Introduces the first large-scale multimodal benchmark MedLayXPlain-122K showing medical VLMs suffer significant lay-register degradation while general VLMs lack clinical precision.
super hub Mixed citations
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Mixed citation behavior. Most common role is background (60%).
701
Pith papers citing it
77
external citations · Pith
Background
60% of classified citations
abstract
We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. This approach allows the model to generate more efficient and accurate visual representations, closely aligning with human perceptual processes. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos. We employ a unified paradigm for processing both images and videos, enhancing the model's visual perception capabilities. To explore the potential of large multimodal models, Qwen2-VL investigates the scaling laws for large vision-language models (LVLMs). By scaling both the model size-with versions at 2B, 8B, and 72B parameters-and the amount of training data, the Qwen2-VL Series achieves highly competitive performance. Notably, the Qwen2-VL-72B model achieves results comparable to leading models such as GPT-4o and Claude3.5-Sonnet across various multimodal benchmarks, outperforming other generalist models. Code is available at https://github.com/QwenLM/Qwen2-VL .
hub tools
citation-role summary
background 103
baseline 28
method 26
dataset 6
other 2
citation-polarity summary
claims ledger
- abstract We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. This approach allows the model to generate more efficient and accurate visual representations, closely aligning with human perceptual processes. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion
authors
co-cited works
representative citing papers
NeuroQA is a large-scale 3D brain MRI visual question answering benchmark with verified image-grounded QA pairs, multi-domain coverage, and baseline evaluations showing current models lag behind text-only performance.
An MLLM-guided architecture with a mixture of frequency experts and relational alignment loss achieves state-of-the-art all-in-one image restoration, outperforming prior methods by up to 1.35 dB on the CDD11 dataset.
GLADOS reconstructs 3D geometry from disjoint views by generating intermediate perspectives, performing robust coarse alignment that tolerates generative inconsistencies, and iteratively expanding context for consistency.
MedHorizon benchmark reveals current multimodal LLMs achieve only 41.1% accuracy on long medical videos due to failures in sparse evidence retrieval and procedural reasoning.
CADFS supplies a large real-world CAD dataset and FeatureScript representation that, after VLM fine-tuning, produces more accurate and feature-rich designs than prior generative CAD systems.
SpikeMLLM is the first spike-based MLLM framework that maintains near-lossless performance under aggressive timestep compression and delivers 9x throughput and 25x power efficiency gains via a custom RTL accelerator.
VLM-UnBench demonstrates that prompt-based training-free unlearning in VLMs leaves forget accuracy near the no-instruction baseline except under oracle conditions that reveal the target concept.
VAREX benchmark shows structured output compliance limits models under 4B parameters more than extraction ability, with layout-preserving text giving the largest accuracy gains over images.
Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
Molmo VLMs trained on newly collected PixMo open datasets achieve state-of-the-art performance among open-weight models and surpass multiple proprietary VLMs including Claude 3.5 Sonnet and Gemini 1.5 Pro.
Introduces APRS task and PanoSeeker agent using VLM plus EgoSphere memory for active 360° search and segmentation, outperforming baselines on a new benchmark.
Proposes WUICC task and WUICC-bench dataset, then evaluates 11 image difference captioning methods plus 2 LLMs on web UI changes.
VLMs show chance-level depth ordering performance (47-56%) on controlled images, driven by language bias rather than pictorial cues, with no improvement from CoT or ICL.
MoHallBench is a new benchmark evaluating motion hallucination in VideoLLMs from co-occurrence priors, sequential inference, and similarity confusion, revealing decoupling from action recognition performance.
TopoGPT pre-trains an autoregressive transformer on serialized lane graphs from 3.3M scenes to learn geometry priors and uses a perception adapter to apply it to BEV features for improved lane graph prediction on OpenLane-V2.
RCT dataset with sequence-preserving splits demonstrates that tactile-to-text models achieve only 25.1% Recall@1 on held-out materials, exposing generalization as the core challenge.
RRG trains MLLMs via a reinforced multimodal reference game with contrastive rewards on hard positives and negatives to produce accurate, discriminative concept descriptions, achieving SOTA on personalization benchmarks.
VLMs default to visual grounding but a sparse circuit of 2.5-4.8% attention heads in later layers mediates prior-knowledge overrides, identified causally via patching and ablation across three model families.
AirGroundBench is a new diagnostic benchmark exposing that MLLMs handle basic spatial perception but struggle with cross-view alignment, transformation reasoning, and embodied navigation under heterogeneous air-ground views.
VLA language backbones show high redundancy on manipulation benchmarks, with half the LLM blocks removable and even two blocks sufficient to recover baseline performance after fine-tuning, unlike vision and action pathways.
Look-Before-Move is a framework that converts narrative intent into Semantic Observation Contracts, uses Monte Carlo Viewpoint Search for feasible viewpoints, and applies Semantic Trajectory Grounding for coherent camera motion in dynamic 3D story worlds.
DiCoBench is a new high-resolution multi-image benchmark exposing large gaps between top MLLMs and human performance (98.3%) on differential and commonality visual cue perception.
citing papers explorer
-
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
-
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
RAPO uses an information-theoretic lower bound on visual gain to select high-entropy reflection anchors and optimizes a chain-masked KL surrogate, delivering gains over baselines on reasoning benchmarks across LVLM backbones.
-
ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
ECHO organizes VLA experiences into a hierarchical memory tree in hyperbolic space via autoencoder and entailment constraints, delivering a 12.8% success-rate gain on LIBERO-Long over the pi0 baseline.
-
AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models
AT-VLA proposes adaptive tactile injection and a dual-stream tactile reaction mechanism to enhance VLA models for contact-rich robotic manipulation with real-time responses.
-
Bottleneck Tokens for Unified Multimodal Retrieval
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.
-
Learning Vision-Language-Action World Models for Autonomous Driving
VLA-World improves autonomous driving by using action-guided future image generation followed by reflective reasoning over the imagined scene to refine trajectories.
-
When Does Multimodal AI Help? Diagnostic Complementarity of Vision-Language Models and CNNs for Spectrum Management in Satellite-Terrestrial Networks
VLMs and CNNs complement each other on spectrum tasks, with CNNs strong on spatial localization and VLMs on semantic reasoning; a router combining them improves composite performance by 39% over CNN alone.
-
PLUME: Latent Reasoning Based Universal Multimodal Embedding
PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.
-
UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
UniGeoSeg releases the first million-scale dataset for instruction-driven remote sensing segmentation and a unified model that achieves state-of-the-art results with strong zero-shot generalization.
-
Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction
CineNeuron improves fMRI-to-video reconstruction by combining bottom-up semantic enrichment with top-down Mixture-of-Memories integration and outperforms prior methods on benchmarks.
-
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% for high-resolution images in MLLMs via slice-based encoding plus intra-ViT early compression while matching or exceeding baseline performance on document, OCR, and VQA benchmarks.
-
Let ViT Speak: Generative Language-Image Pre-training
GenLIP pretrains ViTs to generate language tokens from images via LM objective without contrastive batches or extra decoders, matching baselines on less data and improving on OCR after multi-resolution continued pretraining.
-
POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management
An 8B multimodal search model trained with Agentic Seeding and V-Fold visual-history compression reaches state-of-the-art scores on six web-search VQA benchmarks.
-
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.
-
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
Q-Zoom achieves up to 4.39x inference speedup in high-resolution MLLM scenarios via query-aware gating and region localization, matching or exceeding baseline accuracy on document and high-res benchmarks.
-
VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
-
Emu3.5: Native Multimodal Models are World Learners
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
-
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
GLM-4.5V reaches state-of-the-art results on 42 multimodal benchmarks among open-source models of similar size by applying reinforcement learning with curriculum sampling to a strong vision foundation model.
-
DanceGRPO: Unleashing GRPO on Visual Generation
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
-
Visual-RFT: Visual Reinforcement Fine-Tuning
Visual-RFT applies reinforcement learning with verifiable perception rewards to improve large vision-language models on fine-grained classification, few-shot detection, and grounding tasks.
-
DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
DexVLA combines a scaled diffusion action expert with embodiment curriculum learning to achieve better generalization and performance than prior VLA models on diverse robot hardware and long-horizon tasks.
-
Fast Image Super-Resolution via Consistency Rectified Flow
FlowSR reformulates SR as a rectified flow and applies consistency distillation with HR regularization plus fast-slow scheduling to enable single-step high-quality super-resolution.
-
Motus: A Unified Latent Action World Model
Motus unifies understanding, video generation, and action in one latent world model via MoT experts and optical-flow latent actions, reporting gains over prior methods in simulation and real robots.
-
Retina-RAG: Retrieval-Augmented Vision-Language Modeling for Joint Retinal Diagnosis and Clinical Report Generation
Retina-RAG combines a retinal classifier, LoRA-tuned Qwen2.5-VL, and RAG to jointly grade DR, detect ME, and generate reports, reaching F1 scores of 0.731 and 0.948 while exceeding baselines on ROUGE-L and SBERT metrics.
-
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
The NTIRE 2026 CD-FSOD Challenge report details innovative methods and performance results from 19 teams on cross-domain few-shot object detection in open- and closed-source tracks.
-
Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains
Flowr is an agentic AI framework that decomposes retail supply chain workflows into coordinated LLM-based agents with human-in-the-loop oversight to automate operations in large supermarket chains.