https://github.com/pkunlp-icler/mic
공식 코드MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
Papers with Code 아카이브
Multimodal Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 3
- 보존된 평가 기록
- 13
Reasoning over multimodal inputs.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/quinn777/atomthink
공식 코드Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?
https://github.com/reml-group/fortisavqa
공식 코드FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning
https://github.com/rucaibox/comvint
공식 코드https://github.com/samuelyu2002/pacs
공식 코드PACS: A Dataset for Physical Audiovisual CommonSense Reasoning
https://github.com/sgi-2023/3d-building-classification
공식 코드https://github.com/shawnricecake/heima
공식 코드https://github.com/shunqim/ctrl-cic
공식 코드https://github.com/shuyansy/vidtext
공식 코드VidText: Towards Comprehensive Evaluation for Video Text Understanding
https://github.com/skrighyz/fgve
공식 코드https://github.com/sming256/bolt
공식 코드BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
https://github.com/stemdataset/STEM
공식 코드https://github.com/tencentarc/video-holmes
공식 코드Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
https://github.com/terry-xu-666/visual_inference_chain
공식 코드Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
https://github.com/tgxs002/wikiscenes
공식 코드Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision
https://github.com/the-martyr/causalmm
공식 코드https://github.com/thecharm/bdog
공식 코드A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning
https://github.com/theshi-1128/ABJ-Attack
공식 코드LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
https://github.com/thudm/glm-4.1v-thinking
공식 코드GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
https://github.com/thunlp-mt/vat
공식 코드https://github.com/thunlp/SICOG
공식 코드https://github.com/thunlp/deepperception
공식 코드https://github.com/tomohiro-sawada/cs7643-final-project
공식 코드https://github.com/tongjingqi/code2logic
공식 코드Code2Logic: Game-Code-Driven Data Synthesis for Enhancing VLMs General Reasoning
https://github.com/tttyuntian/vlm_primitive_concepts
공식 코드Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?
https://github.com/turningpoint-ai/visualthinker-r1-zero
공식 코드R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
https://github.com/umass-embodied-agi/mirage
공식 코드Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
https://github.com/univanxx/3mdbench
공식 코드https://github.com/vec-ai/wikihow-tiir
공식 코드https://github.com/virginie-do/e-SNLI-VE
공식 코드e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
https://github.com/visresearch/LLaVA-STF
공식 코드Learning Compact Vision Tokens for Efficient Large Multimodal Models
https://github.com/visual-agent/deepeyes
공식 코드DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
https://github.com/waltonfuture/rl-with-cold-start
공식 코드Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
https://github.com/wanghanbinpanda/codevision
공식 코드Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
https://github.com/weijingxuan/COCO-MMR
공식 코드Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework
https://github.com/wenchuan-zhang/patho-r1
공식 코드Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.