PaperHub

Yang Liu

~Yang_Liu3

48
论文总数
24.0
年均投稿
5.5
平均评分
接收情况27/48
会议分布
ICLR
32
NeurIPS
13
ICML
3

发表论文 (48 篇)

202524

6.8
4

Regretful Decisions under Label Noise

ICLR 2025Poster
5.5
4

Revisiting inverse Hessian vector products for calculating influence functions

ICLR 2025Rejected
6.4
5

Understanding Chain-of-Thought in LLMs Through Information Theory

ICLR 2025Rejected
4.8
4

Learning to Watermark LLM-generated Text via Reinforcement Learning

ICLR 2025Rejected
5.5
3

Understanding Chain-of-Thought in LLMs through Information Theory

ICML 2025Poster
5.8
4

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

ICLR 2025Poster
6.0
4

Adversarial Machine Unlearning

ICLR 2025Poster
6.8
4

Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth

NeurIPS 2025Poster
5.5
4

Robust Multi-bit Text Watermark with LLM-based Paraphrasers

ICML 2025Poster
6.0
3

Noisy Test-Time Adaptation in Vision-Language Models

ICLR 2025Poster
6.4
4

Incentivizing LLMs to Self-Verify Their Answers

NeurIPS 2025Poster
4.5
4

Robust RLHF with Noisy Rewards

ICLR 2025withdrawn
4.3
4

Counterfactual Learning under Rank Preservation

ICLR 2025Rejected
7.3
4

Learning Counterfactual Outcomes Under Rank Preservation

NeurIPS 2025Poster
6.4
4

DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization

NeurIPS 2025Spotlight
7.8
4

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

NeurIPS 2025Rejected
5.5
4

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

ICML 2025Poster
5.3
4

Prompting Fairness: Integrating Causality to Debias Large Language Models

ICLR 2025Poster
4.0
4

Human-Instruction-Free LLM Self-Alignment with Limited Samples

ICLR 2025Rejected
4.8
4

DiffTell: A Comprehensive Dataset for Image Difference Captioning

ICLR 2025Rejected
5.8
4

Improving Data Efficiency via Curating LLM-Driven Rating Systems

ICLR 2025Poster
6.5
4

LLM Unlearning via Loss Adjustment with Only Forget Data

ICLR 2025Poster
4.5
4

Progressive LLM Alignments Using Two-Player Games

ICLR 2025Rejected
6.0
4

Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond

ICLR 2025Rejected

202424

6.0
4

Multi-LLM Debate: Framework, Principals, and Interventions

NeurIPS 2024Poster
5.3
3

Understanding Unfairness via Training Concept Influence

ICLR 2024Rejected
7.5
4

Post-hoc bias scoring is optimal for fair classification

ICLR 2024Spotlight
4.3
3

Explaining recommendation systems through contrapositive perturbations

ICLR 2024Rejected
4.0
3

Dataset Fairness: Achievable Fairness On Your Data With Utility Guarantees

ICLR 2024Rejected
6.7
3

Achievable Fairness on Your Data With Utility Guarantees

NeurIPS 2024Poster
5.7
3

Large Language Model Unlearning

NeurIPS 2024Poster
5.5
4

RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies

ICLR 2024Poster
5.3
3

Adversarial Machine Unlearning: A Stackelberg Game Approach

ICLR 2024Rejected
6.7
3

Procedural Fairness Through Decoupling Objectionable Data Generating Components

ICLR 2024Spotlight
5.8
4

Large Language Model Unlearning via Embedding-Corrupted Prompts

NeurIPS 2024Poster
5.0
4

DOS: Dreaming Outlier Semantics for Out-of-distribution Detection

ICLR 2024Rejected
4.8
4

Incentivizing Data Collection from Heterogeneous Clients in Federated Learning

ICLR 2024Rejected
5.8
4

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

ICLR 2024Poster
4.5
4

Federated Learning with Local Openset Noisy Labels

ICLR 2024Rejected
4.0
4

Deep concept removal

ICLR 2024Rejected
6.0
4

Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation

NeurIPS 2024Poster
5.3
4

Learning the Optimal Policy for Balancing Short-Term and Long-Term Rewards

NeurIPS 2024Poster
6.7
3

User-Creator Feature Polarization in Recommender Systems with Dual Influence

NeurIPS 2024Poster
4.5
4

Fairness without Harm: An Influence-Guided Active Sampling Approach

NeurIPS 2024Poster
3.0
3

UGradSL: Machine Unlearning Using Gradient-based Smoothed Label

ICLR 2024Rejected
5.2
5

Fair Classifiers Without Fair Training: An Influence-Guided Data Sampling Approach

ICLR 2024Rejected
6.5
4

Fair Classifiers that Abstain without Harm

ICLR 2024Poster
4.3
4

Fairness Improves Learning from Noisily Labeled Long-Tailed Data

ICLR 2024Rejected