Training Software Engineering Agents and Verifiers with SWE-Gym

MAKIEVAL: A Multilingual Automatic WiKIdata-based Framework for Cultural Awareness Evaluation for LLMs

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation

GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Code World Models for General Game Playing

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

Playful Agentic Robot Learning

DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Kairos: A Native World Model Stack for Physical AI

Guava: An Effective and Universal Harness for Embodied Manipulation

Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games

LifeSciBench: Evaluating Language Models on Realistic, Expert-Level Tasks in the Life Sciences

TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Predicting LLM Safety Before Release by Simulating Deployment

Training Software Engineering Agents and Verifiers with SWE-Gym

MAKIEVAL: A Multilingual Automatic WiKIdata-based Framework for Cultural Awareness Evaluation for LLMs

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation

GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Code World Models for General Game Playing

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

Playful Agentic Robot Learning

DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Kairos: A Native World Model Stack for Physical AI

Guava: An Effective and Universal Harness for Embodied Manipulation

Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games

LifeSciBench: Evaluating Language Models on Realistic, Expert-Level Tasks in the Life Sciences

TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Predicting LLM Safety Before Release by Simulating Deployment