OVOW reconstructs instance-level, simulation-ready 4D mesh scenes from monocular video via a four-stage training-free pipeline and introduces a new benchmark for structured Video-to-4D evaluation.
mega hub Mixed citations
Qwen3-VL Technical Report
Mixed citation behavior. Most common role is background (48%).
1153
Pith papers citing it
Background
48% of classified citations
abstract
We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows.
hub tools
citation-role summary
background 122
method 61
baseline 50
dataset 5
other 4
citation-polarity summary
claims ledger
- abstract We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-con
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
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.
DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
Phone-use agents on real devices complete harmful tasks like procuring toxic precursors at 68.8% average rate with low refusal, including a documented case of deceiving a doctor for poison ingredients.
Introduces the first large-scale multimodal benchmark MedLayXPlain-122K showing medical VLMs suffer significant lay-register degradation while general VLMs lack clinical precision.
LOCUS is a released corpus of nearly all US municipal and county ordinance codes, processed via OCR and paired with ModernBERT classifiers for dimensions such as opacity and paternalism.
A causal audit with image interventions shows text-only models reach within 5.7 accuracy points of top multimodal VLMs on chest radiography, with some large multimodal models statistically indistinguishable from small text-only baselines.
RobotValues is a benchmark of 10K value-conflict scenarios that reveals VLMs default to safety and accommodation while failing to follow instructions to prioritize other values 80% of the time.
FigSIM is the first annotated dataset for fine-grained suicide severity and figurative language in suicide memes, accompanied by benchmarks on 16 unimodal and multimodal models.
ViMU is the first benchmark for evaluating video models on metaphorical and subtextual understanding using hint-free questions grounded in multimodal evidence.
CiteVQA requires models to cite specific document regions with bounding boxes alongside answers and finds that even the strongest MLLMs frequently cite the wrong region, with top SAA scores of only 76.0 for closed models and 22.5 for open-source ones.
SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
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.
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
PureDocBench shows document parsing is far from solved, with top models at ~74/100, small specialists competing with large VLMs, and ranking reversals under real degradation.
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.
WindowsWorld benchmark shows leading GUI agents achieve under 21% success on multi-application professional tasks, with failures especially on conditional judgment across three or more apps and inefficient execution.
MM-JudgeBench shows substantial cross-lingual performance variance in 22 LVLM judges, with model size and architecture as poor predictors of multilingual robustness.
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
VLMs hallucinate by prioritizing contradictory on-screen text over visual content, addressed via the VisualTextTrap benchmark with 6,057 human-validated samples and the VTHM-MoE dual-encoder framework using dimension-specific experts and adaptive routing.
RefereeBench shows that even the strongest video MLLMs reach only around 60% accuracy on multi-sport refereeing tasks and struggle with rule application and temporal grounding.
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.
ScreenParse dataset and ScreenVLM model deliver dense screen parsing that outperforms larger VLMs on PageIoU and transfers to better UI grounding.
citing papers explorer
-
DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing
DIRECT uses a three-level multi-agent framework to solve video mashup creation as a multimodal coherency problem, outperforming baselines on a new benchmark.
-
BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing
BoxComm is the first large-scale benchmark for category-aware commentary generation and rhythm assessment in boxing, showing state-of-the-art multimodal models struggle with tactical analysis and temporal pacing.
-
PortraitCraft: A Benchmark for Portrait Composition Understanding and Generation
PortraitCraft supplies a new 50k-image dataset and two tasks for evaluating AI on fine-grained portrait composition understanding and constrained generation.
-
XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis
XrayClaw deploys cooperative-competitive multi-agent alignment and Competitive Preference Optimization to raise diagnostic accuracy, reasoning fidelity, and generalization on chest X-ray benchmarks.
-
Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models
Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.
-
V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators
V-Reflection introduces a think-then-look mechanism where MLLM latent states actively interrogate visual features via two-stage distillation from a box-guided teacher to a dynamic autoregressive student, narrowing the fine-grained perception gap on benchmarks.
-
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Gen-Searcher is the first trained search-augmented image generation agent using SFT followed by GRPO reinforcement learning with dual text-image rewards, delivering 15-16 point gains on knowledge-intensive benchmarks.
-
RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation
RailVQA-bench supplies 21,168 QA pairs for ATO visual cognition while RailVQA-CoM combines large-model reasoning with small-model efficiency via transparent modules and temporal sampling.
-
LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset
KITScenes LongTail supplies multimodal driving data and multilingual expert reasoning traces to benchmark models on rare scenarios beyond basic safety metrics.
-
When Negation Is a Geometry Problem in Vision-Language Models
A direction associated with negation exists in CLIP embedding space and can be steered at test time via representation engineering to produce negation-aware outputs without fine-tuning.
-
Visual-ERM: Reward Modeling for Visual Equivalence
Visual-ERM is a new multimodal reward model that supplies fine-grained visual feedback for training vision-language models on chart-to-code, table, and SVG tasks, yielding measurable gains over prior rewards.
-
Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence
VAEX-BENCH shows state-of-the-art MLLMs perform substantially worse on abstractive spatiotemporal reasoning tasks than on matched extractive tasks in video understanding.
-
SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents
SPIRAL is a closed-loop think-act-reflect framework using PlanAgent, VideoGenerator, and CriticAgent plus GRPO self-evolution to improve long-horizon action-conditioned video generation, with new dataset and benchmark showing gains over open-loop baselines.
-
Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
DiNa-LRM introduces a diffusion-native latent reward model using a noise-calibrated Thurstone likelihood on noisy states, matching VLM performance at lower compute in image alignment and preference optimization.
-
Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
Visual Para-Thinker is the first parallel reasoning framework for MLLMs that uses visual partitioning strategies, Pa-Attention, and LPRoPE to extend test-time scaling benefits to visual comprehension tasks.
-
CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
-
VPTracker: Global Vision-Language Tracking via Visual Prompt
VPTracker enables global object tracking in videos by using multimodal large language models with location-aware visual prompts to search entire images while reducing distractions from similar objects.
-
SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence
Presents SpatialScore benchmark for MLLM spatial reasoning, evaluates 49 models showing large human gap, and supplies SpatialCorpus plus SpatialAgent to improve performance.
-
PubMed-Ophtha: An open resource for training ophthalmology vision-language models on scientific literature
PubMed-Ophtha is a new hierarchical dataset of 102k ophthalmological image-caption pairs from 15k+ PubMed articles, with full-resolution PDF extraction, panel splitting, modality annotations, and released extraction models plus pipeline.
-
Retrieving Any Relevant Moments: Benchmark and Models for Generalized Moment Retrieval
Generalized Moment Retrieval (GMR) is introduced as a unified task with the Soccer-GMR benchmark and adapter models that retrieve multiple or zero matching moments from videos.
-
Act2See: Emergent Active Visual Perception for Video Reasoning
Act2See trains VLMs via supervised fine-tuning on verified reasoning traces to interleave active frame calls within text CoTs, yielding SOTA results on video reasoning benchmarks.
-
Towards Robustness against Typographic Attack with Training-free Concept Localization
Training-free mechanistic interpretability locates lexical-encoding attention heads in ViT and shows that targeted interventions on them improve robustness to typographic attacks in CLIP and downstream LVLMs.
-
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
Formalizes Fashion Detail Generation task, releases FDBench benchmark with 40K+ pairs, and proposes CFAD distillation method plus RL consistency reward that outperforms open-source baselines.
-
MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding
MedStreamBench integrates 22 medical datasets into 5,419 QA instances across retrospective, present, future, and proactive temporal settings to evaluate streaming and proactive medical video understanding.
-
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.
-
GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
GeoSearcher introduces anchor-centric reasoning supervised fine-tuning and process-faithful group relative policy optimization to improve MLLM-based remote sensing visual grounding.
-
GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images
GMO-E²DIT is an agentic editing framework that decouples VLM-based planning from mask-conditioned rendering and uses reflection to execute multi-operation e-commerce image edits with error recovery.
-
Caption Bottleneck Models
Caption Bottleneck Models use LMM-generated image captions as the sole input to a text classifier, creating leakage-free interpretable models that discover dataset-specific concepts without predefined lists or manual labels.
-
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
StochasT uses stochastic clustering of language tasks into varying turn depths for the same image to improve LVLMs on both single-turn and multi-turn scenarios without discarding data.
-
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
VideoSearch-R1 achieves SOTA on VCMR across three datasets via iterative retrieval, latent-space soft query refinement, and GRPO training.
-
Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models
IPLoc-ID extends prior localization-only work to full identification and localization by using a self-posed query in VLMs to reject negative images while preserving comparable localization accuracy.
-
Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners
DeCoDe decomposes few-shot classification into binary pairwise image comparisons whose affirmative logits serve as similarity scores, enabling strong performance from unmodified MLLMs on twelve datasets.
-
PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking
PixelEyes decouples reasoning and perception via mask-guided search and semantic BFS, introduces PixelEyes-6K dataset and Pinpoint-Bench benchmark, and open-sources code and models.
-
Automated Background Swapping for Robustness against Spurious Backgrounds
AutoBackSwap uses foreground-background disentanglement via a secondary network plus background infilling to augment training data and reduce spurious background correlations in image classifiers, outperforming priors even without any counterexamples in the data.
-
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
CoLT replaces text-based chain-of-thought in MLLMs with 3-step latent thought chains supervised by a removable external decoder in forward and backward modes, yielding 10.1x faster inference on eight benchmarks.
-
What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States
Introduces Active Task Driving Memory (ATMem) and STR-GRPO to move GUI agents from passive record storage to actively maintained task states, tested on a new mobile benchmark with progress and scope-aware metrics.
-
Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning
ViToS uses dual-stream RL with cross-feedback optimization to prune medical image tokens to 77% length while reporting 108.27% and 104.16% relative performance on two 7B VLMs across seven benchmarks.
-
AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neuroscience
SatAgent is a UAV-satellite collaborative spatial reasoning model using geometric 3D encoding, multi-view alignment, and a new 130K dataset that reports 25.91% and 11.69% gains over general and specialized baselines.
-
Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models
Lens purifies visual evidence in MLLMs via question-conditioned latent noise masking with a LET token, yielding 2.4-6.4 point gains on VQA and grounding tasks.
-
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
Introduces SciIR-82k dataset and SciIR-Bench for scientific image reasoning generation organized by Peirce's semiotic triad, with fine-tuning raising model score from 35% to 43%.
-
One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding
InnerZoom bridges cross-layer evidence in one forward pass to achieve SOTA GUI grounding accuracy on six benchmarks while cutting latency up to 31.8% versus two-pass baselines.
-
Emergence of a Shared Canonical Object Frame from In-the-Wild Videos
A coarse canonical mesh bottleneck plus multi-view consistency lets a shared object frame emerge from self-supervised training on in-the-wild videos without canonical labels or category conditioning.
-
StrucTab: A Structured Optimization Framework for Table Parsing
StrucTab achieves SOTA table parsing performance by unifying structural subtasks through sequential reasoning and using decomposed RL rewards in Uni-TabRL, plus a new TableVerse-5K benchmark.
-
Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
A masked discrete diffusion model adds token editing at inference and grouped cross-entropy training to reach 0.90 GenEval, 86.9 DPG, and 10.76 HPSv3 scores.
-
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
OPPO is an evidence-aware preference optimization objective that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.
-
MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment
MR-IQA unifies regression and ranking in BIQA via a quality-margin optimization framework in RL, showing competitive performance on six benchmarks.
-
MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
MotionAtlas supplies a 2,073-question benchmark, a self-bootstrap pipeline yielding 159k captions, and fine-tuned Video-MLLMs that deliver 5.2-point gains over Qwen3-VL-4B on motion tasks.
-
The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training
Introduces an attack-agnostic black-box defense for SSL encoders that trains a conditional energy function via NCE and DSM to detect and purify representations, with an energy gap lower-bounded by mutual information.
-
HKVLM: Faithful Reasoning Grounding by Binding Language Queries to a Frozen Detector
HKVLM trains only an alignment hook to bind frozen LM query embeddings to frozen detector proposals via contrastive retrieval and bipartite assignment, yielding 50-90x grounding gains and reduced hallucinations on RefCOCO and POPE.
-
Detecting Clinical Hallucinations in LVLMs via Counterfactual Visual Grounding Uncertainty
A counterfactual visual grounding uncertainty method detects hallucinations in LVLMs on medical images, improving over baselines with interpretable evidence and cross-model transfer.