Zhejiang University

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Ningyu submitted a paper 1 day ago

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

Canyu submitted a paper 23 days ago

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

Ningyu submitted a paper 25 days ago

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

View all activity

Papers

Towards Consistent Video Geometry Estimation

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

View all Papers

ZhejiangUniversity 's papers 21

Submitted by

zhu

Towards Consistent Video Geometry Estimation

Zhejiang University

Submitted by

Ningyu Zhang

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

Zhejiang University

Submitted by

Canyu Zhao

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

Zhejiang University

Submitted by

Ningyu Zhang

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

Zhejiang University

Submitted by

Dewei Zhou

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

Zhejiang University

Submitted by

Shumin Deng

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Zhejiang University

Submitted by

Yuqi

LightThinker++: From Reasoning Compression to Memory Management

Zhejiang University

Submitted by

Ningyu Zhang

SkillNet: Create, Evaluate, and Connect AI Skills

Zhejiang University

Submitted by

Ruisi Zhao

Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models

Zhejiang University

Submitted by

Ningyu Zhang

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

Zhejiang University

Submitted by

Yurun Chen

SafePred: A Predictive Guardrail for Computer-Using Agents via World Models

Zhejiang University

Submitted by

Hanxun Yu

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration

Zhejiang University

CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models

Zhejiang University

Submitted by

Ningyu Zhang

Aligning Agentic World Models via Knowledgeable Experience Learning

Zhejiang University

Submitted by

Ningyu Zhang

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Zhejiang University

Submitted by

leo chen

LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator

Zhejiang University

Submitted by

Chao Xu

Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents

Zhejiang University

Submitted by

Ningyu Zhang

LightMem: Lightweight and Efficient Memory-Augmented Generation

Zhejiang University

Submitted by

Mingyu Liu(SII)

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Zhejiang University

Submitted by

Ningyu Zhang

OceanGym: A Benchmark Environment for Underwater Embodied Agents

Zhejiang University

Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation

Zhejiang University