paper-with-me

Papers CoLA

“CoLA” 태그가 달린 논문 78편 · 필터 해제

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

2025-07-10 · Ziyue Li, Yang Li, Tianyi Zhou

Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretra…

CoLALarge Language ModelMath

LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing

2025-06-17 · Wenbing Li, Zikai Song, Hang Zhou, Yunyao Zhang 외

Recent efforts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for adapting large language models (LLMs) to multiple tasks still exhibit prevailing limitations: they either swap entire attention/feed-…

ARCCoLAGSM8KHumanEval+4

CoLA: Collaborative Low-Rank Adaptation

2025-05-21 · Yiyun Zhou, Chang Yao, Jingyuan Chen

The scaling law of Large Language Models (LLMs) reveals a power-law relationship, showing diminishing return on performance as model scale increases. While training LLMs from scratch is resource-intensive, fine-tuning a …

CoLAMixture-of-Expertsparameter-efficient fine-tuning

Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study

2025-04-03 · Aryan Agrawal, Lisa Alazraki, Shahin Honarvar, Marek Rei

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on…

CoLADenoisingQNLISST-2

CoLa -- Learning to Interactively Collaborate with Large LMs

2025-04-03 · Abhishek Sharma, Dan Goldwasser

LLMs' remarkable ability to tackle a wide range of language tasks opened new opportunities for collaborative human-AI problem solving. LLMs can amplify human capabilities by applying their intuitions and reasoning strate…

CoLAText Generation

Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks

2025-04-01 · Naimul Haque

Large Language Models (LLMs) have significantly advanced Natural Language Processing (NLP), particularly in Natural Language Understanding (NLU) tasks. As we progress toward an agentic world where LLM-based agents autono…

CoLAContinual LearningMRPCNatural Language Understanding+2

Controlling Large Language Model with Latent Actions

2025-03-27 · Chengxing Jia, Ziniu Li, Pengyuan Wang, Yi-Chen Li 외

Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, partic…

CoLALanguage ModelingLanguage ModellingLarge Language Model+3

CoCo-CoLa: Evaluating and Improving Language Adherence in Multilingual LLMs

2025-02-18 · Elnaz Rahmati, Alireza S. Ziabari, Morteza Dehghani

Multilingual Large Language Models (LLMs) develop cross-lingual abilities despite being trained on limited parallel data. However, they often struggle to generate responses in the intended language, favoring high-resourc…

CoLA

CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation

2025-02-16 · Ziyue Liu, Ruijie Zhang, Zhengyang Wang, Zi Yang 외

The full-size MLPs and the projection layers in attention introduce tremendous model sizes of large language models (LLMs), imposing extremely demanding needs of computational resources in the pre-training stage. However…

CoLA

Optimizing Language Models for Grammatical Acceptability: A Comparative Study of Fine-Tuning Techniques

2025-01-14 · Shobhit Ratan, Farley Knight, Ghada Jerfel, Sze Chung Ho

This study explores the fine-tuning (FT) of the Open Pre-trained Transformer (OPT-125M) for grammatical acceptability tasks using the CoLA dataset. By comparing Vanilla-Fine-Tuning (VFT), Pattern-Based-Fine-Tuning (PBFT)…

CoLAComputational Efficiencyparameter-efficient fine-tuning

Predicting Emergent Capabilities by Finetuning

2024-11-25 · Charlie Snell, Eric Wallace, Dan Klein, Sergey Levine

A fundamental open challenge in modern LLM scaling is the lack of understanding around emergent capabilities. In particular, language model pretraining loss is known to be highly predictable as a function of compute. How…

CoLAGSM8KMMLU

DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models

2024-10-12 · Wenlong Deng, Yize Zhao, Vala Vakilian, Minghui Chen 외

Storing open-source fine-tuned models separately introduces redundancy and increases response times in applications utilizing multiple models. Delta-parameter pruning (DPP), particularly the random drop and rescale (DARE…

CoLAparameter-efficient fine-tuning

TReX- Reusing Vision Transformer's Attention for Efficient Xbar-based Computing

2024-08-22 · Abhishek Moitra, Abhiroop Bhattacharjee, Youngeun Kim, Priyadarshini Panda

Due to the high computation overhead of Vision Transformers (ViTs), In-memory Computing architectures are being researched towards energy-efficient deployment in edge-computing scenarios. Prior works have proposed effici…

CoLAEdge-computing

Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective

2024-07-22 · Jie Gui, Chengze Jiang, Minjing Dong, Kun Tong 외

While adversarial training is an effective defense method against adversarial attacks, it notably increases the training cost. To this end, fast adversarial training (FAT) is presented for efficient training and has beco…

CoLA

Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinators

2024-07-20 · Harsh Lunia

Recent advancements have introduced multiple vision-language models (VLMs) demonstrating impressive commonsense reasoning across various domains. Despite their individual capabilities, the potential of synergizing these …

Action RecognitionCoLALanguage ModelingLanguage Modelling+2

Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach

2024-07-15 · Hojjat Mokhtarabadi, Ziba Zamani, Abbas Maazallahi, Mohammad Hossein Manshaei

Instruction-tuned large language models have demonstrated remarkable capabilities in following human instructions across various domains. However, their proficiency remains notably deficient in many low-resource language…

CoLAInstruction Following

ADMM Based Semi-Structured Pattern Pruning Framework For Transformer

2024-07-11 · Tianchen Wang

NLP(natural language processsing) has achieved great success through the transformer model.However, the model has hundreds of millions or billions parameters,which is huge burden for its deployment on personal computer o…

CoLAQuantizationRTE

CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection

2024-07-09 · Shuang Hao, Chunlin Zhong, He Tang

The depth/thermal information is beneficial for detecting salient object with conventional RGB images. However, in dual-modal salient object detection (SOD) model, the robustness against noisy inputs and modality missing…

CoLALanguage ModelingLanguage Modellingobject-detection+5

CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations

2024-06-03 · Franz Motzkus, Christian Hellert, Ute Schmid

Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positio…

CoLAcounterfactualimage-classificationImage Classification

An Information Theoretic Evaluation Metric For Strong Unlearning

2024-05-28 · Dongjae Jeon, Wonje Jeung, Taeheon Kim, Albert No 외

Machine unlearning (MU) aims to remove the influence of specific data from trained models, addressing privacy concerns and ensuring compliance with regulations such as the "right to be forgotten." Evaluating strong unlea…

CoLAMachine Unlearningvalid
1–20 / 78 다음 →