Picture for Yisen Wang

Yisen Wang

Rethinking Invariance in In-context Learning

Add code
May 08, 2025
Viaarxiv icon

R^3-VQA: "Read the Room" by Video Social Reasoning

Add code
May 07, 2025
Viaarxiv icon

When More is Less: Understanding Chain-of-Thought Length in LLMs

Add code
Feb 11, 2025
Viaarxiv icon

Three-dimensional signal processing: a new approach in dynamical sampling via tensor products

Add code
Feb 04, 2025
Viaarxiv icon

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation

Add code
Jan 03, 2025
Figure 1 for SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
Figure 2 for SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
Figure 3 for SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
Figure 4 for SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
Viaarxiv icon

An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise

Add code
Jan 02, 2025
Viaarxiv icon

Understanding Difficult-to-learn Examples in Contrastive Learning: A Theoretical Framework for Spectral Contrastive Learning

Add code
Jan 02, 2025
Viaarxiv icon

MADE: Graph Backdoor Defense with Masked Unlearning

Add code
Nov 26, 2024
Viaarxiv icon

Understanding the Role of Equivariance in Self-supervised Learning

Add code
Nov 10, 2024
Viaarxiv icon

Dissecting the Failure of Invariant Learning on Graphs

Add code
Nov 05, 2024
Viaarxiv icon