REVIEW 6 cited by
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Existing encoder-free vision-language models (VLMs) are rapidly narrowing the performance gap with their encoder-based counterparts, highlighting the promising potential for unified multimodal systems with structural simplicity and efficient deployment. We systematically clarify the performance gap between VLMs using pre-trained vision encoders, discrete tokenizers, and minimalist visual layers from scratch, deeply excavating the under-examined characteristics of encoder-free VLMs. We develop efficient strategies for encoder-free VLMs that rival mainstream encoder-based ones. After an in-depth investigation, we launch EVEv2.0, a new and improved family of encoder-free VLMs. We show that: (i) Properly decomposing and hierarchically associating vision and language within a unified model reduces interference between modalities. (ii) A well-designed training strategy enables effective optimization for encoder-free VLMs. Through extensive evaluation, our EVEv2.0 represents a thorough study for developing a decoder-only architecture across modalities, demonstrating superior data efficiency and strong vision-reasoning capability. Code is publicly available at: https://github.com/baaivision/EVE.
Forward citations
Cited by 6 Pith papers
-
Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
Spatial understanding in multimodal LLMs plateaus quickly as training data grows, and position encoding in the visual encoder is the more influential factor.
-
NeoBabel: A Multilingual Open Tower for Visual Generation
A 2B multilingual text-to-image model trained on 124M translated pairs matches or beats larger English-only baselines on English while scoring higher on the authors' multilingual benchmark extensions.
-
Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs
LUViT jointly pretrains a ViT with masked auto-encoding and LoRA adapters in a frozen LLM block, reporting +0.4% ImageNet-1K accuracy and up to +2.2% on ImageNet-A over its own MAE baseline.
-
Dense360: Dense Understanding from Omnidirectional Panoramas
Introduces a 160K-panorama auto-annotated dataset, a dense captioning and grounding benchmark, and ERP-RoPE; fine-tuning Qwen2.5VL on the data lifts benchmark scores.
-
MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts
MoE-TTS adds frozen text-expert MoE modules to a Qwen3-based TTS system and reports better out-of-domain description alignment than ElevenLabs and MiniMax on a small hand-built test set.
-
Regularizing Subspace Redundancy of Low-Rank Adaptation
ReSoRA adds a penalty that reduces redundancy among rank-1 subspaces of LoRA-style adapters, producing modest accuracy improvements on vision-language retrieval and visual classification.
Discussion (0). Sign in to comment.