Picture for Pengfei Wu

Pengfei Wu

FIRP: Faster LLM inference via future intermediate representation prediction

Add code
Oct 27, 2024
Viaarxiv icon

Graph-Structured Speculative Decoding

Add code
Jul 23, 2024
Viaarxiv icon

AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning

Add code
Jul 09, 2024
Figure 1 for AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning
Figure 2 for AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning
Figure 3 for AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning
Figure 4 for AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning
Viaarxiv icon

Optimal Reference Nodes Deployment for Positioning Seafloor Anchor Nodes

Add code
May 24, 2024
Viaarxiv icon

Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration

Add code
Apr 18, 2024
Viaarxiv icon

LSTP: Language-guided Spatial-Temporal Prompt Learning for Long-form Video-Text Understanding

Add code
Feb 25, 2024
Viaarxiv icon

Future Full-Ocean Deep SSPs Prediction based on Hierarchical Long Short-Term Memory Neural Networks

Add code
Nov 16, 2023
Figure 1 for Future Full-Ocean Deep SSPs Prediction based on Hierarchical Long Short-Term Memory Neural Networks
Figure 2 for Future Full-Ocean Deep SSPs Prediction based on Hierarchical Long Short-Term Memory Neural Networks
Figure 3 for Future Full-Ocean Deep SSPs Prediction based on Hierarchical Long Short-Term Memory Neural Networks
Figure 4 for Future Full-Ocean Deep SSPs Prediction based on Hierarchical Long Short-Term Memory Neural Networks
Viaarxiv icon

Underwater Sound Speed Profile Construction: A Review

Add code
Oct 12, 2023
Viaarxiv icon

Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech

Add code
Oct 11, 2021
Figure 1 for Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Figure 2 for Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Figure 3 for Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Figure 4 for Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Viaarxiv icon

FORTAP: Using Formulae for Numerical-Reasoning-Aware Table Pretraining

Add code
Sep 15, 2021
Figure 1 for FORTAP: Using Formulae for Numerical-Reasoning-Aware Table Pretraining
Figure 2 for FORTAP: Using Formulae for Numerical-Reasoning-Aware Table Pretraining
Figure 3 for FORTAP: Using Formulae for Numerical-Reasoning-Aware Table Pretraining
Figure 4 for FORTAP: Using Formulae for Numerical-Reasoning-Aware Table Pretraining
Viaarxiv icon