Le Xu
11 papers · 2021–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (26) 🐣 Hot Topic Early Bird
💎
Century Club · Bronze
🗃️
Keyword Collector
(68)
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(7)
Deep Learning
(6)
Core AI
(6)
Application Areas · Machine Learning
(4)
Optimization & Theory · Machine Learning
(3)
Computer Science
(2)
Learning Types
(2)
Optimization & Theory · Deep Learning
(2)
Systems
(2)
Computer Vision
(1)
Reinforcement Learning
(1)
Analysis
(1)
Application Areas · Deep Learning
(1)
Architectures
(1)
Keywords
large language model
(2)
vision-language model
(2)
voice conversion
(2)
contrastive learning
(1)
offline reinforcement learning
(1)
scene understanding
(1)
robust optimization
(1)
attention mechanism
(1)
knowledge distillation
(1)
efficient inference
(1)
chain-of-thought reasoning
(1)
multimodal learning
(1)
model architecture
(1)
adversarial training
(1)
model merging
(1)
uncertainty quantification
(1)
sharpness-aware minimization
(1)
neural network optimization
(1)
efficient computing
(1)
zero-shot learning
(1)
Papers
BatchGen: An Architecture for Scalable and Efficient Batch Inference
OSDI 2026
Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization (Student Abstract)
AAAI 2026
GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation
CVPR 2026
Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language Model
Interspeech 2025
Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
Interspeech 2025
StitchLLM: Serving LLMs, One Block at a Time
ACL 2025
ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference
ICLR 2024
MOSEL: Inference Serving Using Dynamic Modality Selection
EMNLP 2024
Residual Speaker Representation for One-Shot Voice Conversion
Interspeech 2024
Flow-VAE VC: End-to-End Flow Framework with Contrastive Loss for Zero-shot Voice Conversion
Interspeech 2023
Move Fast and Meet Deadlines: Fine-grained Real-time Stream Processing with Cameo
NSDI 2021