English
Related papers

Related papers: Megrez2 Technical Report

200 papers

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model…

Applying a pre-trained large model to downstream tasks is prohibitive under resource-constrained conditions. Recent dominant approaches for addressing efficiency issues involve adding a few learnable parameters to the fixed backbone model.…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Yangyang Guo , Guangzhi Wang , Mohan Kankanhalli

We introduce the latest series of TeleChat models: \textbf{TeleChat2}, \textbf{TeleChat2.5}, and \textbf{T1}, offering a significant upgrade over their predecessor, TeleChat. Despite minimal changes to the model architecture, the new series…

Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning of world knowledge and reasoning, it does not explicitly optimize for linguistic competence.…

Computation and Language · Computer Science 2026-04-17 Atsuki Yamaguchi , Maggie Mi , Nikolaos Aletras

Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…

Computation and Language · Computer Science 2025-06-27 Xiaoshuang Ji , Zhendong Zhao , Xiaojun Chen , Xin Zhao , Zeyao Liu

Fine-tuning pre-trained language models for multiple tasks tends to be expensive in terms of storage. To mitigate this, parameter-efficient transfer learning (PETL) methods have been proposed to address this issue, but they still require a…

Computation and Language · Computer Science 2023-06-13 Guangtao Zeng , Peiyuan Zhang , Wei Lu

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

Computation and Language · Computer Science 2024-05-31 Zhuoyuan Mao , Chenhui Chu , Sadao Kurohashi

Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks. However, their excessive amount of parameters hinders them from efficient deployment on edge devices. Binarization of the BERT models can…

Computation and Language · Computer Science 2023-05-10 Jiayi Tian , Chao Fang , Haonan Wang , Zhongfeng Wang

We introduce a new balanced assignment of experts (BASE) layer for large language models that greatly simplifies existing high capacity sparse layers. Sparse layers can dramatically improve the efficiency of training and inference by…

Computation and Language · Computer Science 2021-04-01 Mike Lewis , Shruti Bhosale , Tim Dettmers , Naman Goyal , Luke Zettlemoyer

Federated learning (FL) has emerged as a promising paradigm for enabling the collaborative training of models without centralized access to the raw data on local devices. In the typical FL paradigm (e.g., FedAvg), model weights are sent to…

Machine Learning · Computer Science 2024-12-25 Guangyu Sun , Umar Khalid , Matias Mendieta , Pu Wang , Chen Chen

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…

Computation and Language · Computer Science 2025-07-03 Shuangquan Lyu , Yingnan Deng , Guiran Liu , Zhen Qi , Ruotong Wang

Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Zunnan Xu , Zhihong Chen , Yong Zhang , Yibing Song , Xiang Wan , Guanbin Li

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Machine Learning · Computer Science 2025-02-12 Kunfeng Lai , Zhenheng Tang , Xinglin Pan , Peijie Dong , Xiang Liu , Haolan Chen , Li Shen , Bo Li , Xiaowen Chu

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

In large-scale ranking systems, cascading architectures have been widely adopted to achieve a balance between efficiency and effectiveness. The pre-ranking module plays a vital role in selecting a subset of candidates for the subsequent…

Information Retrieval · Computer Science 2024-07-18 YaChen Yan , Liubo Li

Large deep learning models offer significant accuracy gains, but training billions to trillions of parameters is challenging. Existing solutions such as data and model parallelisms exhibit fundamental limitations to fit these models into…

Machine Learning · Computer Science 2020-05-14 Samyam Rajbhandari , Jeff Rasley , Olatunji Ruwase , Yuxiong He

State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not enable sharing…

Computation and Language · Computer Science 2021-06-09 Rabeeh Karimi Mahabadi , Sebastian Ruder , Mostafa Dehghani , James Henderson

In the era of large language models, model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. However, two challenges remain: (a) interference between different models…

Computation and Language · Computer Science 2024-10-15 Zhenyi Lu , Chenghao Fan , Wei Wei , Xiaoye Qu , Dangyang Chen , Yu Cheng

Mixture-of-Experts (MoE) architectures have become standard in large language models, yet many of their core design choices - expert count, granularity, shared experts, load balancing, token dropping - have only been studied one or two at a…

Machine Learning · Computer Science 2026-05-13 Margaret Li , Sneha Kudugunta , Danielle Rothermel , Luke Zettlemoyer