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
-
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.
-
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
LURE reduces object hallucination in LVLMs by 23% via post-hoc revision informed by co-occurrence, uncertainty, and text position analysis.
-
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.
-
Kosmos-2: Grounding Multimodal Large Language Models to the World
Kosmos-2 grounds text to image regions by encoding refer expressions as Markdown links to sequences of location tokens and trains on a new GrIT dataset of grounded image-text pairs.
-
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.
-
PandaGPT: One Model To Instruction-Follow Them All
A single model trained only on image-text pairs gains instruction-following ability across images, video, and audio by routing all modalities through ImageBind's shared embedding space into Vicuna.
-
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
-
Otter: A Multi-Modal Model with In-Context Instruction Tuning
Otter is a multi-modal model instruction-tuned on the MIMIC-IT dataset of over 3 million in-context instruction-response pairs to improve convergence and generalization on tasks with multiple images and videos.
-
mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
mPLUG-Owl introduces a two-stage modular training paradigm that aligns images with text in LLMs via frozen visual modules followed by LoRA fine-tuning, achieving strong multimodal instruction following.
-
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
MiniGPT-4 shows that aligning a frozen vision encoder to Vicuna via one projection layer plus a second-stage detailed-description fine-tune produces GPT-4-like vision-language abilities including detailed captions, creative writing, and instruction following.
-
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
HuggingGPT is an agent system where ChatGPT plans and orchestrates calls to Hugging Face models to solve complex multi-modal AI tasks.
-
EVA-CLIP: Improved Training Techniques for CLIP at Scale
EVA-CLIP delivers improved CLIP training recipes that yield 82.0% zero-shot ImageNet-1K accuracy for a 5B-parameter model after only 9 billion samples.
-
MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks.
-
Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
EyeVLM benchmark finds that current VLMs underperform specialized visual models on gaze following and social gaze prediction, with fine-tuning narrowing but not closing the gap.
-
MORN: Metacognitive Object-Goal Regulation for Resource-Rational Long-Horizon Navigation
MORN augments frozen VLM-based object navigation agents with a System 2 meta-controller using Potentiality Index, Persistence Gating, and Evidence Accumulation to improve goal completion rate from 0.23 to 0.30 and reduce wasted steps on the HM3D dataset.
-
VLA Foundry: A Unified Framework for Training Vision-Language-Action Models
VLA Foundry provides a single training stack for VLA models and releases open models that match prior closed-source performance or outperform baselines on multi-task manipulation in simulation.
-
Qwen3.5-Omni Technical Report
Qwen3.5-Omni scales an omnimodal model to hundreds of billions of parameters with 256k context, introduces ARIA for stable speech synthesis, and reports SOTA performance on 215 audio-visual benchmarks while adding multilingual and audio-visual coding capabilities.
-
ClickAIXR: On-Device Multimodal Vision-Language Interaction with Real-World Objects in Extended Reality
ClickAIXR combines controller-based object selection in XR with on-device VLM inference to enable private, precise multimodal queries about real objects.
-
Grounding Everything in Tokens for Multimodal Large Language Models
GETok partitions images with grid tokens and refines locations via offset tokens to enable better native 2D spatial reasoning in MLLMs.
-
AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and Reasoning
AVATAAR reports relative gains of 5-8% over baseline on CinePile benchmark categories through agentic feedback for long video QA.
-
Qwen2.5-Omni Technical Report
Qwen2.5-Omni presents a multimodal model with block-wise encoders, TMRoPE position embeddings, and a Thinker-Talker architecture that enables simultaneous text and streaming speech generation while matching text performance on reasoning benchmarks.
-
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.
-
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
mPLUG-Owl3 introduces hyper attention blocks to integrate vision and language for long image-sequence understanding and reports SOTA results on single-image, multi-image, and video benchmarks.
-
Hallucination of Multimodal Large Language Models: A Survey
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
-
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Mini-Gemini enhances VLMs via high-resolution visual refinement, curated reasoning data, and self-guided generation to reach leading zero-shot benchmark results across 2B-34B LLMs.
-
Automated Description Generation of Cytologic Findings for Lung Cytological Images Using a Pretrained Vision Model and Dual Text Decoders: Preliminary Study
A CNN classifies lung cytology patches as benign or malignant at 100% sensitivity and 96.4% specificity, then routes to one of two Transformer decoders to generate findings text achieving BLEU-4 of 0.828 on 801 images.
-
Caption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval
Caption-Matching generates image captions via pre-trained VLMs and matches them across domains to achieve SOTA CDIR performance on Office-Home and DomainNet without labeled data or fine-tuning.
-
Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.
-
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
MobileVLM achieves on-par performance with much larger vision-language models on standard benchmarks while delivering state-of-the-art inference speeds of 21.5 tokens per second on Snapdragon 888 CPU and 65.3 on Jetson Orin GPU.
-
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
InternVL scales a vision model to 6B parameters and aligns it with LLMs using web data to achieve state-of-the-art results on 32 visual-linguistic benchmarks.
-
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
SPHINX improves multi-modal LLMs through joint mixing of weights, tasks, and visual embeddings from varied sources to achieve stronger alignment and multi-purpose capabilities.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration
mPLUG-Owl2 presents a modular MLLM architecture that enables modality collaboration via shared functional modules and modality-adaptive components, achieving SOTA on both text and multi-modal tasks with one generic model.
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.
-
MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets
MM-LIMA uses proposed quality metrics and a trainable selector to pick 200 high-quality multimodal instruction examples and outperforms MiniGPT-4 on evaluations.
-
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
LLaMA-Adapter V2 achieves open-ended visual instruction following in LLMs by unlocking more parameters, early fusion of visual tokens, and joint training on disjoint parameter groups with only 14M added parameters.
-
DetailCLIP: Injecting Image Details into CLIP's Feature Space
A patch-based fusion method extends CLIP to high-resolution images by retaining multi-scale details for improved class-prompted retrieval.
-
Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design
Machine interpreting should shift from fidelity metrics to three design priorities—agency, grounding, and experience—drawn from interpreting studies to close the usability gap with human-mediated communication.
-
SmoGVLM: A Small, Graph-enhanced Vision-Language Model
A graph-enhanced 1.3B-parameter VLM achieves up to 16.24% gains and outperforms larger VLMs by integrating structured knowledge via GNNs.