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.
hub Canonical reference
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Canonical reference. 70% of citing Pith papers cite this work as background.
43
Pith papers citing it
Background
70% of classified citations
abstract
Large language models have shown their remarkable capabilities as a general interface for various language-related applications. Motivated by this, we target to build a unified interface for completing many vision-language tasks including image description, visual question answering, and visual grounding, among others. The challenge is to use a single model for performing diverse vision-language tasks effectively with simple multi-modal instructions. Towards this objective, we introduce MiniGPT-v2, a model that can be treated as a unified interface for better handling various vision-language tasks. We propose using unique identifiers for different tasks when training the model. These identifiers enable our model to better distinguish each task instruction effortlessly and also improve the model learning efficiency for each task. After the three-stage training, the experimental results show that MiniGPT-v2 achieves strong performance on many visual question-answering and visual grounding benchmarks compared to other vision-language generalist models. Our model and codes are available at https://minigpt-v2.github.io/
hub tools
citation-role summary
background 7
baseline 2
method 1
citation-polarity summary
representative citing papers
A new framework called THUMB cards organizes gender bias metrics for T2I models by risk-tiered use cases, measurement categories, and harm typologies aligned with the EU AI Act.
STORM is an end-to-end MLLM for referring multi-object tracking that uses task-composition learning to leverage sub-task data and introduces the STORM-Bench dataset, achieving SOTA results.
Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.
SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
MuirBench is a new benchmark showing that top multimodal LLMs struggle with robust multi-image understanding, with GPT-4o at 68% and open-source models below 33% accuracy.
MathVerse is a benchmark that tests multi-modal LLMs on visual math by providing each problem in six versions with progressively less diagram and text information to measure true visual understanding.
VisReflect generates continuous latent visual reflections to emphasize relevant visual features and guide attention in LVLMs, yielding 4.1% gains on image benchmarks and 1.8% on video benchmarks with 44% less inference time than zooming methods.
SafeSteer improves safety in multimodal large language models by up to 33.4% via a decoding probe and modal alignment vector without any fine-tuning.
DR-Smoothing introduces a disrupt-then-rectify prompt processing scheme into smoothing defenses, delivering tight theoretical bounds on success probability against both token- and prompt-level jailbreaks.
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
ThinkDeeper introduces a world-model-based reasoning step that predicts future spatial states to improve multimodal visual grounding for autonomous vehicles, achieving top results on Talk2Car and other benchmarks.
MathFlow decouples perception and inference stages in MLLMs for visual math, with a dedicated perception model delivering gains on the FlowVerse benchmark when paired with existing reasoners.
Uni-NaVid unifies diverse embodied navigation tasks into one video-based vision-language-action model trained on 3.6 million samples from four sub-tasks, achieving state-of-the-art performance on benchmarks and real-world tests.
LongVU adaptively compresses long video tokens using DINOv2-based frame deduplication, text-guided cross-modal selection, and temporal spatial reduction to improve video-language understanding in MLLMs with minimal detail loss.
VLBiasBench is a new large-scale benchmark with 128,342 samples covering nine social bias categories plus two intersectional ones to evaluate biases in LVLMs.
A PRISMA-based survey of 158 computational works on toxic meme detection introduces a new toxicity taxonomy and a framework linking target, intent, and conveyance tactics while noting trends in LLMs and cross-modal methods.
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.
SeeClick improves visual GUI agents via GUI grounding pre-training on automatically curated data and introduces the ScreenSpot benchmark, with results indicating that stronger grounding boosts downstream task performance.
MVBench is a benchmark of 20 temporal video understanding tasks built by transforming static tasks into dynamic ones, with VideoChat2 outperforming prior MLLMs by over 15%.
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.
AMBER is an LLM-free multi-dimensional benchmark for evaluating hallucinations in MLLMs across generative and discriminative tasks.
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.
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.
-
Context Matters: Auditing Gender Bias in T2I Generation through Risk-Tiered Use-Case Profiles
A new framework called THUMB cards organizes gender bias metrics for T2I models by risk-tiered use cases, measurement categories, and harm typologies aligned with the EU AI Act.
-
STORM: End-to-End Referring Multi-Object Tracking in Videos
STORM is an end-to-end MLLM for referring multi-object tracking that uses task-composition learning to leverage sub-task data and introduces the STORM-Bench dataset, achieving SOTA results.
-
Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.
-
SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
-
Toward Generalizable Forgery Detection and Reasoning
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
-
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
MuirBench is a new benchmark showing that top multimodal LLMs struggle with robust multi-image understanding, with GPT-4o at 68% and open-source models below 33% accuracy.
-
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
MathVerse is a benchmark that tests multi-modal LLMs on visual math by providing each problem in six versions with progressively less diagram and text information to measure true visual understanding.
-
VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context
VisReflect generates continuous latent visual reflections to emphasize relevant visual features and guide attention in LVLMs, yielding 4.1% gains on image benchmarks and 1.8% on video benchmarks with 44% less inference time than zooming methods.
-
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models
SafeSteer improves safety in multimodal large language models by up to 33.4% via a decoding probe and modal alignment vector without any fine-tuning.
-
Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
DR-Smoothing introduces a disrupt-then-rectify prompt processing scheme into smoothing defenses, delivering tight theoretical bounds on success probability against both token- and prompt-level jailbreaks.
-
POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
-
Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles
ThinkDeeper introduces a world-model-based reasoning step that predicts future spatial states to improve multimodal visual grounding for autonomous vehicles, achieving top results on Talk2Car and other benchmarks.
-
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
MathFlow decouples perception and inference stages in MLLMs for visual math, with a dedicated perception model delivering gains on the FlowVerse benchmark when paired with existing reasoners.
-
Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
Uni-NaVid unifies diverse embodied navigation tasks into one video-based vision-language-action model trained on 3.6 million samples from four sub-tasks, achieving state-of-the-art performance on benchmarks and real-world tests.
-
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
LongVU adaptively compresses long video tokens using DINOv2-based frame deduplication, text-guided cross-modal selection, and temporal spatial reduction to improve video-language understanding in MLLMs with minimal detail loss.
-
VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
VLBiasBench is a new large-scale benchmark with 128,342 samples covering nine social bias categories plus two intersectional ones to evaluate biases in LVLMs.
-
Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities
A PRISMA-based survey of 158 computational works on toxic meme detection introduces a new toxicity taxonomy and a framework linking target, intent, and conveyance tactics while noting trends in LLMs and cross-modal methods.
-
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.
-
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
SeeClick improves visual GUI agents via GUI grounding pre-training on automatically curated data and introduces the ScreenSpot benchmark, with results indicating that stronger grounding boosts downstream task performance.
-
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
MVBench is a benchmark of 20 temporal video understanding tasks built by transforming static tasks into dynamic ones, with VideoChat2 outperforming prior MLLMs by over 15%.
-
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.
-
AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
AMBER is an LLM-free multi-dimensional benchmark for evaluating hallucinations in MLLMs across generative and discriminative tasks.
-
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.
-
Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack
Gradient Token Masking localizes critical adversarial image tokens via hidden-state gradient norms and masks them to neutralize prompt injection attacks in multimodal LLMs with one forward-backward pass.
-
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
MPD reduces hallucinations in LVLMs by 23.4% while retaining 97.4% of general capability through semantic disentanglement and selective parameter updates.
-
Analogical Reasoning as a Doctor: A Foundation Model for Gastrointestinal Endoscopy Diagnosis
RATNet applies analogical reasoning via a cyclic pre-training strategy to outperform prior foundation models in GI endoscopy diagnosis across diagnosis, few-shot, zero-shot, robustness, adaptation, and federated scenarios.
-
Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation
Firebolt-VL introduces an LFM-based decoder and token-grid correlation to achieve linear-time vision-language inference with improved fine-grained grounding.
-
Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning
Geo-R1 uses reasoning-centric reinforcement fine-tuning to improve few-shot performance and generalization in geospatial referring expression understanding over supervised baselines.
-
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs
GUARD automates generation of guideline-violating questions and jailbreak diagnostics to test LLM compliance with government ethics guidelines, validated empirically on eight models and extended to vision-language models.
-
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
LLaVA-Octopus introduces instruction-driven adaptive fusion of multiple visual projectors in a multimodal LLM to improve video understanding performance.
-
M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation
M4CXR is a multi-modal large language model that performs multiple tasks in chest X-ray analysis including report generation with claimed SOTA clinical accuracy using chain-of-thought prompting.
-
InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model
InternLM-XComposer2 introduces Partial LoRA on InternLM2-7B to enable high-quality free-form text-image composition while matching or exceeding GPT-4V on select vision-language benchmarks.
-
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.
-
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.
-
TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase.
-
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
MobileVLM V2 shows that 1.7B and 3B parameter vision-language models can reach or exceed the performance of 3B and 7B+ models on common VLM benchmarks via targeted design and data improvements.
-
InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition
InternLM-XComposer generates articles with seamlessly integrated images and achieves state-of-the-art results on vision-language benchmarks including MME, MMBench, and Seed-Bench.
-
A Survey on Hallucination in Large Vision-Language Models
This survey reviews the definition, symptoms, evaluation benchmarks, root causes, and mitigation methods for hallucinations in large vision-language models.
- SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
- StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning
- VISTA: Video Interaction Spatio-Temporal Analysis Benchmark
- Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?