论文解读
MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
语音分离 | 7.5/10
基准测试
论文解读
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
基准测试 | 8.0/10
论文解读
MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark
语音问答 | 8.5/10
论文解读
Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
音频场景理解 | 9.0/10
论文解读
Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
多模态模型 | 8.5/10
论文解读
OmniCVR: A Benchmark for Omni-Composed Video Retrieval with Vision, Audio, and Text
音频检索 | 8.5/10
论文解读
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
基准测试 | 7.8/10
论文解读
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
多模态模型 | 8.0/10
论文解读
ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction
语音对话系统 | 8.5/10
论文解读
PrismAudio: Decomposed Chain-of-Thought and Multi-dimensional Rewards for Video-to-Audio Generation
音频生成 | 7.0/10
论文解读
STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
音频问答 | 8.5/10
论文解读
Steering Autoregressive Music Generation with Recursive Feature Machines
音乐生成 | 8.0/10
论文解读
TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization
视频摘要 | 8.0/10
论文解读
TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems
模型评估 | 7.0/10
论文解读
Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
音频分类 | 9.0/10
论文解读
VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Video
多模态模型 | 7.0/10
论文解读
VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models
语音对话系统 | 8.0/10
论文解读
WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables
语音对话系统 | 7.5/10
论文解读
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
基准测试 | 8.5/10
论文解读
XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
基准测试 | 9.0/10