PaperHub

Di Wang

~Di_Wang1

36
论文总数
18.0
年均投稿
5.6
平均评分
接收情况18/36
会议分布
ICLR
22
NeurIPS
8
COLM
4
ICML
2

发表论文 (36 篇)

202520 篇

6.8
4

Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence

NeurIPS 2025Poster
4.8
4

Private Stochastic Convex Optimization with Tysbakov Noise Condition and Large Lipschitz Constant

ICLR 2025withdrawn
6.8
4

Private Stochastic Optimization for Achieving Second-Order Stationary Points

ICLR 2025Rejected
6.8
5

Private Training Large-scale Models with Efficient DP-SGD

NeurIPS 2025Poster
7.8
4

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

ICML 2025Poster
5.0
4

FlashDP: Memory-Efficient and High-Throughput DP-SGD Training for Large Language Models

ICLR 2025withdrawn
3.8
4

ZO-Offloading: Fine-Tuning LLMs with 100 Billion Parameters on a Single GPU

ICLR 2025withdrawn
6.3
4

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

ICLR 2025Rejected
7.3
4

Second-Order Convergence in Private Stochastic Non-Convex Optimization

NeurIPS 2025Poster
6.3
3

Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory

COLM 2025Poster
5.3
3

Dissecting Misalignment of Multimodal Large Language Models via Influence Function

ICLR 2025Rejected
4.5
4

Representation Confusion: Towards Representation Backdoor on CLIP via Concept Activation

ICLR 2025Rejected
5.7
7

Towards User-level Private Reinforcement Learning with Human Feedback

COLM 2025Poster
5.6
5

Editable Concept Bottleneck Models

ICLR 2025Rejected
6.8
4

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

NeurIPS 2025Poster
3.5
4

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View

ICLR 2025withdrawn
3.0
4

What Makes Your Model a Low-empathy or Warmth Person: Exploring the Origins of Personality in LLMs

ICLR 2025withdrawn
4.0
4

XTraffic: A Dataset Where Traffic Meets Incidents with Explainability and More

ICLR 2025withdrawn
4.8
4

Low-cost Enhancer for Text Attributed Graph Learning via Graph Alignment

ICLR 2025withdrawn
7.2
4

Editable Concept Bottleneck Models

ICML 2025Poster

202416 篇

6.4
5

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach

ICLR 2024Poster
4.3
4

Towards Personalized AI: Early-stopping Low-Rank Adaptation of Foundation Models

ICLR 2024Rejected
6.3
4

Perplexity-aware Correction for Robust Alignment with Noisy Preferences

NeurIPS 2024Poster
4.3
4

On the Global Convergence of Natural Actor-Critic with Neural Network Parametrization

ICLR 2024Rejected
5.5
4

Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks

ICLR 2024Rejected
-

Truthful High Dimensional Sparse Linear Regression

ICLR 2024withdrawn
5.3
3

Revisiting Differentially Private ReLU Regression

NeurIPS 2024Poster
6.3
3

Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model

ICLR 2024Poster
5.3
3

An LLM can Fool Itself: A Prompt-Based Adversarial Attack

ICLR 2024Poster
6.3
4

Faithful Vision-Language Interpretation via Concept Bottleneck Models

ICLR 2024Poster
6.5
4

Model Autophagy Analysis to Explicate Self-consumption within Human-AI Interactions

COLM 2024Poster
5.4
5

Fair Text-to-Image Diffusion via Fair Mapping

ICLR 2024Rejected
5.0
3

Truthful High Dimensional Sparse Linear Regression

NeurIPS 2024Poster
2.5
4

Adversarial enhanced representation for link prediction in multi-layer networks

ICLR 2024Rejected
6.8
4

Multi-hop Question Answering under Temporal Knowledge Editing

COLM 2024Poster
6.5
4

Towards Multi-dimensional Explanation Alignment for Medical Classification

NeurIPS 2024Poster
合作者 (20)