影响力指数

74.04/100

前 2%

全站排名 #1,303

发表论文38 篇

平均评分4.8

年均产出12.7 篇/年

Tong Yu

Senior Research Scientist@Adobe Research·美国·OpenReview

研究方向

Vision Language Models · Natural Language Processing · Reinforcement Learning · Recommender System · Data Intelligence

5.5

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

ICLR 2026Rejected

5.3

Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization

ICLR 2026Poster

5.0

AMPS: Adaptive Modality Preference Steering via Functional Entropy

ICLR 2026Rejected

4.5

Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing

ICLR 2026Desk Rejected

4.5

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

ICLR 2026Rejected

4.0

Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners

ICLR 2026Rejected

三作

4.0

FERA: Uncertainty-aware Federated Reasoning for Large Language Models

ICLR 2026Rejected

3.5

WaterFlow: Fast and Robust Watermarking in the Latent Fourier Domain

ICLR 2026Rejected

3.5

A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations

ICLR 2026Withdrawn

2.7

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

NeurIPS 2025Poster

6.8

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

ICLR 2025Poster

6.3

Traceable and Explainable Multimodal Large Language Models: An Information-Theoretic View

COLM 2025Poster

6.0

SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

ICLR 2025Poster

6.0

A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models

COLM 2025Poster

5.5

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

ICML 2025Poster

5.3

VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use

ICLR 2025Rejected

三作

5.0

CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement

ICLR 2025Withdrawn

三作

4.9

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

ICML 2025Poster

4.9

Fully Dynamic Embedding into $\ell_p$ Spaces

ICML 2025Poster

通讯

4.8

CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models

ICLR 2025Rejected

三作

3.8

FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback

ICLR 2025Withdrawn

3.0

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

合作者 (20)

Tong Yu

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization

AMPS: Adaptive Modality Preference Steering via Functional Entropy

Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners

FERA: Uncertainty-aware Federated Reasoning for Large Language Models

WaterFlow: Fast and Robust Watermarking in the Latent Fourier Domain

A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization

Beyond Static Retrieval Policies: Task-Aware Adaptive RAG With METAR

Contextual Bandits with LLM-Derived Priors and Adaptive Calibration

In-context Ranking Preference Optimization

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

Traceable and Explainable Multimodal Large Language Models: An Information-Theoretic View

SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use

CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

Fully Dynamic Embedding into $\ell_p$ Spaces

CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models

FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation