Papers with Code 아카이브

Open-Ended Question Answering

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Open-ended questions are defined as those that simply pose the question, without imposing any constraints on the format of the response. This distinguishes them from questions with a predetermined answer format.

코드

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

https://github.com/lee-group-cmu/lf2i

공식 코드

Likelihood-Free Frequentist Inference: Bridging Classical Statistics and Machine Learning for Reliable Simulator-Based Inference

https://github.com/libeineu/SDT-Training

공식 코드

Shallow-to-Deep Training for Neural Machine Translation

https://github.com/lily-x/artificial-replay

공식 코드

Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits

https://github.com/liujch1998/gkp

공식 코드

Generated Knowledge Prompting for Commonsense Reasoning

https://github.com/liuxiangyuan/mba

공식 코드

Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment

https://github.com/lizhaoliu-lec/ccse

공식 코드

Instance Segmentation for Chinese Character Stroke Extraction, Datasets and Benchmarks

https://github.com/lucasmansilla/ACRN_Chest_X-ray_IA

공식 코드

Learning Deformable Registration of Medical Images with Anatomical Constraints

https://github.com/lucasmansilla/NIH_chest_xray14_segmentations

공식 코드

Learning Deformable Registration of Medical Images with Anatomical Constraints

https://github.com/lynshao/semanticpapr

공식 코드

Semantic Communications with Discrete-time Analog Transmission: A PAPR Perspective

https://github.com/lywang3081/coscl

공식 코드

CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One

https://github.com/marthaflinderslewis/clip-binding

공식 코드

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

https://github.com/masih4/Skin-lesion-segmentation-effects-of-the-classification-perfromnce

공식 코드

The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classification

https://github.com/mattiaspaul/TernaryNet

공식 코드

TernaryNet: Faster Deep Model Inference without GPUs for Medical 3D Segmentation using Sparse and Binary Convolutions

https://github.com/mayer123/udt-qa

공식 코드

Open Domain Question Answering with A Unified Knowledge Interface

https://github.com/mbzuai-oryx/bimedix

공식 코드

BiMediX: Bilingual Medical Mixture of Experts LLM

https://github.com/mcubelab/pdproc

공식 코드

Combining Learned and Analytical Models for Predicting Action Effects from Sensory Data

https://github.com/mdelhoneux/avc_analyser

공식 코드

What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions?

https://github.com/microsoft/DeepSpeed

공식 코드

Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam

https://github.com/microsoft/lmops

공식 코드

Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers

https://github.com/mikemccabe210/mapper_comparison

공식 코드

Mapper Comparison with Wasserstein Metrics

https://github.com/mingdachen/syntactic-template-generation

공식 코드

Leveraging Natural Supervision for Language Representation Learning and Generation

https://github.com/mingxilii/localegn

공식 코드

Few-Sample Traffic Prediction with Graph Networks using Locale as Relational Inductive Biases

https://github.com/mmadmax/culfit

공식 코드

CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis

https://github.com/mrfanuel/learningcontinuousdpps.jl

공식 코드

Nonparametric estimation of continuous DPPs with kernel methods

https://github.com/ndnlp/parity

공식 코드

Overcoming a Theoretical Limitation of Self-Attention

https://github.com/neuralaudio/hear-eval-kit

공식 코드

HEAR: Holistic Evaluation of Audio Representations

https://github.com/neuroailab/lr-identify

공식 코드

Identifying Learning Rules From Neural Network Observables

https://github.com/nicofirst1/speaker-adaptation

공식 코드

Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind

https://github.com/nightingal3/fig-qa

공식 코드

Testing the Ability of Language Models to Interpret Figurative Language

https://github.com/nightingal3/lm-compositionality

공식 코드

Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models

https://github.com/noamrazin/imp_reg_dl_not_norms

공식 코드

Implicit Regularization in Deep Learning May Not Be Explainable by Norms

https://github.com/open-mmlab/mmdetection

공식 코드

Hybrid Task Cascade for Instance Segmentation

https://github.com/opendatalab/craft

공식 코드

Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning

https://github.com/paper-submission-rafa/diversification-code

공식 코드

Result Diversification by Multi-objective Evolutionary Algorithms with Theoretical Guarantees

https://github.com/paul-rottger/multiq

공식 코드

Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ

https://github.com/prajjwal1/rl_paradigm

공식 코드

When should we prefer Decision Transformers for Offline Reinforcement Learning?

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