ViMU is the first benchmark for evaluating video models on metaphorical and subtextual understanding using hint-free questions grounded in multimodal evidence.
super hub Mixed citations
Qwen3-VL Technical Report
Mixed citation behavior. Most common role is background (47%).
826
Pith papers citing it
Background
47% 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 121
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
co-cited works
representative citing papers
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.
GUIGuard-Bench is a new benchmark with annotated GUI screenshots that measures privacy recognition, planning fidelity under protection, and utility impact for trajectory-based GUI agents.
Cultural commonsense in India is mostly regional, with only 39.4% agreement across five regions, and LLMs achieve just 13.4-20.9% accuracy while over-representing North and Central areas.
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.
S1-MMAlign is a new large-scale dataset of 15.5 million semantically enhanced scientific image-text pairs created via an AI recaptioning pipeline to improve multimodal understanding.
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.
GaussDet enables open-vocabulary and referring segmentation in 3D Gaussians by learning instance features and aggregating votes from 2D detectors, improving referential grounding by 16.7% mIoU in zero-shot setting.
Goku supplies a 2M-scale dataset, synthesis pipeline, decoupled dual-branch model, and 1000-case benchmark for multi-task instruction-based video editing, reporting up to 8% gains in instruction following.
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.
MuseBench shows state-of-the-art MLLMs achieve only 48.29% accuracy on intent-level audiovisual arts understanding versus 87.18% for human experts.
citing papers explorer
-
DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
RTR-DiT distills a bidirectional DiT teacher into an autoregressive few-step model using Self Forcing and Distribution Matching Distillation, plus a reference-preserving KV cache, to enable stable real-time text- and reference-guided video stylization.
-
Lyra 2.0: Explorable Generative 3D Worlds
Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
-
Boosting Visual Instruction Tuning with Self-Supervised Guidance
Mixing 3-10% of visually grounded self-supervised instructions into visual instruction tuning consistently boosts MLLM performance on vision-centric benchmarks.
-
Towards Long-horizon Agentic Multimodal Search
LMM-Searcher uses file-based visual UIDs and a fetch tool plus 12K synthesized trajectories to fine-tune a multimodal agent that scales to 100-turn horizons and reaches SOTA among open-source models on MM-BrowseComp and MMSearch-Plus.
-
MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games
MISID is a multimodal multi-turn dataset for intent recognition in strategic deception games, paired with the FRACTAM framework that improves MLLM performance on hidden intent detection via decouple-anchor-reason steps.
-
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
MemJack achieves 71.48% attack success rate on unmodified COCO val2017 images against Qwen3-VL-Plus by coordinating agents to map visual entities to malicious intents, apply multi-angle camouflage, and filter refusals via iterative nullspace projection while transferring strategies through a shared
-
Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models
Decoder-side Temporal Rebalancing (DTR) reduces hallucinations in Video-LLMs by mitigating over-dominance of a single anchor frame during inference without training or auxiliary models.
-
HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models
HTDC mitigates hallucinations in LVLMs by triggering calibration only at hesitation-prone decoding steps via contrasts with visual-nullification and semantic-nullification probes.
-
Narrative-Driven Paper-to-Slide Generation via ArcDeck
ArcDeck models paper-to-slide generation as narrative reconstruction using discourse parsing and multi-agent refinement, plus a new ArcBench benchmark, to improve flow and coherence over direct summarization.
-
CLASP: Closed-loop Asynchronous Spatial Perception for Open-vocabulary Desktop Object Grasping
CLASP achieves 87% success in open-vocabulary desktop grasping via dual-pathway perception, asynchronous closed-loop evaluation, and automated multimodal data synthesis.
-
rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training
rPPG-VQA filters in-the-wild videos using signal-level SNR consensus and scene-level MLLM interference detection, then applies two-stage adaptive sampling to produce unsupervised rPPG models with substantially higher benchmark accuracy.
-
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
-
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
TorchUMM is the first unified codebase and benchmark suite for multimodal understanding, generation, and editing across varied UMM models and datasets.
-
AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models
AITP is a new multimodal large language model that uses multimodal chain-of-thought and retrieval-augmented generation of legal knowledge to achieve state-of-the-art results on traffic accident responsibility allocation and related tasks, supported by the DecaTARA benchmark of 67,941 videos.
-
RIRF: Reasoning Image Restoration Framework
R&R couples structured diagnostic reasoning from a fine-tuned Qwen3-VL model with reinforcement learning guided by degradation severity to achieve state-of-the-art universal image restoration with added interpretability.
-
Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation
Personalized soft prompts steer VLM attention to match user-specific gaze patterns, yielding better attention alignment and click prediction in recommendation simulations.
-
FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding
FashionStylist is an expert-annotated benchmark dataset that unifies outfit-to-item grounding, completion, and evaluation tasks for multimodal large language models in fashion.
-
CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation
CORA applies conformal risk control to calibrate safe versus abstained actions for GUI agents, adds a Diagnostician for rejected steps, and introduces the Phone-Harm benchmark to improve the safety-helpfulness trade-off.
-
UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding
UniversalVTG is a lightweight foundation model for video temporal grounding that achieves state-of-the-art results across five benchmarks while being over 100 times smaller than recent MLLM-based methods.
-
What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metric
A semantic scanpath similarity method using VLMs to encode fixations as text and NLP metrics to compare content agreement independent of spatial alignment.
-
Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models
Orion-Lite uses latent feature distillation and trajectory supervision to create a vision-only model that surpasses its LLM-based teacher on closed-loop Bench2Drive evaluation, achieving a new SOTA driving score of 80.6.
-
Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
BAIM enriches knowledge tracing item representations by deriving stage-level embeddings from Polya's four problem-solving stages and routing them adaptively per learner context, yielding consistent gains over pretraining baselines on two datasets.
-
Small Vision-Language Models are Smart Compressors for Long Video Understanding
Tempo uses a 6B SVLM as a local temporal compressor with training-free adaptive token allocation to achieve SOTA long-video understanding at 0.5-16 tokens per frame, scoring 52.3 on 4101s LVBench under 8K budget.
-
HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
HEX introduces a state-centric framework with humanoid-aligned representations and mixture-of-experts proprioceptive prediction for coordinated whole-body control on bipedal humanoids.
-
AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning
AnomalyAgent uses tool-augmented reinforcement learning with self-reflection to generate realistic industrial anomalies, achieving better metrics than zero-shot methods on MVTec-AD.
-
Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
Semantic-level UI Element Injection distracts GUI agents by overlaying safety-aligned UI elements, achieving up to 4.4x higher attack success rates that transfer across models and create persistent attractors.
-
LPM 1.0: Video-based Character Performance Model
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
-
Towards Knowledgeable Deep Research: Framework and Benchmark
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
-
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
GameWorld is a new benchmark providing standardized interfaces, 34 games, 170 tasks, and verifiable outcome metrics to evaluate multimodal large language model agents in video game environments.
-
LungCURE: Benchmarking Multimodal Real-World Clinical Reasoning for Precision Lung Cancer Diagnosis and Treatment
LungCURE is the first standardized multimodal benchmark of 1,000 real-world lung cancer cases for TNM staging, treatment recommendation, and end-to-end decisions, paired with the LCAgent multi-agent framework that improves LLM guideline compliance.
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
SciTikZer-8B uses a new dataset, benchmark, and dual self-consistency RL to generate TikZ code for scientific graphics, outperforming much larger models like Gemini-2.5-Pro.
-
CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference
CodecSight reuses video codec signals for online patch pruning before the vision transformer and selective KV-cache refresh in the LLM, delivering up to 3x higher throughput and 87% lower GPU compute than prior baselines with 0-8% F1 drop.
-
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
WikiSeeker boosts KB-VQA performance by using VLMs to rewrite image-informed queries for better retrieval and to decide when to route to external LLM or rely on internal VLM knowledge.
-
Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs
GUIDE unrolls multi-granularity geometric priors layer-wise into early MLLM layers with gating to improve spatial reasoning and perception.
-
PanopticQuery: Unified Query-Time Reasoning for 4D Scenes
PanopticQuery lifts 2D semantic predictions into globally consistent 4D groundings via neural field optimization and sets new state-of-the-art results on complex language queries for attributes, actions, and interactions.
-
Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
DAERT generates diverse adversarial instructions via a uniform policy in RL to drop VLA task success rates from 93.33% to 5.85% on benchmarks with models like π0 and OpenVLA.
-
EchoAgent: Towards Reliable Echocardiography Interpretation with "Eyes","Hands" and "Minds"
EchoAgent is a new agentic AI system that integrates visual observation, quantitative measurement, and expert knowledge reasoning to achieve reliable echocardiography interpretation with up to 80% accuracy on CAMUS and MIMIC-EchoQA datasets.
-
RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains
RoboPlayground reframes robotic manipulation evaluation as a language-driven process over structured physical domains, letting users author varied yet reproducible tasks that reveal policy generalization failures.
-
Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D
BoxerNet lifts 2D bounding boxes to metric 3D boxes via transformer regression with aleatoric uncertainty and median depth encoding, then fuses multi-view results to outperform CuTR by large margins on open-world benchmarks.
-
MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
-
GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
GLANCE introduces a bi-loop multi-agent framework with global-local coordination mechanisms that outperforms baselines by up to 33% on music-grounded nonlinear video editing tasks using a new MVEBench benchmark.
-
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Video-MME-v2 is a new benchmark that applies progressive visual-to-reasoning levels and non-linear group scoring to expose gaps in video MLLM capabilities.
-
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.
-
Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning
G2F-RAG converts retrieved knowledge subgraphs into a single visual reasoning frame appended to videos, enabling training-free and interpretable improvements for LMM-based video reasoning on knowledge-intensive tasks.
-
Learning Robust Visual Features in Computed Tomography Enables Efficient Transfer Learning for Clinical Tasks
VoxelFM learns robust 3D CT visual features via DINO self-distillation that transfer effectively to seven clinical task categories using frozen backbones and lightweight heads, outperforming prior CT foundation models even on report generation.
-
FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation
FSUNav's dual brain-inspired modules achieve state-of-the-art zero-shot goal navigation across heterogeneous robots with improved speed, safety, and generalization.
-
STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models
STEAR reduces spatial and temporal hallucinations in Video-LLMs via layer-aware evidence intervention from middle decoder layers in a single-encode pass.
-
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
CharTool equips MLLMs with cropping and code tools plus agentic RL on DuoChart data to raise chart-reasoning accuracy by up to 9.78 percent on benchmarks.
-
LumiVideo: An Intelligent Agentic System for Video Color Grading
LumiVideo deploys an LLM-based agent with RAG and Tree of Thoughts to generate ASC-CDL parameters and 3D LUTs for automatic cinematic color grading from raw log video, approaching expert quality.