Picture for Lei Li

Lei Li

Carnegie Mellon University

CAR: Controllable Autoregressive Modeling for Visual Generation

Add code
Oct 07, 2024
Viaarxiv icon

Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems

Add code
Oct 07, 2024
Viaarxiv icon

Adaptive Masking Enhances Visual Grounding

Add code
Oct 04, 2024
Figure 1 for Adaptive Masking Enhances Visual Grounding
Figure 2 for Adaptive Masking Enhances Visual Grounding
Figure 3 for Adaptive Masking Enhances Visual Grounding
Figure 4 for Adaptive Masking Enhances Visual Grounding
Viaarxiv icon

Efficiently Identifying Watermarked Segments in Mixed-Source Texts

Add code
Oct 04, 2024
Viaarxiv icon

The Role of Deductive and Inductive Reasoning in Large Language Models

Add code
Oct 03, 2024
Figure 1 for The Role of Deductive and Inductive Reasoning in Large Language Models
Figure 2 for The Role of Deductive and Inductive Reasoning in Large Language Models
Figure 3 for The Role of Deductive and Inductive Reasoning in Large Language Models
Figure 4 for The Role of Deductive and Inductive Reasoning in Large Language Models
Viaarxiv icon

TypedThinker: Typed Thinking Improves Large Language Model Reasoning

Add code
Oct 02, 2024
Viaarxiv icon

You Only Speak Once to See

Add code
Sep 27, 2024
Figure 1 for You Only Speak Once to See
Figure 2 for You Only Speak Once to See
Figure 3 for You Only Speak Once to See
Figure 4 for You Only Speak Once to See
Viaarxiv icon

Multimodal Trajectory Prediction for Autonomous Driving on Unstructured Roads using Deep Convolutional Network

Add code
Sep 27, 2024
Viaarxiv icon

Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification

Add code
Sep 14, 2024
Figure 1 for Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
Figure 2 for Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
Figure 3 for Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
Figure 4 for Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
Viaarxiv icon

Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label

Add code
Sep 14, 2024
Figure 1 for Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label
Figure 2 for Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label
Figure 3 for Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label
Figure 4 for Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label
Viaarxiv icon