What matters when building vision-language models?
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:JMFMACRYrecord.jsonopen to challenge →
read the original abstract
The growing interest in vision-language models (VLMs) has been driven by improvements in large language models and vision transformers. Despite the abundance of literature on this subject, we observe that critical decisions regarding the design of VLMs are often not justified. We argue that these unsupported decisions impede progress in the field by making it difficult to identify which choices improve model performance. To address this issue, we conduct extensive experiments around pre-trained models, architecture choice, data, and training methods. Our consolidation of findings includes the development of Idefics2, an efficient foundational VLM of 8 billion parameters. Idefics2 achieves state-of-the-art performance within its size category across various multimodal benchmarks, and is often on par with models four times its size. We release the model (base, instructed, and chat) along with the datasets created for its training.
This paper has not been read by Pith yet.
Forward citations
Cited by 25 Pith papers
-
Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding
Injecting pre-computed layout priors from RT-DETR into VLM prompts raises markdown F1 from 0.37 to 0.92 on a 10k-page OOD benchmark and cuts infinite-loop failures across domains.
-
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
-
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.
-
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
VisRAG achieves 20-40% better end-to-end performance than text-based RAG by directly embedding and retrieving document images with VLMs.
-
LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
LLaVA-NeXT-Interleave unifies multi-image, video, and 3D capabilities in large multimodal models via a new 1.18M-sample interleaved dataset and benchmark, achieving leading results across those tasks while preserving ...
-
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Cambrian-1 is a vision-centric multimodal LLM family that evaluates over 20 vision encoders, introduces CV-Bench and the Spatial Vision Aggregator, and releases open models, code, and data achieving strong performance...
-
Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap
ReVisIT achieves near-SOTA performance on open multimodal tasks by retrieving and reasoning over labeled images as visual exemplars in a train-free scaffold, closing the open-vs-closed gap for models like Qwen3-VL-30B.
-
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
-
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.
-
Multimodal Language Models Cannot Spot Spatial Inconsistencies
Multimodal LLMs significantly underperform humans at spotting objects that break 3D consistency in multi-view image pairs.
-
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
SmolVLA is a small efficient VLA model that achieves performance comparable to 10x larger models while training on one GPU and deploying on consumer hardware via community data and chunked asynchronous action prediction.
-
SmolVLM: Redefining small and efficient multimodal models
SmolVLM-256M outperforms a 300-times larger model using under 1 GB GPU memory, while the 2.2B version matches state-of-the-art VLMs at half the memory cost.
-
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.
-
ESC: Emotional Self-Correction for Reliable Vision-Language Models
ESC uses emotional cues triggered by an external verifier to enable training-free self-correction in VLMs, improving reliability on safety, hallucination, and reasoning benchmarks.
-
Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
TASM proposes a task-aware structured memory framework using task-vector compression, bipartite token merging, and a Core Memory plus Latent Bank hierarchy to enable efficient dynamic multi-modal in-context learning.
-
VLMs May Not Globally Enhance Human Alignment over LLMs During Natural Reading
Multimodal pretraining does not provide a uniform global advantage over language-only pretraining in aligning model representations with human fMRI and eye-tracking data during natural reading, though selective advant...
-
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
ReCAPA uses multi-level predictive correction and semantic alignment modules to reduce cascading failures in VLA systems, with new metrics for tracking error propagation and recovery on embodied benchmarks.
-
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
ReCAPA adds predictive correction and multi-level semantic alignment to VLA models, plus two new metrics for tracking error spread and recovery, yielding competitive benchmark results over LLM baselines.
-
ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection
ZSG-IAD is a zero-shot multimodal system that uses language-guided two-hop grounding and rule-based reinforcement learning to produce anomaly masks and explainable reports from industrial sensor data.
-
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.
-
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
MiniCPM-Llama3-V 2.5 delivers GPT-4V-level multimodal performance on phones through architecture, pretraining, and alignment optimizations.
-
Vision Language Model Helps Private Information De-Identification in Vision Data
VisShield with OPTIC dataset enables VLMs to localize and mask private text in vision data via instruction tuning for privacy preservation.
-
Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.
-
PaliGemma 2: A Family of Versatile VLMs for Transfer
PaliGemma 2 is a family of vision-language models that achieves state-of-the-art results on transfer tasks like table structure recognition and radiography report generation by combining SigLIP with Gemma 2 models at ...
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.