shanghai ailab

non-profit

AI & ML interests

None defined yet.

Recent Activity

xyingzhang submitted a paper about 7 hours ago

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Elliott submitted a paper 29 days ago

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

UML submitted a paper about 1 month ago

SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

View all activity

Papers

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

DeepSight: An All-in-One LM Safety Toolkit

View all Papers

ShanghaiAiLab 's Papers 17

Submitted by

xyingZHANG

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Submitted by

Lijun Li

DeepSight: An All-in-One LM Safety Toolkit

Submitted by

Jianhao Yan

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

Submitted by

MulinYu

SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

Submitted by

MulinYu

PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction

Submitted by

Lijun Li

Toward Efficient Agents: Memory, Tool learning, and Planning

Submitted by

Lijun Wu

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch

Submitted by

Jiaxuan Lu

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning

Submitted by

Ivan Tang

Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation

Submitted by

Yuzhe Gu

OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification

2

Submitted by

Yuzhe Gu

Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving

4

Submitted by

Yuzhe Gu

Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning

Submitted by

Xiaoye Qu

VideoSSR: Video Self-Supervised Reinforcement Learning

Submitted by

Weida Wang

Chem-R: Learning to Reason as a Chemist

Submitted by

Ganlin Yang

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

Submitted by

MulinYu

ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation

Submitted by

L

BRIDGE - Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation