Interpretability for Multimodal Models

💡 This post is initially focused on interpretability for multimodal models, while later a lot of papers in other fields are included, just for convenience. Resource Interpretability for MLLMs survey A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models Sparks of Explainability Recent Advancements in Explaining Large Vision Models Awesome LMMs Mechanistic Interpretability probing Probing Multimodal Large Language Models for Global and Local Semantic Representations representation Zoom in: An introduction to circuits Multimodal Neurons in Artificial Neural Networks Interpreting CLIP’s Image Representation via Text-Based Decomposition Interpreting the Second-Order Effects of Neurons in CLIP CLIP不同层 Multimodal Neurons in Pretrained Text-Only Transformers circuit **(causal tracing) Understanding Information Storage and Transfer in Multi-modal Large Language Models Automatic Discovery of Visual Circuits Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP SAE Case study: Interpreting, manipulating, and controlling clip with sparse autoencoders Towards multimodal interpretability: Learning sparse interpretable features in vision transformers Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery visualization Visualizer！简化你的Vision Transformer可视化！ (DVT) Denoising Vision Transformers Token Activation Map to Visually Explain Multimodal LLMs LVLM-Intrepret: An Interpretability Tool for Large Vision Language Models Transformer Interpretability Beyond Attention Visualization others **Towards interpreting visual information processing in vision-language models demo (dogit lens) Laying the Foundations for Vision and Multimodal Mechanistic Interpretability & Open Problems Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space information flow **Cross-modal Information Flow in Multimodal Large Language Models *From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks *What’s in the Image? A Deep-Dive into the Vision of Vision Language Models The Narrow Gate: Localized Image-Text Communication in Vision-Language Models Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference analyses on MLLMs Words or Vision: Do Vision-Language Models Have Blind Faith in Text? Forgotten Polygons: Multimodal Large Language Models are Shape-Blind Vision Transformers Need Registers On the rankability of visual embeddings Other fields of MLLMs visual pretraining Scaling Language-Free Visual Representation Learning spatial good Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas (ViT+LLM > ViT) Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder ! Learning Visual Composition through Improved Semantic Guidance (prompt-based) Things not Written in Text: Exploring Spatial Commonsense from Visual Signals (prompt-based) Does CLIP Bind Concepts? Probing Compositionality in Large Image Models Probing the Role of Positional Information in Vision-Language Models evaluation Can Multimodal Large Language Models Understand Spatial Relations? SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation REC (看 related work) Exploring Spatial Language Grounding Through Referring Expressions (文本引导) ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension attention Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs Lost in the middle: How language models use long contexts Efficient streaming language models with attention sinks (delimiters) Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection MagicPIG: LSH Sampling for Efficient LLM Generation Label words are anchors: An information flow perspective for understanding in-context learning ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features POS “闭门造车”之多模态思路浅谈（三）：位置编码 社区供稿 | 图解RoPE旋转位置编码及其特性 Base of RoPE Bounds Context Length Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding NoPE Transformer Language Models without Positional Encodings Still Learn Positional Information Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings The Impact of Positional Encoding on Length Generalization in Transformers (NoPE limits) Length Generalization of Causal Transformers without Position Encoding Long context Extending Context Window of Large Language Models via Positional Interpolation YaRN: Efficient Context Window Extension of Large Language Models hallucination survey Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models Hallucination of Multimodal Large Language Models: A Survey *Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs Interpreting and editing vision-language representations to mitigate hallucinations Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference Debiasing Multimodal Large Language Models token compression survey When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios methods (CDPruner) Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs *AdaFV: Rethinking of Visual-Language alignment for VLM acceleration (FasterVLM) [CLS] Attention is All You Need for Training-FreeVisual Token Pruning: Make VLM Inference Faster Sparsevlm: Visual token sparsification for efficient vision-language Model Inference (FastV) An image is worth 1/2 tokens after layer 2: Plug-and-PLay Acceleration for VLLM Inference LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token *Inference Optimal VLMs Need Only One Visual Token but Larger Models TokenPacker: Efficient Visual Projector for Multimodal LLM Matryoshka Multimodal Models Matryoshka Query Transformer for Large Vision-Language Models FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding active perception Please refer to this post. Dataset general VQA: Visual Question Answering repo download [(VQA v2.0) Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering] (GQA) GQA:ANewDataset for Real-World Visual Reasoning and Compositional Question Answering [website]https://cs.stanford.edu/people/dorarad/gqa/index.html (TextVQA) Towards VQA Models That Can Read website repo MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models repo MMBench: Is Your Multi-modal Model an All-around Player? spatial (ARO) When and why vision-language models behave like bags-of-words, and what to do about it? (Whatsup) What’s “up” with vision-language models? Investigating their struggle with spatial reasoning [repo]https://github.com/amitakamath/whatsup_vlms (VSR) Visual Spatial Reasoning [repo]https://github.com/cambridgeltl/visual-spatial-reasoning SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data (COMFORT) Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities hallucination (POPE) Evaluating object hallucination in large vision-language models repo (CHAIR) Object hallucination in image captioning repo (OpenCHAIR) Mitigating Open-Vocabulary Caption Hallucinations website Models llm gpt-oss Introducing gpt-oss | OpenAI OpenAI开源模型gpt-oss-120b的妙妙小观察 关于gpt-oss那些值得关注的点 vlm basic (Transformer) Attention is all you need (VIT) An Image is Worth 16x16 Words: Transformers for Image Recognition fat Scale (CLIP) Learning Transferable Visual Models From Natural Language Supervision (SigLIP) Sigmoid Loss for Language Image Pre-Training (PACL) Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning (BLIP-2) BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution Qwen2.5-VL Technical Report 万字长文图解Qwen2.5-VL实现细节 (DFN) Data Filtering Networks LLaVA系列 (LLaVA) Visual Instruction Tuning (LLaVA-1.5) Improved Baselines with Visual Instruction Tuning InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks (InternVL 1.5) How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites (InternVL 2.5) Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling visual contrastive learning (SimCLR) A Simple Framework for Contrastive Learning of Visual Representations (MoCo) Momentum Contrast for Unsupervised Visual Representation Learning BeiT (MAE) Masked Autoencoders Are Scalable Vision Learners (iBOT) Image BERT: A New Vision-Language Pre-training Framework (BYOL) Bootstrap Your Own Latent A New Approach to Self-Supervised Learning (DINO) Emerging Properties in Self-Supervised Vision Transformers DINOv2: Learning Robust Visual Features without Supervision DINOv3 Self-Supervised Learning 超详细解读 (目录) 万字长文超详解读之DINO全系列—视觉表征对比学习的高峰 万字长文超详解之DINO-V3（DINO全系列之补充篇） DINO&DINO v2：颠覆自监督视觉特征表示学习 resolution Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution Swin Transformer: Hierarchical Vision Transformer using Shifted Windows DualFocus: A Unified Framework for Integrating Positive and Negative Descriptors in Text-based Person Retrieval generative models 视觉生成超详细解读 (目录) image basic (T2I) (VAE) Auto-Encoding Variational Bayes vae和重参数化技巧 (DDPM) Denoising Diffusion Probabilistic Models (DDIM) Denoising Diffusion Implicit Models (Classifier-guided) Diffusion Models Beat GANs on Image Synthesis (Classifier-free) Classifier-free diffusion guidance (VQGAN) Taming transformers for high-resolution image synthesis VQGAN 论文与源码解读：前Diffusion时代的高清图像生成模型 (DIT) Scalable Diffusion Models with Transformers (LDM) High-resolution image synthesis with latent diffusion models (GLIDE) GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models (Imagen) (DALL-E) Zero-Shot Text-to-Image Generation (DALL-E-2) Hierarchical Text-Conditional Image Generation with CLIP Latents (DALL-E-3) Improving Image Generation with Better Captions (ControlNet) Adding Conditional Control to Text-to-Image Diffusion Models Consistency Models (LCM) Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference (SDXL Turbo) Adversarial Diffusion Distillation (EDM) Elucidating the Design Space of Diffusion-Based Generative Models Flow Matching for Generative Modeling (Stable Diffusion 3) Scaling Rectified Flow Transformers for High-Resolution Image Synthesis Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction Stable Diffusion技术路线发展历程回顾 image editing InstructPix2Pix: Learning to Follow Image Editing Instructions Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry Diffusion Model-Based Image Editing: A Survey video survey The Dawn of Video Generation: Preliminary Explorations with SORA-like Models generation Video Diffusion Models Latte: Latent Diffusion Transformer for Video Generation Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning I2V video editing AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks TokenFlow: Consistent Diffusion Features for Consistent Video Editing STABLEV2V: Stablizing Shape Consistency in Video-to-Video Editing VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing autogressive image generation Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation AGI unified generation and comprehension papers Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities Janus-Pro Janus+Janus-Pro 论文解析 Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding (BAGEL) Emerging Properties in Unified Multimodal Pretraining 生成理解统一模型解读 (十一)：万字长文解读生成理解统一模型 BAGEL：高质量多模态交织预训练 SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation Emu: Generative Pretraining in Multimodality (Emu2) Generative Multimodal Models are In-Context Learners Emu3: Next-Token Prediction is All You Need NExT-GPT： Any-to-Any Multimodal LLM blogs 2025 年，生成和理解多模态大模型一些思考 new mllm archs Fuyu-8B: A Multimodal Architecture for AI Agents (SAIL) The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer 字节 SAIL 论文解读 world models blogs 3D/4D World Model（WM）近期发展的总结和思考 VLA 对VLA的RL最新进展梳理 VLA扩充数据来源方法进展梳理 JEPA JEPA：自主机器智能的“蛋糕胚”——JEPA模型发展脉络梳理（第一弹） (I-JEPA) Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning world simulator A Summary “Embodied AI” A Survey on Vision-Language-Action Models: An Action Tokenization Perspective navigation Navigation World Models physical reasoning Denoising Hamiltonian Network for Physical Reasoning

Resource#

Interpretability for MLLMs#

Other fields of MLLMs#

Dataset#

Models#

Resource

Interpretability for MLLMs

Other fields of MLLMs

Dataset

Models