PaperHub

Yisen Wang

~Yisen_Wang1

41
论文总数
20.5
年均投稿
5.6
平均评分
接收情况23/41
会议分布
ICLR
28
NeurIPS
9
ICML
4

发表论文 (41 篇)

202522

4.0
4

EKAN: Equivariant Kolmogorov-Arnold Networks

ICLR 2025withdrawn
4.9
4

Incorporating Arbitrary Matrix Group Equivariance into KANs

ICML 2025Poster
6.6
4

Identifying and Understanding Cross-Class Features in Adversarial Training

ICML 2025Poster
7.0
4

Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD

ICLR 2025Poster
4.9
4

An Augmentation-Aware Theory for Self-Supervised Contrastive Learning

ICML 2025Poster
5.5
4

Output Alignment: A Top-down Approach to Length Generalization

ICLR 2025Rejected
6.3
4

Can In-context Learning Really Generalize to Out-of-distribution Tasks?

ICLR 2025Poster
6.1
4

Long-Short Alignment for Effective Long-Context Modeling in LLMs

ICML 2025Poster
6.5
4

TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice

ICLR 2025Poster
5.0
5

Propagation Alone is Enough for Graph Contrastive Learning

ICLR 2025Rejected
5.0
4

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

ICLR 2025Rejected
4.3
4

Are Synthetic Classifiers Really as Good as Real Classifiers?

ICLR 2025Rejected
6.0
4

Rethinking Invariance in In-context Learning

ICLR 2025Poster
6.5
4

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation

ICLR 2025Poster
7.3
4

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms

NeurIPS 2025Poster
6.8
4

Projection Head is Secretly an Information Bottleneck

ICLR 2025Poster
4.0
4

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

ICLR 2025withdrawn
7.8
4

$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning

NeurIPS 2025Poster
3.5
4

Towards Reliable Backdoor Attacks on Vision Transformers

ICLR 2025withdrawn
6.4
4

Language Ranker: A Lightweight Ranking framework for LLM Decoding

NeurIPS 2025Poster
5.8
5

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

ICLR 2025Poster
6.8
5

What is Wrong with Perplexity for Long-context Language Modeling?

ICLR 2025Poster

202419

5.3
4

Improved Invariant Learning for Node-level Out-of-distribution Generalization on Graphs

ICLR 2024Rejected
7.0
4

On the Role of Discrete Tokenization in Visual Representation Learning

ICLR 2024Spotlight
5.0
4

CONTROL: A Contrastive Learning Framework for Open World Semi-Supervised Learning

ICLR 2024Rejected
6.0
3

On the Theoretical Analysis of Dense Contrastive Learning

ICLR 2024Rejected
4.3
4

Characterizing Robust Overfitting in Adversarial Training via Cross-Class Features

ICLR 2024Rejected
5.8
4

Dissecting the Failure of Invariant Learning on Graphs

NeurIPS 2024Poster
5.6
5

Do Generated Data Always Help Contrastive Learning?

ICLR 2024Poster
5.5
4

Bridging Autoregressive and Masked Modeling for Enhanced Visual Representation Learning

ICLR 2024Rejected
4.3
4

How to Craft Backdoors with Unlabeled Data Alone?

ICLR 2024Rejected
4.8
5

Fight Back Against Jailbreaking via Prompt Adversarial Tuning

NeurIPS 2024Poster
5.8
4

Non-negative Contrastive Learning

ICLR 2024Poster
4.5
4

EigenGuard: Backdoor Defense in Eigenspace

ICLR 2024Rejected
4.4
5

A Unified Framework of Theoretically Robust Contrastive Loss against Label Noise

ICLR 2024Rejected
5.8
4

A Canonicalization Perspective on Invariant and Equivariant Learning

NeurIPS 2024Poster
6.3
4

Understanding the Role of Equivariance in Self-supervised Learning

NeurIPS 2024Poster
4.5
4

Towards Reliable Backdoor Attacks on Vision Transformers

ICLR 2024Rejected
6.6
5

A Theoretical Understanding of Self-Correction through In-context Alignment

NeurIPS 2024Poster
4.8
4

AttnGCG: Enhancing Adversarial Attacks on Language Models with Attention Manipulation

NeurIPS 2024Rejected
5.5
4

Towards Control-Centric Representations in Reinforcement Learning from Images

ICLR 2024Rejected