S1-VL combines structured scientific reasoning with iterative image manipulation via code execution to reach state-of-the-art results on visual and scientific reasoning benchmarks.
hub Mixed citations
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
Mixed citation behavior. Most common role is background (60%).
62
Pith papers citing it
17
external citations · Pith
Background
60% of classified citations
abstract
The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs. In this work, we design a large-scale vision-language foundation model (InternVL), which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources. This model can be broadly applied to and achieve state-of-the-art performance on 32 generic visual-linguistic benchmarks including visual perception tasks such as image-level or pixel-level recognition, vision-language tasks such as zero-shot image/video classification, zero-shot image/video-text retrieval, and link with LLMs to create multi-modal dialogue systems. It has powerful visual capabilities and can be a good alternative to the ViT-22B. We hope that our research could contribute to the development of multi-modal large models. Code and models are available at https://github.com/OpenGVLab/InternVL.
hub tools
citation-role summary
background 9
baseline 5
method 1
citation-polarity summary
representative citing papers
ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
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.
MMMU provides 11.5K heterogeneous college-level multimodal questions that current models solve at 56-59% accuracy, establishing a new standard for expert multimodal evaluation.
Introduces Neighbor Leakage Rate showing high trigger leakage in VLAS backdoors at 3% poisoning, caused by broad activation regions in fine-tuning that hard-negative samples can narrow.
PlanBench-V is a new benchmark and dataset for evaluating VLMs on spatial planning map interpretation via a four-stage framework of Perception, Reasoning, Association, and Implementation.
CosFlyTrack provides 12,000 expert UAV trajectories with aligned RGB, depth, segmentation, pose, target state, and bilingual instructions to train visual tracking agents, yielding 53-69 point gains in success rate after fine-tuning.
Visual token pruning in MLLMs fails on complex reasoning due to Relevant Visual Information Shift during decoding, but the DSTP framework fixes it training-free across models.
Mosaic combines text perturbation, multi-view image optimization, and surrogate model ensembles to reduce reliance on any single open-source model and achieve higher attack success rates on commercial closed-source VLMs.
FLARE is a vision-language model family using text-guided vision encoding, context-aware alignment decoding, dual-semantic mapping loss, and text-driven VQA synthesis to achieve deep cross-modal integration, outperforming larger models with only 630 vision tokens at 3B scale.
WE-MATH benchmark reveals most LMMs rely on rote memorization for visual math while GPT-4o has shifted toward knowledge generalization.
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.
Qwen-RobotWorld is a language-conditioned video world model using Double-Stream MMDiT, an 8.6M-frame embodied corpus, and progressive curriculum training that ranks first on EWMBench and DreamGen Bench.
The paper creates InsightVQA, a 725K QA-pair benchmark with perception, grounded-understanding, and cognition levels for emotion-cognitive visual question answering, plus a 30K-sample evaluation set and InsightNet baseline.
T-CLIP introduces a physics-aware thermal captioning dataset (IR-Cap) and a decoupled dual-LoRA adaptation of CLIP that improves cross-modal retrieval on thermal benchmarks by separating scene-level and object-level thermal understanding.
ChartAct is a benchmark for dynamic chart understanding that shows most multimodal models struggle with interactive charts, with top performance at 84.5%.
SWIM aligns cross-attention maps from object nouns to ground-truth masks during training on the new NL-Refer dataset to enable text-only fine-grained video object understanding in MLLMs.
CREST selects video frames using curvature-adaptive non-maximum suppression on CLIP relevance scores, beating AKS by ~0.5% on two long-video QA benchmarks while using a fraction of MIRA's preprocessing cost.
Modality representations share dominant semantic geometry but have an anisotropic residual gap; AnisoAlign corrects source representations boundedly using target geometry for unpaired alignment.
LVLM-based agents exhibit trust boundary confusion with visual injections and a multi-agent defense separating perception from decision-making reduces misleading responses while preserving correct ones.
CodecSight reuses video codec signals for online patch pruning before the vision transformer and selective KV-cache refresh in the LLM, delivering up to 3x higher throughput and 87% lower GPU compute than prior baselines with 0-8% F1 drop.
AICA-Bench evaluates 23 VLMs on affective image analysis, identifies weak intensity calibration and shallow descriptions as limitations, and proposes training-free Grounded Affective Tree Prompting to improve performance.
AD-Copilot trains an MLLM on a new curated industrial dataset Chat-AD with a Comparison Encoder that uses cross-attention on image pairs, reaching 82.3% accuracy on MMAD and 3.35x gains on MMAD-BBox while generalizing and exceeding human experts on some tasks.
Attacking only the top 20% high-entropy token positions in vision-language models causes comparable semantic damage and more harmful outputs than global attacks, and these vulnerable tokens transfer across model architectures.
citing papers explorer
-
Agentic AI for Remote Sensing: Technical Challenges and Research Directions
Position paper identifies structural challenges in applying generic agentic AI to Earth Observation and outlines design principles for EO-native agents focused on geospatial state and validity.
-
Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving
Introduces structured NuScenes-S dataset and 0.9B FastDrive VLM claiming 20% higher decision accuracy and over 10x inference speedup versus larger unstructured VLMs.
-
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
-
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
VITA-1.5 integrates vision and speech into a single LLM through multi-stage training, delivering competitive benchmark results on image, video, and speech tasks with near real-time response speed.
-
PaliGemma: A versatile 3B VLM for transfer
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.
-
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
-
StepGuard: Guarding Web Navigation via Single-Step Calibration
StepGuard framework with DDPO and CANR claims SOTA navigation and answer accuracy on web benchmarks by switching policies and triggering reflection on low-confidence steps.
-
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.
-
SAGE Celer 2.6 Technical Card
SAGE Celer 2.6 is a new line of language models with inverse reasoning training, integrated vision, and strong performance on math, coding, and South Asian language benchmarks.
- VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models
- Compatibility of Face Embeddings Across Deep Neural Networks
- Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding