PaperHub

Masashi Sugiyama

~Masashi_Sugiyama1

33
论文总数
16.5
年均投稿
5.9
平均评分
接收情况19/33
会议分布
ICLR
22
NeurIPS
7
ICML
3
COLM
1

发表论文 (33 篇)

202520

5.7
3

Parallel simulation for sampling under isoperimetry and score-based diffusion models

ICLR 2025Rejected
6.8
4

The Adaptive Complexity of Minimizing Relative Fisher Information

NeurIPS 2025Poster
7.8
4

Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models

ICML 2025Spotlight
4.8
4

Delving into Weakly Supervised Learning with Pre-Trained Models

ICLR 2025Rejected
6.8
4

The adaptive complexity of parallelized log-concave sampling

ICLR 2025withdrawn
4.4
4

Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability

ICML 2025Poster
6.8
4

Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback

COLM 2025Poster
7.8
4

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update

NeurIPS 2025Poster
6.8
4

Sharpness-Aware Black-Box Optimization

ICLR 2025Poster
6.0
5

Towards Out-of-Modal Generalization without Instance-level Modal Correspondence

ICLR 2025Poster
5.0
4

Causal Graph Learning via Distributional Invariance of Cause-Effect Relationship

ICLR 2025Rejected
3.0
5

On Unsupervised Prompt Learning for Classification with Black-box Language Models

ICLR 2025withdrawn
5.5
4

On the Cost-Effectiveness of Partially-Annotating Methods for Multi-Label Learning

ICLR 2025Rejected
5.8
4

Decoupling the Class Label and the Target Concept in Machine Unlearning

ICLR 2025Rejected
7.5
4

Realistic Evaluation of Deep Partial-Label Learning Algorithms

ICLR 2025Spotlight
5.5
4

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

ICLR 2025Poster
5.8
4

CARPRT: Class-Aware Prompt Reweighting for Pre-Trained Vision-Language Models

ICLR 2025Rejected
4.0
4

Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning

ICLR 2025withdrawn
7.8
4

Adaptive Localization of Knowledge Negation for Continual LLM Unlearning

ICML 2025Poster
5.4
5

Learning View-invariant World Models for Visual Robotic Manipulation

ICLR 2025Poster

202413