OmniTide: Co-Designing Algorithms and Systems for Efficient On-Device Omni-LLM Streaming
cs.AI, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-29
Code: https://github.com/csuhan/OneLLM
Sources
- MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Mistral 7B
- MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
- FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
- StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
- Efficient Streaming Language Models with Attention Sinks
- Qwen2.5-Omni Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems