Fudan University

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Yesianrohn submitted a paper 3 days ago

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

wchengad submitted a paper 9 days ago

FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

Daniel0724 submitted a paper 16 days ago

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

View all activity

Papers

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

View all Papers

Fudan-University 's papers 29

Submitted by

Xingsong Ye

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

Fudan-University

Fudan University

Submitted by

Wei Cheng

FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

Fudan-University

Fudan University

Submitted by

Junke Wang

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

Fudan-University

Fudan University

Submitted by

Zhixiong Zhang (SII)

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion

Fudan-University

Fudan University

Submitted by

Caijun Xu

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

Fudan-University

Fudan University

Submitted by

Tiehua Mei

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

Fudan-University

Fudan University

Submitted by

Yaofeng Su

Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments

Fudan-University

Fudan University

Submitted by

rain

SEIF: Self-Evolving Reinforcement Learning for Instruction Following

Fudan-University

Fudan University

Submitted by

liangjiaqing

GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)

Fudan-University

Fudan University

Submitted by

JiaxinYe

Hierarchical Codec Diffusion for Video-to-Speech Generation

Fudan-University

Fudan University

Submitted by

Changze Lv

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Fudan-University

Fudan University

Submitted by

jingyi Yang

DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

Fudan-University

Fudan University

Submitted by

Wei Cheng

PixelSmile: Toward Fine-Grained Facial Expression Editing

Fudan-University

Fudan University

Submitted by

Ellie Chen

DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use

Fudan-University

Fudan University

Skill-Evolving Grounded Reasoning for Free-Text Promptable 3D Medical Image Segmentation

Fudan-University

Fudan University

Submitted by

OpenVGLab

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

Fudan-University

Fudan University

Submitted by

Zihan Yang

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation

Fudan-University

Fudan University

Submitted by

SII-Yibin Wang

Unified Personalized Reward Model for Vision Generation

Fudan-University

Fudan University

Submitted by

Mingyang Song

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

Fudan-University

Fudan University

Submitted by

Yuming Yang

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Fudan-University

Fudan University

Submitted by

Fu

The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios

Fudan-University

Fudan University

Submitted by

JPShi

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding

Fudan-University

Fudan University

Submitted by

Shuyuan Tu

FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction

Fudan-University

Fudan University

The Role of Entropy in Visual Grounding: Analysis and Optimization

Fudan-University

Fudan University

Submitted by

SII-Yibin Wang

UniREditBench: A Unified Reasoning-based Image Editing Benchmark

Fudan-University

Fudan University

Submitted by

XinghaoWang

Sparser Block-Sparse Attention via Token Permutation

Fudan-University

Fudan University

Submitted by

XuHao Hu

LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

Fudan-University

Fudan University

Submitted by

jingyi Yang

Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step

Fudan-University

Fudan University

RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis

Fudan-University

Fudan University