Improving Proactive AI Assistance with Hierarchical Procedural Understanding
cs.LG, cs.CV
Submitted: 2026-10-05
Updated: 2026-10-06
Project page: https://jinsuby.github.io/ProactiveCoach
Sources
- Qwen3-VL Technical Report
- Action100M: A Large-scale Video Action Dataset
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
- StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
- IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
- VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
- OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
- GUIDE: A Guideline-Guided Dataset for Instructional Video Comprehension
- OpenAI GPT-5 System Card
- Qwen3.5-Omni Technical Report
- ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
- Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
- VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
- OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
- Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks