影响力指数

90.88/100

前 0.5%

全站排名 #334

发表论文37 篇

平均评分5.0

年均产出12.3 篇/年

Han-Jia Ye

Associate Professor@Nanjing University·中国·OpenReview

研究方向

Tabular Machine Learning · Meta-Learning · Pre-Trained Model Reuse · Similarity Learning · metric learning · Representation Learning

5.6

One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo

ICLR 2026Rejected

通讯

4.0

Efficient Evaluation of Large Language Models via Collaborative Filtering

ICLR 2026Rejected

三作

4.0

Hierarchical Representation Matching for CLIP-based Class-Incremental Learning

ICLR 2026Withdrawn

3.0

Dynamic Rank Reallocation for Module-Level LoRA

ICLR 2026Withdrawn

二作

3.0

Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Needs

ICLR 2026Withdrawn

通讯

2.0

Knowledge-Enhanced Tabular Data Generation

ICLR 2026Withdrawn

二作

2.0

FrontierBench: Are We Only Testing Agents Under the Streetlight?

ICLR 2026Rejected

通讯

2.0

Dimensional Debiasing via Multi-Agent Correction

ICLR 2026Withdrawn

通讯

7.3

A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities

NeurIPS 2025Poster

一作

7.3

Multimodal Tabular Reasoning with Privileged Structured Information

NeurIPS 2025Poster

通讯

6.8

Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation

NeurIPS 2025Poster

三作

6.8

Feature-aware Modulation for Learning from Temporal Tabular Data

NeurIPS 2025Poster

二作

6.1

TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems

ICML 2025Poster

二作

6.1

Understanding the Limits of Deep Tabular Methods with Temporal Shift

ICML 2025Poster

二作

6.1

Parrot: Multilingual Visual Instruction Tuning

ICML 2025Poster

通讯

6.0

Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective

ICLR 2025Rejected

一作

6.0

Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later

ICLR 2025Poster

一作

6.0

Let the LLM Stick to Its Strengths: Learning to Route Economical LLM

NeurIPS 2025Poster

通讯

5.8

Parrot: Multilingual Visual Instruction Tuning

ICLR 2025Rejected

通讯

5.5

ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs

ICLR 2025Poster

通讯

5.0

Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning

ICLR 2025Withdrawn

三作

4.9

Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

ICML 2025Poster

三作

4.9

Compositional Condition Question Answering in Tabular Understanding

ICML 2025Poster

通讯

4.8

Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens

合作者 (20)

Han-Jia Ye

The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?

UniCA: Unified Covariate Adaptation for Time Series Foundation Model

Agreement with the Ensemble for Zero-Shot Vision-Language Model Selection

One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo

Efficient Evaluation of Large Language Models via Collaborative Filtering

Hierarchical Representation Matching for CLIP-based Class-Incremental Learning

Dynamic Rank Reallocation for Module-Level LoRA

Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Needs

Knowledge-Enhanced Tabular Data Generation

FrontierBench: Are We Only Testing Agents Under the Streetlight?

Dimensional Debiasing via Multi-Agent Correction

A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities

Multimodal Tabular Reasoning with Privileged Structured Information

Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation

Feature-aware Modulation for Learning from Temporal Tabular Data

TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems

Understanding the Limits of Deep Tabular Methods with Temporal Shift

Parrot: Multilingual Visual Instruction Tuning

Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective

Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later

Let the LLM Stick to Its Strengths: Learning to Route Economical LLM

Parrot: Multilingual Visual Instruction Tuning

ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs

Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning

Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

Compositional Condition Question Answering in Tabular Understanding

Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens