A blank-image ablation test reveals that high probe accuracy on VLM spatial reasoning frequently reflects priors or inverted signs rather than image grounding, with horizontal grounded, vertical prior, and depth inverted.
mega hub Mixed citations
Qwen2.5-VL Technical Report
Mixed citation behavior. Most common role is background (53%).
1072
Pith papers citing it
Background
53% of classified citations
abstract
We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.
hub tools
citation-role summary
background 152
baseline 57
method 57
dataset 5
other 3
citation-polarity summary
claims ledger
- abstract We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as wel
authors
mega hub controls
export citing contexts JSON
export graph JSON
export full bundle JSON
open full Pith review
annotated reader queued
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
The paper presents RoboAbstention, a new benchmark showing frontier VLMs and embodied planners abstain on only 16.5-39% of 6,069 instructions grounded in robotics images, with prompting interventions raising rates to 88-93% but not solving the problem.
MI-CXR is a new benchmark that shows state-of-the-art vision-language models achieve only 29.3% accuracy on longitudinal reasoning tasks across multi-visit chest X-ray sequences.
A multi-view transformer predicts dense perspective fields that feed a geometric optimizer to estimate camera intrinsics and gravity from arbitrary numbers of real-world views.
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.
Hilbert-Geo creates the first unified formal language for solid geometry and a two-step parsing-then-reasoning method that reaches SOTA accuracy on solid geometry benchmarks.
M³Att poisons medical multimodal RAG by pairing covert textual misinformation with query-agnostic visual perturbations that increase retrieval of the bad content, causing LLMs to generate clinically plausible but incorrect responses.
DeepTumorVQA is a new stage-wise 3D CT VQA benchmark showing that quantitative measurement is the main failure point for current medical VLMs and that tool augmentation substantially improves later reasoning stages.
Flame3D enables zero-shot compositional 3D scene reasoning by representing scenes as editable visual-textual memories exposed to agentic MLLMs through composable and synthesizable spatial tools.
RuleSafe-VL creates 2,166 rule-conditioned cases from 93 atomic rules and 92 relations across three policy families to diagnose where VLMs fail at rule-based content moderation reasoning.
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.
EgoSound is a new benchmark with 7315 QA pairs across seven tasks to evaluate egocentric sound understanding in multimodal large language models.
VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.
Cornfigurator is the first automated deployment planner for generic any-to-any multimodal models that explores the full range of colocation-to-disaggregation strategies and delivers 1.12x to 6.32x higher goodput than existing systems or expert plans.
ToG-Bench is the first benchmark for task-oriented spatio-temporal video grounding in egocentric videos, with explicit-implicit dual grounding and one-to-many object scenarios across 100 ScanNet clips and 2704 instructions.
FLEX is the first large-scale multimodal multiview dataset for fitness AQA, featuring RGB, 3D pose, sEMG and physiological data plus a Fitness Knowledge Graph for structured annotations and a VideoQA benchmark.
Introduces VidPair-Halluc benchmark of 1K background-controlled adversarial video pairs and 11K QA pairs generated via PairFlow pipeline to evaluate hallucination in LVMs.
The paper proposes an operator-level visual-token skipping framework for MLLMs that reduces TFLOPs by 33.7% on Qwen3-VL while retaining 99.5% performance across VQA benchmarks.
Arena-T2I Hard benchmark with ~30 decomposed constraints per prompt and a dependency-aware checklist reward yields better faithfulness-aesthetics trade-off than single-reward or weighted-sum baselines on SD3.5-Medium and FLUX.1-dev.
VSE perturbs images only to probe visual ambiguity in VLMs, clusters outputs into semantic prototypes, and computes mass-weighted dispersion, outperforming prior entropy methods on five VQA benchmarks across five models.
MLLMs drop from over 85% accuracy on action presence to under 50% on matched action-denial videos, exposing a causal verification gap that causal graph prompts partially close.
OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
Small well-performing LVLMs gain the most from test-time scaling with up to 30% improvements that can match or exceed larger models, while visual information is used mainly early in reasoning chains.
OrthoTryOn uses Orthogonal Subspace Projection on shared LoRA and Fisher-guided Negative Guidance to enable conflict-free unified fashion generation, outperforming task-specific models on benchmarks.
citing papers explorer
-
Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances
AFFORDMEM improves AP50 by 3.23-3.7 points on SceneFun3D splits by using a reusable cross-scene affordance memory bank and in-scene spatial memory to guide VLMs toward actionable 3D regions.
-
Is Your Driving World Model an All-Around Player?
WorldLens benchmark reveals no driving world model dominates across visual, geometric, behavioral, and perceptual fidelity, with contributions of a 26K human-annotated dataset and a distilled vision-language evaluator.
-
ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
ViSRA boosts MLLM 3D spatial reasoning performance by up to 28.9% on unseen tasks via a plug-and-play video-based agent that extracts explicit spatial cues from expert models without any post-training.
-
Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
SAVEMem improves streaming video understanding scores by adding semantic awareness to memory compression and query-adaptive retrieval without any model training.
-
HP-Edit: A Human-Preference Post-Training Framework for Image Editing
HP-Edit introduces a post-training framework and RealPref-50K dataset that uses a VLM-based HP-Scorer to align diffusion image editing models with human preferences, improving outputs on Qwen-Image-Edit-2509.
-
mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval
mEOL creates aligned embeddings for text, images, and SVGs using instruction-guided MLLM one-word summaries and semantic SVG rewriting, outperforming baselines on a new text-to-SVG retrieval benchmark.
-
OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
-
RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs
RemoteAgent uses RL fine-tuning on VagueEO to align MLLMs for vague EO intent recognition, handling simple tasks internally and routing dense predictions to tools via Model Context Protocol.
-
RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation
A new benchmark dataset of 456 real rare-disease face images demonstrates that phenotype-aware synthetic augmentation with landmark filtering improves AI diagnostic accuracy by up to 13.7% in ultra-low-data regimes.
-
Token Warping Helps MLLMs Look from Nearby Viewpoints
Backward token warping in ViT-based MLLMs enables reliable reasoning from nearby viewpoints by preserving semantic coherence better than pixel-wise warping or fine-tuning baselines.
-
DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning
DocShield presents a new agentic reasoning framework using Cross-Cues-aware Chain of Thought to detect, localize, and explain text-centric forgeries in documents, with reported F1 gains of 41.4% over specialized methods and 23.4% over GPT-4o on T-IC13.
-
Video-R1: Reinforcing Video Reasoning in MLLMs
Video-R1 uses temporal-aware RL and mixed datasets to boost video reasoning in MLLMs, with a 7B model reaching 37.1% on VSI-Bench and surpassing GPT-4o.
-
Unified Reward Model for Multimodal Understanding and Generation
UnifiedReward is the first unified reward model that jointly assesses multimodal understanding and generation to provide better preference signals for aligning vision models via DPO.
-
SoccerMaster: A Vision Foundation Model for Soccer Understanding
SoccerMaster is the first soccer-specific vision foundation model that unifies tasks from player detection to event classification via multi-task pretraining and outperforms task-specific models on downstream evaluations.
-
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
Continued pre-training with balanced long-document VQA data extends a 7B LVLM to 128K context, improving long-document VQA by 7.1% and generalizing to 512K without further training.
-
Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
Proxy3D generates efficient 3D proxy representations via semantic clustering from video frames and aligns them to VLMs through multi-stage training on the new SpaceSpan dataset, achieving competitive performance on 3D VQA, grounding, and spatial benchmarks with shorter sequences.
-
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
-
DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation
A scalable training-free pipeline using video segmentation, filtering, and off-the-shelf multimodal models creates DenseStep2M, a dataset of 100K videos and 2M detailed instructional steps that improves dense captioning, step grounding, and cross-modal retrieval.
-
Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.
-
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
-
Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos
EgoIn uses a fine-tuned vision-language model to infer transition steps and a conditioning module plus auxiliary supervision to generate coherent egocentric video sequences of object state changes.
-
Visually-grounded Humanoid Agents
A coupled world-agent framework uses 3D Gaussian reconstruction and first-person RGB-D perception with iterative planning to enable goal-directed, collision-avoiding humanoid behavior in novel reconstructed scenes.
-
SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
SceneScribe-1M is a new dataset of 1 million videos with semantic text, camera parameters, dense depth, and consistent 3D point tracks to support monocular depth estimation, scene reconstruction, point tracking, and text-to-video synthesis.
-
VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
VideoStir introduces a spatio-temporal graph-based structure and intent-aware retrieval for long-video RAG, achieving competitive performance with SOTA methods via a new IR-600K dataset.
-
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
AutoVLA unifies semantic reasoning and trajectory planning in one autoregressive VLA model for end-to-end autonomous driving by tokenizing trajectories into discrete actions and using GRPO reinforcement fine-tuning to adaptively reduce unnecessary reasoning.
-
ImgEdit: A Unified Image Editing Dataset and Benchmark
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.
-
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
VBench-2.0 is a benchmark suite that automatically evaluates video generative models on five dimensions of intrinsic faithfulness: Human Fidelity, Controllability, Creativity, Physics, and Commonsense using VLMs, LLMs, and anomaly detection methods.
-
ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
A sandbox-trained multimodal search agent with process-oriented rewards transfers zero-shot to real Google Search and outperforms prior methods on FVQA, InfoSeek, and MMSearch.
-
SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing
SmartPhotoCrafter performs automatic photographic image editing by coupling an Image Critic module that identifies deficiencies with a Photographic Artist module that generates edits, trained via multi-stage pretraining, reasoning supervision, and reinforcement learning.
-
FineEdit: Fine-Grained Image Edit with Bounding Box Guidance
FineEdit adds multi-level bounding box injection to diffusion image editing, releases a 1.2M-pair dataset with box annotations, and shows better instruction following and background consistency than prior open models on new and existing benchmarks.
-
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
OmniJigsaw is a self-supervised proxy task that reconstructs shuffled audio-visual clips via joint integration, sample-level selection, and clip-level masking strategies, yielding gains on 15 video, audio, and reasoning benchmarks.
-
Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
Lightweight multimodal projector alignment transfers RGB VLMs to thermal drone imagery, achieving F1 scores of 0.915-0.968 for deer, rhino, and elephant recognition plus high enumeration accuracy and habitat context interpretation on a real drone dataset.
-
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.
-
Qwen-Image Technical Report
Qwen-Image is a foundation model that reaches state-of-the-art results in image generation and editing by combining a large-scale text-focused data pipeline with curriculum learning and dual semantic-reconstructive encoding for editing consistency.
-
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
UniWorld-V1 shows that semantic features from large multimodal models enable unified visual understanding and generation, achieving strong results on perception and manipulation tasks with only 2.7 million training samples.
-
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
-
Perceptual Flow Network for Visually Grounded Reasoning
PFlowNet decouples perception from reasoning, integrates multi-dimensional rewards with vicinal geometric shaping via variational RL, and reports new SOTA results on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).
-
simpleposter: a simple baseline for product poster generation
SimplePoster achieves 98.7% subject preservation and improved text accuracy in product posters via full-parameter fine-tuning of an inpainting model and zero-cost character-level position encoding, outperforming complex baselines like SeedEdit 3.0.
-
RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation
RCoT-Seg uses GRPO-reinforced keyframe selection from a CoT-start corpus followed by SAM2 mask propagation to improve video object segmentation under implicit temporal instructions over prior MLLM sampling methods.
-
Step1X-Edit: A Practical Framework for General Image Editing
Step1X-Edit integrates a multimodal LLM with a diffusion decoder, trained on a custom high-quality dataset, to deliver image editing performance that surpasses open-source baselines and approaches proprietary models on the new GEdit-Bench.