Papers with Code 아카이브

Multimodal Reasoning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

3

보존된 평가 기록

13

코드

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

https://github.com/hanhpt23/silvar

SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization

https://github.com/huofushuo/SID

Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding

https://github.com/iammrhelo/pytorch-vqa-dan

Dual Attention Networks for Multimodal Reasoning and Matching

https://github.com/infly-ai/inf-mllm

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

https://github.com/jzhang38/EasyContext

Long Context Transfer from Language to Vision

https://github.com/lastmile-ai/aiconfig

A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise

https://github.com/luomancs/remuq

WebQA: Multihop and Multimodal QA

https://github.com/mammoth-vl/mammoth-vl

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

https://github.com/mathllm/math-v

Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset

https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation

Semi-supervised Domain Adaptation via Minimax Entropy

https://github.com/necla-ml/SNLI-VE

e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations

https://github.com/neverbiasu/ComfyUI-BAGEL

Emerging Properties in Unified Multimodal Pretraining

https://github.com/nvlabs/eagle

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

https://github.com/open-compass/vlmevalkit

MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs

https://github.com/opendrivelab/drivelm

Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models

https://github.com/opengvlab/internvideo2

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

https://github.com/opengvlab/internvl

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

https://github.com/opengvlab/videochat-flash

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

https://github.com/orionbench/orionbench

ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation

https://github.com/princeton-nlp/CharXiv

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

https://github.com/renshuhuai-andy/timechat

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

https://github.com/rowanz/merlot

MERLOT: Multimodal Neural Script Knowledge Models

https://github.com/seephys/seephys-project

Skywork-R1V3 Technical Report

https://github.com/shubham-gupta-iitr/mmmlX

WebQA: Multihop and Multimodal QA

https://github.com/spcl/knowledge-graph-of-thoughts

Affordable AI Assistants with Knowledge Graph of Thoughts

https://github.com/tidedra/lmm-r1

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

https://github.com/tiger-ai-lab/vl-rethinker

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

https://github.com/userb2020/s3d

Semi-supervised Domain Adaptation via Minimax Entropy

https://github.com/xlang-ai/aguvis

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

https://github.com/xzf-thu/audio-reasoner

Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models

https://github.com/yfzhang114/r1_reward

MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs

https://github.com/zhaoolee/garss

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

https://github.com/zjunlp/MKGformer

Multimodal Analogical Reasoning over Knowledge Graphs

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