs) necessitates a comprehensive understanding of their scaling properties. However, the existing literature on the scaling prop…
OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models
Shengding Hu, Ning Ding, Weilin Zhao +4
The scale of large pre-trained models (PTMs) poses significant challenges in adapting to downstream tasks due to the high optimization overhead and storage costs associated with fu…
Won't Get Fooled Again: Answering Questions with False Premises
Shengding Hu, Yifan Luo, Huadong Wang +3
Pre-trained language models (PLMs) have shown unprecedented potential in various fields, especially as the backbones for question-answering (QA) systems. However, they tend to be e…
Exploring the Impact of Model Scaling on Parameter-Efficient Tuning
Yusheng Su, Chi-Min Chan, Jiali Cheng +9
Parameter-efficient tuning (PET) methods can effectively drive extremely large pre-trained language models (PLMs) by training only minimal parameters. Different PET methods utilize…
Exploring Lottery Prompts for Pre-trained Language Models
Yulin Chen, Ning Ding, Xiaobin Wang +4
Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Give…
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
Ning Ding, Yulin Chen, Bokai Xu +6
Fine-tuning on instruction data has been widely validated as an effective practice for implementing chat language models like ChatGPT. Scaling the diversity and quality of such dat…
Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder
Zihao Fu, Wai Lam, Qian Yu +4
The sequence-to-sequence (seq2seq) task aims at generating the target sequence based on the given input source sequence. Traditionally, most of the seq2seq task is resolved by the…