Jun 2026
Orca: The World is in Your Mind
arXiv ↗We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it
💛 185
📚 Awesome Multimodal
10,492 papers across 0 tags, ranked by community signal and explained.
Jun 2026
InterleaveThinker: Reinforcing Agentic Interleaved Generation
arXiv ↗Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained b
💛 77
Jun 2026
In-Context World Modeling for Robotic Control
arXiv ↗Modern Vision-Language-Action (VLA) models often fail to generalize to novel setups, such as altered camera viewpoints or robot morphologies, because they are ty
💛 59
Jun 2026
ViQ: Text-Aligned Visual Quantized Representations at Any Resolution
arXiv ↗A unified representation for text and vision is a natural pursuit, as it enables simpler multimodal modeling and more efficient training. However, representing images
💛 38
Jun 2026
Orchestra-o1: Omnimodal Agent Orchestration
arXiv ↗The recent success of agent swarms has shifted the paradigm of large language model (LLM)-based agents from single-agent workflows to multi-agent systems, highlighting t
💛 37
Jun 2026
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models
arXiv ↗Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, w
💛 53
Jun 2026
M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks
arXiv ↗As multi-modal models advance towards long-form video understanding, memory emerges as a critical capability. Despite substantial efforts in developing video datasets and
💛 26
Jun 2026
V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
arXiv ↗Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in local image regions
💛 26
Jun 2026
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
arXiv ↗We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts phys
💛 22
May 2026
Representation Forcing for Bottleneck-Free Unified Multimodal Models
arXiv ↗Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrained VAE for ima
💛 50
Jun 2026
OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains
arXiv ↗Current automated pipelines for audio-visual Question Answering (QA) generally adopt a ``video-caption-QA'' paradigm. However, these methods typically segment videos into
💛 26
Jun 2026
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction
arXiv ↗Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Vi
💛 22
May 2026
Task-Focused Memorization for Multimodal Agents
arXiv ↗Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, constructing effecti
💛 24
Jun 2026
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
arXiv ↗Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, re
💛 13
Jun 2026
Text-Vision Co-Instructed Image Editing
arXiv ↗Existing image editing methods can be generally categorized into textual instruction-based and visual prompt-based ones. Textual instructions are semantically expressive,
💛 12
Jun 2026
Native Active Perception as Reasoning for Omni-Modal Understanding
arXiv ↗Passive models for long video understanding typically rely on a "watch-it-all" paradigm, processing frames uniformly regardless of query difficulty, causing computationa
💛 16
Jun 2026
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
arXiv ↗Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where ob
💛 16
Apr 2026
FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
arXiv ↗The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution, yet current evaluations fai…
💛 95
Jun 2026
UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer
arXiv ↗Unified Multimodal Models (UMMs) have emerged as a critical direction for general-purpose multimodal intelligence, integrating understanding and generation into a single f
💛 9
Jun 2026
Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification
arXiv ↗Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate
💛 14
May 2026
PEEK: Picking Essential frames via Efficient Knowledge distillation
arXiv ↗Video-language models can process only a limited number of frames, making frame selection a key bottleneck for efficient video captioning. Most captioning pipelines still
💛 15
Jun 2026
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
arXiv ↗Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations
💛 13
Jun 2026
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
arXiv ↗Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface:
💛 8
Apr 2026
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
arXiv ↗Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual…
💛 72