PaperHub

Defu Lian

~Defu_Lian1

24
论文总数
12.0
年均投稿
6.2
平均评分
接收情况17/24
会议分布
ICLR
14
NeurIPS
8
ICML
2

发表论文 (24 篇)

202516 篇

5.5
4

Multi-play Multi-armed Bandit Model with Scarce Sharable Arm Capacities

ICLR 2025Rejected
6.0
5

Making Transformer Decoders Better Differentiable Indexers

ICLR 2025Poster
5.8
4

TDDBench: A Benchmark for Training data detection

ICLR 2025Poster
4.5
4

Multiple-play Stochastic Bandits with Prioritized Resource Sharing

ICLR 2025Rejected
7.8
4

Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective

NeurIPS 2025Poster
5.3
4

Harnessing Query Heterogeneity for Cost-Effective Proactive Caching in LLM Inference

ICLR 2025Rejected
4.5
4

Strengthening Federated Learning: Surrogate Data-Guided Aggregation for Robust Backdoor Defense

ICLR 2025Rejected
7.0
4

Making Text Embedders Few-Shot Learners

ICLR 2025Poster
5.5
4

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models

ICML 2025Poster
9.0
4

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

ICLR 2025Oral
6.8
4

P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models

NeurIPS 2025Poster
6.1
4

HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking

ICML 2025Poster
8.2
4

LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data

NeurIPS 2025Spotlight
6.8
5

Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference

NeurIPS 2025Poster
6.3
4

RecFlow: An Industrial Full Flow Recommendation Dataset

ICLR 2025Poster
6.5
4

ToolACE: Winning the Points of LLM Function Calling

ICLR 2025Poster

20248 篇

6.3
4

Learning from Highly Sparse Spatio-temporal Data

NeurIPS 2024Poster
7.3
4

Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure

NeurIPS 2024Oral
5.0
3

Mitigating Backdoor Attacks in Federated Learning through Noise-Guided Aggregation

ICLR 2024Rejected
6.3
4

Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model

NeurIPS 2024Poster
8.0
3

NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation

ICLR 2024Spotlight
5.3
4

FilterNet: Harnessing Frequency Filters for Time Series Forecasting

NeurIPS 2024Poster
3.8
5

Enhancing Graph Injection Attacks Through Over-Smoothing Amplification

ICLR 2024Rejected
5.7
3

Open-Source Can Be Dangerous: On the Vulnerability of Value Alignment in Open-Source LLMs

ICLR 2024Rejected
合作者 (20)