MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
super hub Canonical reference
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Canonical reference. 75% of citing Pith papers cite this work as background.
115
Pith papers citing it
Background
75% of classified citations
abstract
The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and frozen large language models. BLIP-2 bridges the modality gap with a lightweight Querying Transformer, which is pre-trained in two stages. The first stage bootstraps vision-language representation learning from a frozen image encoder. The second stage bootstraps vision-to-language generative learning from a frozen language model. BLIP-2 achieves state-of-the-art performance on various vision-language tasks, despite having significantly fewer trainable parameters than existing methods. For example, our model outperforms Flamingo80B by 8.7% on zero-shot VQAv2 with 54x fewer trainable parameters. We also demonstrate the model's emerging capabilities of zero-shot image-to-text generation that can follow natural language instructions.
hub tools
citation-role summary
background 31
method 6
baseline 2
dataset 1
citation-polarity summary
claims ledger
- abstract The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and frozen large language models. BLIP-2 bridges the modality gap with a lightweight Querying Transformer, which is pre-trained in two stages. The first stage bootstraps vision-language representation learning from a frozen image encoder. The second stage bootstraps vision-to-language generative
authors
co-cited works
representative citing papers
UniShield introduces a knowledge-graph-informed multimodal framework that improves unified detection of physical and digital face attacks through instruction tuning and consistency-optimized reasoning.
Geo2Sound generates geographically realistic soundscapes from satellite imagery via geospatial attribute modeling, semantic hypothesis expansion, and geo-acoustic alignment, achieving SOTA FAD of 1.765 on a new 20k-pair benchmark.
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
Bottleneck Tokens paired with a masked generative objective achieve state-of-the-art unified multimodal retrieval performance among 2B-scale models on the MMEB-V2 benchmark with 78 datasets.
UCGP is a universal physical adversarial patch that compromises cross-modal semantic alignment in IR-VLMs through curved-grid parameterization and representation-space disruption.
WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.
LooseRoPE modulates RoPE in diffusion attention maps to continuously trade off between preserving a pasted object's identity and harmonizing it with its new surroundings.
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.
ReKep encodes robotic tasks as optimizable Python functions over 3D keypoints that are generated automatically from language and RGB-D input, enabling real-time hierarchical planning on single- and dual-arm platforms without task-specific data.
Presents Med-HallMark benchmark, MediHall Score metric, and MediHallDetector model for hallucination detection and evaluation in medical LVLMs.
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
Vim is a bidirectional Mamba vision backbone that outperforms DeiT in accuracy on standard tasks while being substantially faster and more memory-efficient for high-resolution images.
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
HallusionBench shows GPT-4V reaches only 31.42% accuracy on paired questions testing language hallucination and visual illusion in LVLMs, with other models below 16%.
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.
Large vision-language models exhibit severe object hallucination that varies with training instructions, and the proposed POPE polling method evaluates it more stably and flexibly than prior approaches.
VideoChat integrates video models and LLMs via a learnable interface for chat-based spatiotemporal and causal video reasoning, trained on a new video-centric instruction dataset.
LLaVA is trained on GPT-4 generated visual instruction data to achieve 85.1% relative performance to GPT-4 on synthetic multimodal tasks and 92.53% accuracy on Science QA.
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.
citing papers explorer
-
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
-
UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
UniShield introduces a knowledge-graph-informed multimodal framework that improves unified detection of physical and digital face attacks through instruction tuning and consistency-optimized reasoning.
-
Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
-
Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
UCGP is a universal physical adversarial patch that compromises cross-modal semantic alignment in IR-VLMs through curved-grid parameterization and representation-space disruption.
-
WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.
-
SAM 3: Segment Anything with Concepts
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
-
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.
-
Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
Presents Med-HallMark benchmark, MediHall Score metric, and MediHallDetector model for hallucination detection and evaluation in medical LVLMs.
-
3D-VLA: A 3D Vision-Language-Action Generative World Model
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
-
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Vim is a bidirectional Mamba vision backbone that outperforms DeiT in accuracy on standard tasks while being substantially faster and more memory-efficient for high-resolution images.
-
LRM: Large Reconstruction Model for Single Image to 3D
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
-
HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
HallusionBench shows GPT-4V reaches only 31.42% accuracy on paired questions testing language hallucination and visual illusion in LVLMs, with other models below 16%.
-
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
-
Evaluating Object Hallucination in Large Vision-Language Models
Large vision-language models exhibit severe object hallucination that varies with training instructions, and the proposed POPE polling method evaluates it more stably and flexibly than prior approaches.
-
VideoChat: Chat-Centric Video Understanding
VideoChat integrates video models and LLMs via a learnable interface for chat-based spatiotemporal and causal video reasoning, trained on a new video-centric instruction dataset.
-
Visual Instruction Tuning
LLaVA is trained on GPT-4 generated visual instruction data to achieve 85.1% relative performance to GPT-4 on synthetic multimodal tasks and 92.53% accuracy on Science QA.
-
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
-
ViperGPT: Visual Inference via Python Execution for Reasoning
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
-
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.
-
Self-Prophetic Decoding to Unlock Visual Search in LVLMs
SeProD is a plug-and-play self-prophetic decoding framework that combines pre- and post-training LVLM capabilities via probability-based sampling to improve coherent visual search and multi-step reasoning.
-
Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs
Proposes the first unified incomplete video-language model that processes missing modalities and serves as a plug-and-play module to boost existing VLMs on multi-modal tasks.
-
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
-
StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
StyleTextGen proposes a dual-branch style encoder, text style consistency loss, and mask-guided inference to achieve superior style consistency and cross-lingual performance in multilingual scene text generation on a new bilingual benchmark.
-
Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology
MLLMs achieve zero-shot recognition of seizure semiological features better than fine-tuned vision models on most tested features, with signal enhancement and faithful explanations.
-
AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning
AIM applies modality-specific masks to balance stability and plasticity in asymmetric VLMs, achieving SOTA average performance and reduced forgetting on continual VQA v2 and GQA while preserving generalization to novel compositions.
-
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
-
Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models
Visual Funnel resolves contextual blindness in MLLMs by constructing an entropy-scaled portfolio of hierarchically structured image crops that preserves both local detail and global context.
-
Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
RUDDER creates a persistent visual anchor by extracting CARD from prefill residuals and modulating its injection via an adaptive Beta Gate, cutting CHAIR_S by 24.4% and CHAIR_i by 23.6% on average across LLaVA, Idefics2, InstructBLIP and Qwen2.5-VL with >96% throughput.
-
Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?
The ITW-SM dataset and targeted optimization of detector design choices yield a 26.87% average AUC improvement for state-of-the-art AI-generated image detectors under real-world social media conditions.
-
How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
Multimodal foundation models achieve respectable but sub-specialist performance on semantic vision tasks and weaker results on geometric tasks when evaluated through prompt chaining on established benchmarks.
-
RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
RedDiffuser is a reinforced diffusion framework that generates adversarial visual contexts to audit and expose widespread multimodal safety failures in VLMs, increasing unsafe response rates by up to 10.69% on LLaVA with transfer to other models.
-
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
PPLLaVA uses CLIP-based alignment and prompt-guided convolution-style pooling to reduce visual tokens 18x in Video LLMs, achieving SOTA results on captioning, QA, and long-form reasoning benchmarks with higher throughput.
-
ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval
Presents ChatSearch dataset and ChatSearcher generative model for conversational image retrieval on open-domain images, claiming superior performance on the new dataset and competitive results elsewhere.
-
LLaVA-Video: Video Instruction Tuning With Synthetic Data
LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.
-
SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation
SketchDeco performs training-free sketch colourisation via diffusion inversion to insert user colors followed by custom self-attention blending for local fidelity and global harmony.
-
BLINK: Multimodal Large Language Models Can See but Not Perceive
BLINK benchmark shows multimodal LLMs reach only 45-51 percent accuracy on core visual perception tasks where humans achieve 95 percent, indicating these abilities have not emerged.
-
Are We on the Right Way for Evaluating Large Vision-Language Models?
Current LVLM benchmarks overestimate capabilities because many questions can be answered without images due to design flaws or data leakage; MMStar is a human-curated set of 1,500 vision-indispensable samples across 6 capabilities and 18 axes with new metrics for leakage and true multi-modal gain.
-
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
MM1 models achieve state-of-the-art few-shot multimodal results by pre-training on a careful mix of image-caption, interleaved, and text-only data with optimized image encoders.
-
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Biased noise sampling for rectified flows combined with a bidirectional text-image transformer architecture yields state-of-the-art high-resolution text-to-image results that scale predictably with model size.
-
NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
NaVid, a video-based VLM trained on 510k navigation and 763k web samples, achieves SOTA VLN performance using only monocular RGB video for next-step action planning in sim and real environments.
-
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
MoE-LLaVA applies mixture-of-experts sparsity to LVLMs via MoE-Tuning, delivering LLaVA-1.5-7B level visual understanding and better hallucination resistance with only ~3B active parameters.
-
InstantID: Zero-shot Identity-Preserving Generation in Seconds
InstantID enables zero-shot identity-preserving image generation from one facial image via a novel IdentityNet that combines strong semantic and weak spatial conditioning with text prompts in diffusion models.
-
ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
A new 1.2M-caption dataset generated via GPT-4V improves LMMs on MME and MMBench by 222.8/22.0/22.3 and 2.7/1.3/1.5 points respectively when used for supervised fine-tuning.
-
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Video-LLaVA creates a unified visual representation for images and videos via pre-projection alignment, enabling mutual enhancement from joint training and strong results on image and video benchmarks.
-
DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
DragNUWA integrates text, image, and trajectory controls into a diffusion video model using a Trajectory Sampler, Multiscale Fusion, and Adaptive Training to enable fine-grained open-domain video generation.
-
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
IP-Adapter adds effective image prompting to text-to-image diffusion models using a lightweight decoupled cross-attention adapter that works alongside text prompts and other controls.
-
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
InternVid supplies 7M videos and LLM captions to train ViCLIP, which reaches leading zero-shot action recognition and competitive retrieval performance.
-
MMBench: Is Your Multi-modal Model an All-around Player?
MMBench is a new bilingual benchmark that uses curated questions, CircularEval, and LLM-assisted answer conversion to provide objective, fine-grained evaluation of vision-language models.
-
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
A new dataset of 400k visual instructions including negative examples at three semantic levels reduces hallucinations in models like MiniGPT-4 when used for fine-tuning while improving benchmark performance.
-
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
MME is a manually annotated benchmark evaluating MLLMs on perception and cognition across 14 subtasks to avoid data leakage and support fair model comparisons.