1

EmoTalker: Emotionally Editable Talking Face Generation via Diffusion Model
In recent years, the field of talking faces generation has attracted considerable attention, with certain methods adept at generating …
Cite arXiv Dataset IEEE
EmoTalker: Emotionally Editable Talking Face Generation via Diffusion Model
ED-TTS: Multi-Scale Emotion Modeling Using Cross-Domain Emotion Diarization for Emotional Speech Synthesis
Existing emotional speech synthesis methods often utilize an utterance-level style embedding extracted from reference audio, neglecting …
Cite arXiv IEEE
ED-TTS: Multi-Scale Emotion Modeling Using Cross-Domain Emotion Diarization for Emotional Speech Synthesis
Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval
Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations …
Cite arXiv IEEE
Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval
INCPrompt: Task-Aware Incremental Prompting for Rehearsal-Free Class-incremental Learning
This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. …
Cite arXiv IEEE
INCPrompt: Task-Aware Incremental Prompting for Rehearsal-Free Class-incremental Learning
Leveraging Biases in Large Language Models: bias-kNN for Effective Few-Shot Learning
Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning. …
Cite arXiv IEEE
Leveraging Biases in Large Language Models: bias-kNN for Effective Few-Shot Learning
P2DT: Mitigating Forgetting in Task-Incremental Learning with Progressive Prompt Decision Transformer
Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance …
Cite arXiv IEEE
P2DT: Mitigating Forgetting in Task-Incremental Learning with Progressive Prompt Decision Transformer
Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
Deploying neural networks on microcontroller units (MCUs) presents substantial challenges due to their constrained computation and …
Cite arXiv IEEE
Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer
Federated Learning (FL) has been widely con- cerned for it enables decentralized learning while ensuring data privacy. However, most …
PDF Cite arXiv IJCAI
FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer
GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world …
PDF Cite Poster Slides
GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models
Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains …
PDF Cite arXiv AAAI
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models