Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams

arXiv:2609.27303 · cs.LG · Submitted 2026-09-23 · Read on arXiv

cs.LG

Submitted: 2026-09-23

Updated: 2026-09-23

Project page: https://daryl-gsj.github.io/LiveAssistant

Terminology

• Benchmark — 26× in this paper · explained in 2 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Failure Taxonomy — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
• KuaiLive-M3: A Multi-Modal, Multi-Domain, and Multi-Feedback Dataset for Live Streaming Recommendation
• MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning
• ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding
• StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
• LiveChat: Video Comment Generation from Audio-Visual Multimodal Contexts
• VideoModerator: A Risk-aware Framework for Multimodal Video Moderation in E-Commerce
• Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching
• An LLM Benchmark for Addressee Recognition in Multi-modal Multi-party Dialogue
• Group Sequence Policy Optimization
• StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
• Qwen3-Omni Technical Report
• Thinking in Streaming Video
• Qwen3-VL Technical Report
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams
• Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
• StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
• LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
• From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks