Picture for Han Bao

Han Bao

VModA: An Effective Framework for Adaptive NSFW Image Moderation

Add code
May 29, 2025
Viaarxiv icon

MentalMAC: Enhancing Large Language Models for Detecting Mental Manipulation via Multi-Task Anti-Curriculum Distillation

Add code
May 21, 2025
Viaarxiv icon

Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Losses

Add code
May 15, 2025
Viaarxiv icon

Many-to-Many Matching via Sparsity Controlled Optimal Transport

Add code
Mar 31, 2025
Viaarxiv icon

Any-stepsize Gradient Descent for Separable Data under Fenchel--Young Losses

Add code
Feb 07, 2025
Viaarxiv icon

TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

Add code
Jan 29, 2025
Viaarxiv icon

Online Inverse Linear Optimization: Improved Regret Bound, Robustness to Suboptimality, and Toward Tight Regret Analysis

Add code
Jan 27, 2025
Viaarxiv icon

Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel$-$Young Loss Perspective and Gap-Dependent Regret Analysis

Add code
Jan 24, 2025
Viaarxiv icon

DeepSeek-V3 Technical Report

Add code
Dec 27, 2024
Figure 1 for DeepSeek-V3 Technical Report
Figure 2 for DeepSeek-V3 Technical Report
Figure 3 for DeepSeek-V3 Technical Report
Figure 4 for DeepSeek-V3 Technical Report
Viaarxiv icon

Zipfian Whitening

Add code
Nov 01, 2024
Figure 1 for Zipfian Whitening
Figure 2 for Zipfian Whitening
Figure 3 for Zipfian Whitening
Figure 4 for Zipfian Whitening
Viaarxiv icon