Papers with Code 아카이브

model

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/IBM/SPAHM

공식 코드

Statistical Model Aggregation via Parameter Matching

https://github.com/IBM/helm-enterprise-benchmark

공식 코드

Enterprise Benchmarks for Large Language Model Evaluation

https://github.com/ICB-DCM/model_calibration_protocol_preprint

공식 코드

A protocol for dynamic model calibration

https://github.com/Idesan/HawkesGranger

공식 코드

Cardinality-Regularized Hawkes-Granger Model

https://github.com/IntelLabs/AVUC

공식 코드

Improving model calibration with accuracy versus uncertainty optimization

https://github.com/IntelLabs/causality-lab

공식 코드

A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment

https://github.com/IraKorshunova/bruno

공식 코드

BRUNO: A Deep Recurrent Model for Exchangeable Data

https://github.com/Ivanopolo/modnet

공식 코드

Unsupervised Community Detection with Modularity-Based Attention Model

https://github.com/JACKPURCELL/sok-llm-watermark

공식 코드

Watermark under Fire: A Robustness Evaluation of LLM Watermarking

https://github.com/JH-GEECS/CART_public

공식 코드

Revisiting Weight Averaging for Model Merging

https://github.com/JannerM/mbpo

공식 코드

When to Trust Your Model: Model-Based Policy Optimization

https://github.com/JasonGross/guarantees-based-mechanistic-interpretability

공식 코드

Compact Proofs of Model Performance via Mechanistic Interpretability

https://github.com/Jie0618/PhysicsRegression

공식 코드

A Neural Symbolic Model for Space Physics

https://github.com/JimTheBarbarian/Official-TTV-Segmentation

공식 코드

An Image Segmentation Model with Transformed Total Variation

https://github.com/Jinjiarui/DRSR

공식 코드

A Deep Recurrent Survival Model for Unbiased Ranking

https://github.com/Jinxu-Lin/BSCE-GRA

공식 코드

Uncertainty Weighted Gradients for Model Calibration

https://github.com/Joe-Hall-Lee/Debias

공식 코드

Mitigating the Bias of Large Language Model Evaluation

https://github.com/John-JoB/DIMMPF

공식 코드

Differentiable Interacting Multiple Model Particle Filtering

https://github.com/JosephKJ/MASON

공식 코드

MASON: A Model AgnoStic ObjectNess Framework

https://github.com/JulySinceAndrew/FedNewsRec-EMNLP-Findings-2020

공식 코드

Privacy-Preserving News Recommendation Model Learning

https://github.com/KRR-Oxford/DeepOnto

공식 코드

Language Model Analysis for Ontology Subsumption Inference

https://github.com/KU-CVLAB/DiffMatch

공식 코드

Diffusion Model for Dense Matching

https://github.com/KaijuML/data-to-text-hierarchical

공식 코드

A Hierarchical Model for Data-to-Text Generation

https://github.com/KatherLab/COBRA

공식 코드

Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

https://github.com/KhrulkovV/tt-pytorch

공식 코드

Tensorized Embedding Layers for Efficient Model Compression

https://github.com/LAMDA-RL/CoLA

공식 코드

Controlling Large Language Model with Latent Actions

https://github.com/LG-AI-EXAONE/EXAONEPath

공식 코드

EXAONEPath 1.0 Patch-level Foundation Model for Pathology

https://github.com/LHKode/NameyYourFood

공식 코드

Detecting Korean Food Using Image using Hierarchical Model

https://github.com/LINs-lab/M3

공식 코드

Towards Robust Multi-Modal Reasoning via Model Selection

https://github.com/LKJacky/Differentiable-Model-Scaling

공식 코드

Differentiable Model Scaling using Differentiable Topk

https://github.com/LLMSELECTOR/LLMSELECTOR

공식 코드

Optimizing Model Selection for Compound AI Systems

https://github.com/LMA-NeurIPS19/LMA

공식 코드

Light Multi-segment Activation for Model Compression

https://github.com/Lightning-AI/lit-gpt

공식 코드

TinyLlama: An Open-Source Small Language Model

https://github.com/LinZichuan/AdMRL

공식 코드

Model-based Adversarial Meta-Reinforcement Learning

https://github.com/LoreDema/GePpeTto

공식 코드

GePpeTto Carves Italian into a Language Model

https://github.com/Lyz1213/BadEdit

공식 코드

BadEdit: Backdooring large language models by model editing

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.