论文解读
BFCL Audio: An Audio Function Calling Evaluation for Large Language Models
语音交互 | 7.7/10
Icml-2026
论文解读
Bioacoustic Geolocation: Species Sounds as Geographic Signals
音频理解 | 5.8/10
论文解读
Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
语音合成 | 8/10
论文解读
Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling
Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling
论文解读
CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
音乐生成 | 6.4/10
论文解读
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
语音合成 | 7.1/10
论文解读
CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
音视频理解 | 8.3/10
论文解读
ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis
多模态模型 | 6.1/10
论文解读
Convex Low-resource Accent-Robust Language Detection in Speech Recognition
语音识别 | 6/10
论文解读
Decoupling The "What" and "Where" With Polar Coordinate Positional Embedding
音乐生成 | 7.8/10
论文解读
DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing
音乐生成 | 8/10
论文解读
Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox
语音属性识别 | 8/10
论文解读
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
音视频生成 | 8/10
论文解读
Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
语音增强 | 8.4/10
论文解读
E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs
音视频问答 | 6.9/10
论文解读
EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
音视频理解 | 6.3/10
论文解读
Efficient Distributed MLLM Training with Cornstarch
音视频理解 | 7/10
论文解读
Efficient Multi-modal Dataset Distillation via Analytic Parameter Matching
对比学习 | 7.2/10
论文解读
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
音乐检索 | 4.7/10
论文解读
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability
语音合成 | 6.6/10