Fan Zhou

Affiliations

Shanghai Jiao Tong UniversityUniversity of Electronic Science and Technology of China

papers

320

total citations

papers (19)

Lemur: Harmonizing Natural Language and Code for Language Agents

ICLR 2024arXiv

citations

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

NEURIPS 2023arXiv

citations

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

NEURIPS 2025arXiv

citations

Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making

NEURIPS 2023arXiv

citations

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

NEURIPS 2025arXiv

citations

Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge Augmentation

AAAI 2025

citations

Borrowing Eyes for the Blind Spot: Overcoming Data Scarcity in Malicious Video Detection via Cross-Domain Retrieval Augmentation

ICCV 2025

citations

Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference

ICCV 2025arXiv

citations

GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting

AAAI 2024arXiv

citations

Rate-Optimal Subspace Estimation on Random Graphs

NEURIPS 2021

citations

In-context Prompt-augmented Micro-video Popularity Prediction

AAAI 2025

citations

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement

NEURIPS 2023

citations

Learning Latent Seasonal-Trend Representations for Time Series Forecasting

NEURIPS 2022

citations

Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork

NEURIPS 2023

citations

Non-Crossing Quantile Regression for Distributional Reinforcement Learning

NEURIPS 2020

citations

Fan Zhou

Affiliations

papers (19)

Lemur: Harmonizing Natural Language and Code for Language Agents

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

MegaMath: Pushing the Limits of Open Math Corpora

Directional diffusion models for graph representation learning

Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning

Generalizing across Temporal Domains with Koopman Operators

Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge Augmentation

Borrowing Eyes for the Blind Spot: Overcoming Data Scarcity in Malicious Video Detection via Cross-Domain Retrieval Augmentation

Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference

GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting

Rate-Optimal Subspace Estimation on Random Graphs

In-context Prompt-augmented Micro-video Popularity Prediction

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement

Learning Latent Seasonal-Trend Representations for Time Series Forecasting

Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork

Non-Crossing Quantile Regression for Distributional Reinforcement Learning

papers (19)

Lemur: Harmonizing Natural Language and Code for Language Agents

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

MegaMath: Pushing the Limits of Open Math Corpora

Directional diffusion models for graph representation learning

Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning

Generalizing across Temporal Domains with Koopman Operators

Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge Augmentation

Borrowing Eyes for the Blind Spot: Overcoming Data Scarcity in Malicious Video Detection via Cross-Domain Retrieval Augmentation

Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference

GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting

Rate-Optimal Subspace Estimation on Random Graphs

In-context Prompt-augmented Micro-video Popularity Prediction

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement

Learning Latent Seasonal-Trend Representations for Time Series Forecasting

Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork

Non-Crossing Quantile Regression for Distributional Reinforcement Learning