Zhejiang University

university

Verified

https://www.zju.edu.cn/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

panrusheng authored a paper 5 days ago

ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs

Ningyu authored a paper 11 days ago

TokenPilot: Cache-Efficient Context Management for LLM Agents

wangsssssss authored a paper 12 days ago

UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

View all activity

Papers

From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion

VIA-SD: Verification via Intra-Model Routing for Speculative Decoding

View all Papers

zju 's papers 29

Submitted by

Yunqiu Xu

From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion

zju

Zhejiang University

5

Submitted by

Yunqiu Xu

VIA-SD: Verification via Intra-Model Routing for Speculative Decoding

zju

Zhejiang University

4

Submitted by

Haoyuan Li

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

zju

Zhejiang University

Submitted by

zhumuzhi

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching

zju

Zhejiang University

Submitted by

zhumuzhi

Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

zju

Zhejiang University

Submitted by

Yu Zhang

Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer

zju

Zhejiang University

2

Submitted by

Yu Zhang

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios

zju

Zhejiang University

2

Submitted by

Weijie Wang

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

zju

Zhejiang University

NEWTON: Agentic Planning for Physically Grounded Video Generation

zju

Zhejiang University

Submitted by

xichen

PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World

zju

Zhejiang University

Submitted by

Jason Ji

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models

zju

Zhejiang University

Submitted by

ding

Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing

zju

Zhejiang University

Submitted by

Weijie Wang

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

zju

Zhejiang University

Submitted by

Yongliang Shen

ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents

zju

Zhejiang University

Submitted by

zhumuzhi

OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering

zju

Zhejiang University

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

zju

Zhejiang University

Submitted by

taesiri

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning

zju

Zhejiang University

Submitted by

Canyu Zhao

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

zju

Zhejiang University

Submitted by

Guangyi Liu

MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

zju

Zhejiang University

Submitted by

Chenye Meng

Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes

zju

Zhejiang University

Submitted by

Haotong Lin

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

zju

Zhejiang University

Submitted by

Song Wang

Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

zju

Zhejiang University

Submitted by

MikaStars39

Evaluating Parameter Efficient Methods for RLVR

zju

Zhejiang University

Submitted by

zhumuzhi

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

zju

Zhejiang University

2

Submitted by

Zhang Mengchen

ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation

zju

Zhejiang University

Submitted by

xhl

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering

zju

Zhejiang University

Submitted by

taesiri

GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts

zju

Zhejiang University

Submitted by

Zedong Wang

Taming LLMs by Scaling Learning Rates with Gradient Grouping

zju

Zhejiang University

Submitted by

Juanxi Tian

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

zju

Zhejiang University