Omni-Life: Benchmarking Omnimodal Real-Time AI Assistants in People's Daily Lives
cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/todayai-labs/omni-life
Terminology
Sources
- FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
- Realtime-Venus: A full-duplex interaction system with asynchronous delegation
- MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Moshi: a speech-text foundation model for real-time dialogue
- Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction
- DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction
- OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents
- AURA: Always-On Understanding and Real-Time Assistance via Video Streams
- OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants
- Qwen3.5-Omni Technical Report
- MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention
- EgoSocial: Benchmarking Proactive Intervention Ability of Omnimodal LLMs via Egocentric Social Interaction Perception
- ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
- JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
- OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data