notes
26 个文件夹 · 0 篇笔记
- 2024_A_Full-duplex_Speech_Dialogue_Scheme_Based_On_Large_Language_Models文件夹
- 2024_Beyond_Turn-Based_Interfaces_Synchronous_LLMs_as_Full-Duplex_Dialogue_Agents文件夹
- 2024_Freeze-Omni_A_Smart_and_Low_Latency_Speech-to-Speech_Dialogue_Model_with_Frozen_LLM文件夹
- 2024_Moshi_A_Speech-Text_Foundation_Model_for_Real-Time_Dialogue文件夹
- 2025_Daily-Omni_Towards_Audio-Visual_Reasoning_with_Temporal_Alignment_across_Modalities文件夹
- 2025_Efficient_and_Direct_Duplex_Modeling_for_Speech-to-Speech_Language_Model文件夹
- 2025_FD-Bench_A_Full-Duplex_Benchmarking_Pipeline_Designed_for_Full_Duplex_Spoken_Dialogue_Systems文件夹
- 2025_JoyAvatar_Real-time_and_Infinite_Audio-Driven_Avatar_Generation_with_Autoregressive_Diffusion文件夹
- 2025_Qwen3-Omni_Technical_Report文件夹
- 2025_Vision-Speech_Models_Teaching_Speech_Models_to_Converse_about_Images文件夹
- 2025_VITA-1.5_Towards_GPT-4o_Level_Real-Time_Vision_and_Speech_Interaction文件夹
- 2026_Avatar_Forcing_Real-Time_Interactive_Head_Avatar_Generation_for_Natural_Conversation文件夹
- 2026_Beyond_Monologue_Interactive_Talking-Listening_Avatar_Generation_with_Conversational_Audio_Context-Aware_Kernels文件夹
- 2026_DuplexOmni_Real-Time_Listening_Seeing_Thinking_and_Speaking_for_Full-Duplex_Interaction文件夹
- 2026_DyaPlex_Full-Duplex_Speech-Motion_Model_for_Dyadic_Interaction文件夹
- 2026_F-Actor_Controllable_Conversational_Behaviour_in_Full-Duplex_Models文件夹
- 2026_FacePlex_Full-Duplex_Joint_Speech-Facial_Motion_Generation_for_Conversational_Avatars文件夹
- 2026_Hierarchical_Acoustic-Semantic_Modeling_for_Full-Duplex_SLMs文件夹
- 2026_Interaction_Models_A_Scalable_Approach_to_Human-AI_Collaboration文件夹
- 2026_InteractiveAvatar_Real-Time_Streaming_Video_Generation_for_Consistent_and_Intent-Aware_Avatars文件夹
- 2026_Liberating_LLM_Capabilities_in_Full-Duplex_Speech_Models文件夹
- 2026_MiniCPM-o_4.5_Towards_Real-Time_Full-Duplex_Omni-Modal_Interaction文件夹
- 2026_PersonaPlex_Voice_and_Role_Control_for_Full_Duplex_Conversational_Speech_Models文件夹
- 2026_Qwen3.5-Omni_Technical_Report文件夹
- 2026_Synchronization_and_Turn-Taking_in_Full-Duplex_Speech_Dialogue_Models文件夹
- 2026_VideoFDB_Evaluating_Full-Duplex_Vision-Speech_Capabilities_in_Conversational_Agents文件夹