Latest 15 Papers - June 02, 2026

**Please check the [Github](https://github.com/zezhishao/MTS_Daily_ArXiv) page for a better reading experience and more papers.**

## Unified
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning](https://arxiv.org/abs/2507.08064v3)** | 2026-06-01 | |
| **[Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models](https://arxiv.org/abs/2606.02374v1)** | 2026-06-01 | |
| **[Unified Context Evolution for LLM Agents](https://arxiv.org/abs/2606.02304v1)** | 2026-06-01 | |
| **[CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation](https://arxiv.org/abs/2606.02287v1)** | 2026-06-01 | |
| **[Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments](https://arxiv.org/abs/2605.30280v2)** | 2026-06-01 | 34 pages |
| **[Unified Semantic Transformer for 3D Scene Understanding](https://arxiv.org/abs/2512.14364v3)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted at TMLR. Project page: https://unite-page.github.io/</details> |
| **[A Unified Framework for Structured Flow Modeling: From Continuous Fields to Data-Driven Representations](https://arxiv.org/abs/2605.18250v2)** | 2026-06-01 | |
| **[A Unified E2E Energy Efficiency Testing Framework for Open RAN](https://arxiv.org/abs/2606.01931v1)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted for publication in IEEE Communications Standards Magazine</details> |
| **[Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits](https://arxiv.org/abs/2606.01799v1)** | 2026-06-01 | |
| **[TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control](https://arxiv.org/abs/2604.17456v2)** | 2026-06-01 | |
| **[A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback](https://arxiv.org/abs/2606.01729v1)** | 2026-06-01 | |
| **[UniVocal: Unified Speech-Singing Code-Switching Synthesis](https://arxiv.org/abs/2606.01677v1)** | 2026-06-01 | accepted by ACL 2026 |
| **[UniNote: A Unified Embedding Model for Multimodal Representation and Ranking](https://arxiv.org/abs/2605.29287v2)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted by KDD Ads Track 2026</details> |
| **[A Unified Evaluation-Instructed Framework for Query-Dependent Prompt Optimization](https://arxiv.org/abs/2511.19829v2)** | 2026-06-01 | |
| **[A Unified Framework for Adversary-Aware Differential Privacy Bounds](https://arxiv.org/abs/2507.08158v2)** | 2026-06-01 | |

## Video Understanding
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events](https://arxiv.org/abs/2606.02522v1)** | 2026-06-01 | <details><summary>28 pa...</summary>28 pages, 10 figures, 11 tables</details> |
| **[Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection](https://arxiv.org/abs/2606.02352v1)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted at the IEEE ITSC 2026</details> |
| **[InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models](https://arxiv.org/abs/2606.02161v1)** | 2026-06-01 | 15 pages, 8 figures |
| **[v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound](https://arxiv.org/abs/2509.25773v3)** | 2026-06-01 | 24 pages, 9 figures |
| **[Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection](https://arxiv.org/abs/2606.02120v1)** | 2026-06-01 | |
| **[3rd Place at CVPR 2026 CASTLE Challenge: Agentic Multi-View Long-Context Video Understanding via Hierarchical Knowledge Graph Retrieval](https://arxiv.org/abs/2606.01933v1)** | 2026-06-01 | |
| **[Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey](https://arxiv.org/abs/2604.11283v2)** | 2026-06-01 | |
| **[An Efficient Streaming Video Understanding Framework with Agentic Control](https://arxiv.org/abs/2605.17921v2)** | 2026-06-01 | |
| **[EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models](https://arxiv.org/abs/2606.01756v1)** | 2026-06-01 | <details><summary>Prepr...</summary>Preprint. 12 pages, 6 figures, 7 tables</details> |
| **[APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention](https://arxiv.org/abs/2601.21444v2)** | 2026-06-01 | ACL 2026 main |
| **[VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding](https://arxiv.org/abs/2602.04094v2)** | 2026-05-31 | |
| **[V-LynX: Token Interface Alignment for Video+X LLMs](https://arxiv.org/abs/2606.00508v1)** | 2026-05-30 | <details><summary>ICML ...</summary>ICML 2026 Camera-ready</details> |
| **[Towards Sparse Video Understanding and Reasoning](https://arxiv.org/abs/2602.13602v2)** | 2026-05-30 | <details><summary>Accep...</summary>Accepted to CVPR 2026. Project page: https://sparsevideounderstanding.github.io</details> |
| **[Linear Scaling Video VLMs for Long Video Understanding](https://arxiv.org/abs/2605.31598v1)** | 2026-05-29 | |
| **[Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding](https://arxiv.org/abs/2508.20478v2)** | 2026-05-29 | <details><summary>Accep...</summary>Accepted by ICML 2026. Camera-ready version</details> |

## World Model
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[RoboDream: Compositional World Models for Scalable Robot Data Synthesis](https://arxiv.org/abs/2606.02577v1)** | 2026-06-01 | <details><summary>Proje...</summary>Project page: https://junjieye.com/RoboDream/</details> |
| **[From Zero to Hero: Training-Free Custom Concept Spawning in World Models](https://arxiv.org/abs/2606.02575v1)** | 2026-06-01 | |
| **[WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World](https://arxiv.org/abs/2512.10958v2)** | 2026-06-01 | <details><summary>CVPR ...</summary>CVPR 2026 Oral Presentation; 80 pages, 37 figures, 29 tables; Project Page at https://worldbench.github.io/worldlens GitHub at https://github.com/worldbench/WorldLens</details> |
| **[Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation](https://arxiv.org/abs/2606.02486v1)** | 2026-06-01 | <details><summary>28 pa...</summary>28 pages, 7 figures, 16 tables, Su</details> |
| **[Geometry-Aware Implicit Memory for Video World Models](https://arxiv.org/abs/2606.02436v1)** | 2026-06-01 | <details><summary>Proje...</summary>Project page: https://gim-world.github.io/</details> |
| **[Policy and World Modeling Co-Training for Language Agents](https://arxiv.org/abs/2606.02388v1)** | 2026-06-01 | 9 pages, 6 figures |
| **[TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks](https://arxiv.org/abs/2606.02384v1)** | 2026-06-01 | |
| **[COMAP: Co-Evolving World Models and Agent Policies for LLM Agents](https://arxiv.org/abs/2606.02372v1)** | 2026-06-01 | |
| **[Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation](https://arxiv.org/abs/2605.15141v3)** | 2026-06-01 | |
| **[World-Task Factorization for Robot Learning](https://arxiv.org/abs/2606.02027v1)** | 2026-06-01 | |
| **[Scaling Agentic Capabilities via Grounded Interaction Synthesis](https://arxiv.org/abs/2606.02001v1)** | 2026-06-01 | |
| **[SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning](https://arxiv.org/abs/2606.01991v1)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), Main Conference</details> |
| **[Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects](https://arxiv.org/abs/2606.01950v1)** | 2026-06-01 | |
| **[Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning](https://arxiv.org/abs/2606.01935v1)** | 2026-06-01 | |
| **[WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching](https://arxiv.org/abs/2603.06331v2)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted by ICML 2026</details> |

## Multimodal
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling](https://arxiv.org/abs/2606.02578v1)** | 2026-06-01 | ICML 2026 |
| **[ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning](https://arxiv.org/abs/2606.02576v1)** | 2026-06-01 | |
| **[Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design](https://arxiv.org/abs/2606.02507v1)** | 2026-06-01 | |
| **[CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning](https://arxiv.org/abs/2606.02502v1)** | 2026-06-01 | |
| **[Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation](https://arxiv.org/abs/2510.24870v2)** | 2026-06-01 | <details><summary>https...</summary>https://github.com/alexmartin1722/mirage</details> |
| **[PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning](https://arxiv.org/abs/2507.08064v3)** | 2026-06-01 | |
| **[Attention Dynamics and Adaptive Decision Support in C5ISR: A Recurrence Quantification Analysis of Visual and Multimodal Attention Guidance Effects on Mission Performance](https://arxiv.org/abs/2606.02382v1)** | 2026-06-01 | 11 Figures, 3 Tables |
| **[Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains](https://arxiv.org/abs/2606.02357v1)** | 2026-06-01 | |
| **[WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata](https://arxiv.org/abs/2602.12819v2)** | 2026-06-01 | <details><summary>Softw...</summary>Software: https://www.robots.ox.ac.uk/~vgg/software/wise/ , Online demos: https://www.robots.ox.ac.uk/~vgg/software/wise/demo/ , Example Queries: https://www.robots.ox.ac.uk/~vgg/software/wise/examples/</details> |
| **[Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality](https://arxiv.org/abs/2603.01471v2)** | 2026-06-01 | |
| **[Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics](https://arxiv.org/abs/2601.04946v3)** | 2026-06-01 | |
| **[Context-Aware Workflow Decomposition for Automated Mobile UI Annotation Using Multimodal Large Language Models](https://arxiv.org/abs/2606.02208v1)** | 2026-06-01 | |
| **[Multimodal Approaches for Visually-Rich Document Type Classification: A Comparative Analysis](https://arxiv.org/abs/2606.02162v1)** | 2026-06-01 | |
| **[Jailbreaking Multimodal Large Language Models using Multi-Clip Video](https://arxiv.org/abs/2606.02111v1)** | 2026-06-01 | <details><summary>27 pa...</summary>27 pages, 20 figures, Accepted to the Main Conference of ACL 2026</details> |
| **[MMSkills: Towards Multimodal Skills for General Visual Agents](https://arxiv.org/abs/2605.13527v3)** | 2026-06-01 | <details><summary>25 pa...</summary>25 pages, 8 figures, 8 tables. Project page: https://zkangning.github.io/MMSkills_for_Visual_Agents/</details> |

## Multimodal LLM
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling](https://arxiv.org/abs/2606.02578v1)** | 2026-06-01 | ICML 2026 |
| **[DenseMLLM: Standard Multimodal LLMs for Dense Prediction](https://arxiv.org/abs/2602.14134v2)** | 2026-06-01 | ICML 2026 |
| **[Enhancing the Socioeconomic Understanding of Foundation Models with Urban Mobility](https://arxiv.org/abs/2606.01745v1)** | 2026-06-01 | |
| **[Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference](https://arxiv.org/abs/2606.01711v1)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted to ICML 2026</details> |
| **[Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval](https://arxiv.org/abs/2604.18360v2)** | 2026-06-01 | <details><summary>Accep...</summary>Accepted at ACL 2026 Main Conference. Camera-ready version</details> |
| **[Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim Verification](https://arxiv.org/abs/2606.01679v1)** | 2026-06-01 | |
| **[FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning](https://arxiv.org/abs/2604.03893v2)** | 2026-06-01 | 9 pages, 5 figures |
| **[AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection](https://arxiv.org/abs/2602.08868v2)** | 2026-05-31 | ICML 2026 |
| **[Sandboxed Coding Agents are Competitive Omni-modal Task Solvers](https://arxiv.org/abs/2606.00579v1)** | 2026-05-30 | Paper under review |
| **[Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs](https://arxiv.org/abs/2603.09095v3)** | 2026-05-30 | |
| **[LLMs Need Encoders for Semantic IDs Too](https://arxiv.org/abs/2606.00324v1)** | 2026-05-29 | |
| **[The Regularizing Power of Language-Training Deepfake Detectors](https://arxiv.org/abs/2605.31192v1)** | 2026-05-29 | |
| **[BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs](https://arxiv.org/abs/2605.30900v1)** | 2026-05-29 | |
| **[Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages](https://arxiv.org/abs/2606.00154v1)** | 2026-05-29 | |
| **[MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding](https://arxiv.org/abs/2605.30794v1)** | 2026-05-29 | accept by iclm2026 |

## Video Foundation Model
| **Title** | **Date** | **Comment** |
| --- | --- | --- |
| **[WALL-WM: Carving World Action Modeling at the Event Joints](https://arxiv.org/abs/2606.01955v1)** | 2026-06-01 | |
| **[AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance](https://arxiv.org/abs/2606.01362v1)** | 2026-05-31 | |
| **[GeoSAM-3D: Geodesic Prompt Propagation for Open-Vocabulary 3D Scene Segmentation from Monocular Video](https://arxiv.org/abs/2606.00447v1)** | 2026-05-30 | |
| **[minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models](https://arxiv.org/abs/2605.30263v1)** | 2026-05-28 | |
| **[PlayClass: Automated Play Behaviour Classification in Poultry](https://arxiv.org/abs/2605.27304v1)** | 2026-05-26 | <details><summary>Accep...</summary>Accepted at CV4Animals Workshop @ CVPR 2026</details> |
| **[World-R1: Reinforcing 3D Constraints for Text-to-Video Generation](https://arxiv.org/abs/2604.24764v4)** | 2026-05-26 | <details><summary>ICML ...</summary>ICML 2026, Project Page: https://aka.ms/world-r1, Code: https://github.com/microsoft/World-R1</details> |
| **[EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation](https://arxiv.org/abs/2605.23271v1)** | 2026-05-22 | |
| **[Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models](https://arxiv.org/abs/2605.19137v1)** | 2026-05-18 | <details><summary>Accep...</summary>Accepted to CVPR 2026 Workshops CV4Smalls</details> |
| **[Latent Video Prediction Learns Better World Models](https://arxiv.org/abs/2605.15618v1)** | 2026-05-15 | |
| **[DriveCtrl: Conditioned Sim-to-Real Driving Video Generation](https://arxiv.org/abs/2605.15116v1)** | 2026-05-14 | |
| **[Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception](https://arxiv.org/abs/2510.01502v2)** | 2026-05-12 | <details><summary>v2: M...</summary>v2: Major revision. Retitled; expanded from TimeSformer alone to four backbones (V-JEPA 2/2.1, TimeSformer, VideoMAE, CLIP), with V-JEPA 2.1 nearly tripling pretrained performance. Adds zero-shot PHASE transfer, attention-rollout analysis, and a language-distillation control. Data (OOO sim. judgments) & core hybrid triplet+RSA LoRA method unchanged from v1. Prepared for NeurIPS 2026 submission</details> |
| **[MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation](https://arxiv.org/abs/2604.23789v2)** | 2026-05-09 | 17 pages, 9 figues |
| **[Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios](https://arxiv.org/abs/2605.06185v1)** | 2026-05-07 | |
| **[UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models](https://arxiv.org/abs/2602.19202v2)** | 2026-05-07 | |
| **[Prompt-to-Gesture: Measuring the Capabilities of Image-to-Video Deictic Gesture Generation](https://arxiv.org/abs/2604.14953v1)** | 2026-04-16 | <details><summary>Accep...</summary>Accepted at 2026 International Conference on Automatic Face and Gesture Recognition (FG)</details> |

Title	Date	Comment
PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning	2026-06-01
Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models	2026-06-01
Unified Context Evolution for LLM Agents	2026-06-01
CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation	2026-06-01
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments	2026-06-01	34 pages
Unified Semantic Transformer for 3D Scene Understanding	2026-06-01	Accep... Accepted at TMLR. Project page: https://unite-page.github.io/
A Unified Framework for Structured Flow Modeling: From Continuous Fields to Data-Driven Representations	2026-06-01
A Unified E2E Energy Efficiency Testing Framework for Open RAN	2026-06-01	Accep... Accepted for publication in IEEE Communications Standards Magazine
Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits	2026-06-01
TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control	2026-06-01
A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback	2026-06-01
UniVocal: Unified Speech-Singing Code-Switching Synthesis	2026-06-01	accepted by ACL 2026
UniNote: A Unified Embedding Model for Multimodal Representation and Ranking	2026-06-01	Accep... Accepted by KDD Ads Track 2026
A Unified Evaluation-Instructed Framework for Query-Dependent Prompt Optimization	2026-06-01
A Unified Framework for Adversary-Aware Differential Privacy Bounds	2026-06-01

Title	Date	Comment
Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events	2026-06-01	28 pa... 28 pages, 10 figures, 11 tables
Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection	2026-06-01	Accep... Accepted at the IEEE ITSC 2026
InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models	2026-06-01	15 pages, 8 figures
v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound	2026-06-01	24 pages, 9 figures
Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection	2026-06-01
3rd Place at CVPR 2026 CASTLE Challenge: Agentic Multi-View Long-Context Video Understanding via Hierarchical Knowledge Graph Retrieval	2026-06-01
Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey	2026-06-01
An Efficient Streaming Video Understanding Framework with Agentic Control	2026-06-01
EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models	2026-06-01	Prepr... Preprint. 12 pages, 6 figures, 7 tables
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention	2026-06-01	ACL 2026 main
VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding	2026-05-31
V-LynX: Token Interface Alignment for Video+X LLMs	2026-05-30	ICML ... ICML 2026 Camera-ready
Towards Sparse Video Understanding and Reasoning	2026-05-30	Accep... Accepted to CVPR 2026. Project page: https://sparsevideounderstanding.github.io
Linear Scaling Video VLMs for Long Video Understanding	2026-05-29
Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding	2026-05-29	Accep... Accepted by ICML 2026. Camera-ready version

Title	Date	Comment
RoboDream: Compositional World Models for Scalable Robot Data Synthesis	2026-06-01	Proje... Project page: https://junjieye.com/RoboDream/
From Zero to Hero: Training-Free Custom Concept Spawning in World Models	2026-06-01
WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World	2026-06-01	CVPR ... CVPR 2026 Oral Presentation; 80 pages, 37 figures, 29 tables; Project Page at https://worldbench.github.io/worldlens GitHub at https://github.com/worldbench/WorldLens
Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation	2026-06-01	28 pa... 28 pages, 7 figures, 16 tables, Su
Geometry-Aware Implicit Memory for Video World Models	2026-06-01	Proje... Project page: https://gim-world.github.io/
Policy and World Modeling Co-Training for Language Agents	2026-06-01	9 pages, 6 figures
TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks	2026-06-01
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents	2026-06-01
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation	2026-06-01
World-Task Factorization for Robot Learning	2026-06-01
Scaling Agentic Capabilities via Grounded Interaction Synthesis	2026-06-01
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning	2026-06-01	Accep... Accepted to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), Main Conference
Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects	2026-06-01
Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning	2026-06-01
WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching	2026-06-01	Accep... Accepted by ICML 2026

Title	Date	Comment
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling	2026-06-01	ICML 2026
ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning	2026-06-01
Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design	2026-06-01
CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning	2026-06-01
Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation	2026-06-01	https... https://github.com/alexmartin1722/mirage
PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning	2026-06-01
Attention Dynamics and Adaptive Decision Support in C5ISR: A Recurrence Quantification Analysis of Visual and Multimodal Attention Guidance Effects on Mission Performance	2026-06-01	11 Figures, 3 Tables
Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains	2026-06-01
WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata	2026-06-01	Softw... Software: https://www.robots.ox.ac.uk/~vgg/software/wise/ , Online demos: https://www.robots.ox.ac.uk/~vgg/software/wise/demo/ , Example Queries: https://www.robots.ox.ac.uk/~vgg/software/wise/examples/
Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality	2026-06-01
Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics	2026-06-01
Context-Aware Workflow Decomposition for Automated Mobile UI Annotation Using Multimodal Large Language Models	2026-06-01
Multimodal Approaches for Visually-Rich Document Type Classification: A Comparative Analysis	2026-06-01
Jailbreaking Multimodal Large Language Models using Multi-Clip Video	2026-06-01	27 pa... 27 pages, 20 figures, Accepted to the Main Conference of ACL 2026
MMSkills: Towards Multimodal Skills for General Visual Agents	2026-06-01	25 pa... 25 pages, 8 figures, 8 tables. Project page: https://zkangning.github.io/MMSkills_for_Visual_Agents/

Title	Date	Comment
WALL-WM: Carving World Action Modeling at the Event Joints	2026-06-01
AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance	2026-05-31
GeoSAM-3D: Geodesic Prompt Propagation for Open-Vocabulary 3D Scene Segmentation from Monocular Video	2026-05-30
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models	2026-05-28
PlayClass: Automated Play Behaviour Classification in Poultry	2026-05-26	Accep... Accepted at CV4Animals Workshop @ CVPR 2026
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation	2026-05-26	ICML ... ICML 2026, Project Page: https://aka.ms/world-r1, Code: https://github.com/microsoft/World-R1
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation	2026-05-22
Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models	2026-05-18	Accep... Accepted to CVPR 2026 Workshops CV4Smalls
Latent Video Prediction Learns Better World Models	2026-05-15
DriveCtrl: Conditioned Sim-to-Real Driving Video Generation	2026-05-14
Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception	2026-05-12	v2: M... v2: Major revision. Retitled; expanded from TimeSformer alone to four backbones (V-JEPA 2/2.1, TimeSformer, VideoMAE, CLIP), with V-JEPA 2.1 nearly tripling pretrained performance. Adds zero-shot PHASE transfer, attention-rollout analysis, and a language-distillation control. Data (OOO sim. judgments) & core hybrid triplet+RSA LoRA method unchanged from v1. Prepared for NeurIPS 2026 submission
MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation	2026-05-09	17 pages, 9 figues
Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios	2026-05-07
UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models	2026-05-07
Prompt-to-Gesture: Measuring the Capabilities of Image-to-Video Deictic Gesture Generation	2026-04-16	Accep... Accepted at 2026 International Conference on Automatic Face and Gesture Recognition (FG)

Navigation Menu

Latest 15 Papers - June 02, 2026 #215

Unified

Video Understanding

World Model

Multimodal

Multimodal LLM

Video Foundation Model

Metadata

Assignees

Labels

Projects

Milestone

Relationships

Development

Latest 15 Papers - June 02, 2026 #215

Description

Unified

Video Understanding

World Model

Multimodal

Multimodal LLM

Video Foundation Model

Metadata

Metadata

Assignees

Labels

Projects

Milestone

Relationships

Development

Issue actions