# JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence

arXiv: https://arxiv.org/abs/2606.14777 · HTML: https://mlsanity.com/paper/2606.14777/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 53 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 30 of 39)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [MMVU: Measuring Expert-Level Multi-Discipline Video Understanding](https://mlsanity.com/paper/2501.12380/) (2025)
- [Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction](https://mlsanity.com/paper/2501.03218/) (2025)
- [Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?](https://mlsanity.com/paper/2505.21374/) (2025)
- [TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos](https://mlsanity.com/paper/2504.17343/) (2025)
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2305.11013/) (2023)
- [StreamForest: Efficient Online Video Understanding with Persistent Event Memory](https://mlsanity.com/paper/2509.24871/) (2025)
- [TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models](https://mlsanity.com/paper/2410.23266/) (2024)
- [MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models](https://mlsanity.com/paper/2501.02955/) (2025)
- [Online Video Understanding: OVBench and VideoChat-Online](https://mlsanity.com/paper/2501.00584/) (2024)
- [LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2501.08282/) (2025)
- [Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding](https://mlsanity.com/paper/2604.05015/) (2026)
- [TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2512.14698/) (2025)
- [VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format](https://mlsanity.com/paper/2411.17991/) (2024)
- [VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning](https://mlsanity.com/paper/2504.07956/) (2025)
- [HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding](https://mlsanity.com/paper/2601.14724/) (2026)
- [Accelerating Streaming Video Large Language Models via Hierarchical Token Compression](https://mlsanity.com/paper/2512.00891/) (2025)
- [VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos](https://mlsanity.com/paper/2506.05349/) (2025)

## Built on by (most cited first, 14 of 14)

- [DOPD: Dual On-policy Distillation](https://mlsanity.com/paper/2606.30626/) (2026)
- [MOSS-VL Technical Report](https://mlsanity.com/paper/2608.15045/) (2026)
- [Realtime-Venus: A full-duplex interaction system with asynchronous delegation](https://mlsanity.com/paper/2609.13814/) (2026)
- [Multimodal Duplex Interaction Agent](https://mlsanity.com/paper/2609.08977/) (2026)
- [MobileMem: Learning from a Year of Mobile Experiences](https://mlsanity.com/paper/2608.13606/) (2026)
- [OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction](https://mlsanity.com/paper/2610.01762/) (2026)
- [LiveProBench: Can Streaming Video Models Really Interact Like Humans?](https://mlsanity.com/paper/2609.12658/) (2026)
- [OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue](https://mlsanity.com/paper/2609.21465/) (2026)
- [TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series](https://mlsanity.com/paper/2609.26389/) (2026)
- [TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding](https://mlsanity.com/paper/2609.30670/) (2026)
- [InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems](https://mlsanity.com/paper/2610.05775/) (2026)
- [FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?](https://mlsanity.com/paper/2610.12427/) (2026)
- [EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos](https://mlsanity.com/paper/2610.17128/) (2026)
- [DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding](https://mlsanity.com/paper/2610.19849/) (2026)

## Abstract (arXiv)

Many moments in the real world do not wait for a user to ask. A fire starts on a security monitor, an expression flickers across a video call, or a product a viewer wants flashes by in a livestream. Yet today's large models remain mostly turn-based by design: they answer only when addressed, and even video-call apps that appear interactive still operate as question-answer systems, reacting only when polled or prompted. We argue for a different paradigm: a model that is present in the world like a person. It continuously watches what is happening now, decides on its own whether to speak or stay silent, interacts in real time, and delegates to a background model when the problem is hard. To advance interaction models and their adoption across domains, we make two fully open-sourced contributions. First, we release JoyAI-VL-Interaction, an 8B-scale, vision-first VL-interaction model. The model makes the response decision internally, choosing each second to stay silent, respond, or delegate to a background model, and it excels at vision-triggered responsiveness and time awareness. We pair it with a transferable training recipe, from which capabilities we never trained for emerge, such as guiding a shopper through changing app screens or improvising a lecture from a slide deck. Second, we release a complete, deployable system built around that model. The system streams any ongoing video into the model, making it genuinely present in the world. All other components are pluggable, including ASR/TTS modules, memory, visualization UI, and a background brain that can connect to any API or agent. Across six real-world scenarios, human raters prefer JoyAI-VL-Interaction over the in-app video-call assistants of Doubao and Gemini by a wide margin. To our knowledge, this is the first open, vision-driven interaction model released together with its training recipe, data, and complete deployable system.