Zhejiang University

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Ningyu submitted a paper about 12 hours ago

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

Canyu submitted a paper 22 days ago

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

Ningyu submitted a paper 24 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

submitted a paper to Daily Papers about 12 hours ago

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

Paper • 2605.30219 • Published 1 day ago • 13

submitted a paper to Daily Papers 22 days ago

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

Paper • 2605.06507 • Published 23 days ago • 40

submitted a paper to Daily Papers 24 days ago

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

Paper • 2605.00877 • Published Apr 25 • 15

submitted a paper to Daily Papers about 1 month ago

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

Paper • 2604.14258 • Published Apr 15 • 23

submitted a paper to Daily Papers about 2 months ago

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

Paper • 2604.06870 • Published Apr 8 • 43

submitted a paper to Daily Papers about 2 months ago

LightThinker++: From Reasoning Compression to Memory Management

Paper • 2604.03679 • Published Apr 4 • 38

submitted a paper to Daily Papers about 2 months ago

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Paper • 2604.04804 • Published Apr 6 • 35

submitted a paper to Daily Papers 3 months ago

SkillNet: Create, Evaluate, and Connect AI Skills

Paper • 2603.04448 • Published Feb 26 • 94

submitted a paper to Daily Papers 4 months ago

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

Paper • 2602.01725 • Published Feb 2 • 1

submitted a paper to Daily Papers 4 months ago

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

Paper • 2602.04735 • Published Feb 4 • 15

submitted a paper to Daily Papers 4 months ago

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

Paper • 2601.22674 • Published Jan 30 • 5

submitted a paper to Daily Papers 4 months ago

Aligning Agentic World Models via Knowledgeable Experience Learning

Paper • 2601.13247 • Published Jan 19 • 15

submitted a paper to Daily Papers 5 months ago

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Paper • 2601.05905 • Published Jan 9 • 21

authored a paper 5 months ago

SpatialTree: How Spatial Abilities Branch Out in MLLMs

Paper • 2512.20617 • Published Dec 23, 2025 • 44

submitted a paper to Daily Papers 6 months ago

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

Paper • 2512.10605 • Published Dec 11, 2025 • 7

authored 5 papers 6 months ago

GaitGCI: Generative Counterfactual Intervention for Gait Recognition

Paper • 2306.03428 • Published Jun 6, 2023

GVDIFF: Grounded Text-to-Video Generation with Diffusion Models

Paper • 2407.01921 • Published Jul 2, 2024

Group Diffusion Transformers are Unsupervised Multitask Learners

Paper • 2410.15027 • Published Oct 19, 2024

ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers

Paper • 2412.12571 • Published Dec 17, 2024 • 8

IDEA-Bench: How Far are Generative Models from Professional Designing?

Paper • 2412.11767 • Published Dec 16, 2024