StreamDuo: A Live Commentator and a Research Agent for Unseen Games
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/ZixianGao/StreamDuo-code
Project page: https://zixiangao.github.io/StreamDuo
Terminology
Sources
- Qwen3-VL Technical Report
- LoRA: Low-Rank Adaptation of Large Language Models
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Language Models (Mostly) Know What They Know
- LLaVA-OneVision: Easy Visual Task Transfer
- Unifying distillation and privileged information
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
- Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
- ReAct: Synergizing Reasoning and Acting in Language Models
- Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
- Game-MUG: Multimodal Oriented Game Situation Understanding and Commentary Generation Dataset
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs