Papers with Code 아카이브
Visual Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 12
- 보존된 평가 기록
- 192
Ability to understand actions and reasoning associated with any visual images
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/slotabstractor/slotabstractor
공식 코드https://github.com/sohojoe/clip_visual-spatial-reasoning
공식 코드https://github.com/souradipp76/mm-poe
공식 코드MM-PoE: Multiple Choice Reasoning via. Process of Elimination using Multi-Modal Models
https://github.com/sreyan88/vdgd
공식 코드Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
https://github.com/stanfordnlp/mac-network
공식 코드https://github.com/stanfordnlp/phrasenode
공식 코드https://github.com/steven-ccq/visualreasoner
공식 코드From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis
https://github.com/sycny/selfsynthx
공식 코드Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
https://github.com/szzexpoi/poem
공식 코드Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning
https://github.com/szzexpoi/rex
공식 코드https://github.com/tanjatang/CAN
공식 코드Interpretable Visual Understanding with Cognitive Attention Network
https://github.com/tanjatang/DMVCR
공식 코드Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory
https://github.com/teleema/sade
공식 코드An Examination of the Compositionality of Large Generative Vision-Language Models
https://github.com/tgc1997/RMN
공식 코드Learning to Discretely Compose Reasoning Module Networks for Video Captioning
https://github.com/theshi-1128/ABJ-Attack
공식 코드LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
https://github.com/thorin215/gre
공식 코드https://github.com/thudm/cogcom
공식 코드CogCoM: Train Large Vision-Language Models Diving into Details through Chain of Manipulations
https://github.com/thunlp-mt/vat
공식 코드https://github.com/thunlp/pevl
공식 코드PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
https://github.com/tianhewu/visualquality-r1
공식 코드VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
https://github.com/tianyi-lab/colorbench
공식 코드https://github.com/togethercomputer/dragonfly
공식 코드Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models
https://github.com/tomer-barak/learning-independent_abstract_reasoning
공식 코드Untrained neural networks can demonstrate memorization-independent abstract reasoning
https://github.com/tonychenxyz/vit-interpret
공식 코드Interpreting and Controlling Vision Foundation Models via Text Explanations
https://github.com/tossowski/keycomp
공식 코드Prompting Large Vision-Language Models for Compositional Reasoning
https://github.com/tsinghua-fib-lab/CityEQA
공식 코드CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space
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/tzjtatata/myriad
공식 코드Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection
https://github.com/ubc-nlp/peacock
공식 코드Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks
https://github.com/ubc-vision/RefTR
공식 코드Referring Transformer: A One-step Approach to Multi-task Visual Grounding
https://github.com/ucsc-vlaa/vllm-safety-benchmark
공식 코드How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
https://github.com/udiNaveh/nlvr_tau_nlp_final_proj
공식 코드https://github.com/umass-embodied-agi/mirage
공식 코드Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
https://github.com/umich-vl/think_visually
공식 코드https://github.com/unira-zwj/PhysVLM
공식 코드PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.