Command Palette
Search for a command to run...
Papers
Daily updated cutting-edge AI research papers to help you keep up with the latest AI trends
papers

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Language Models Can Control Their Own Attention






























It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
H3-World: Turning Language Understanding into World Control
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
UI-Venus-2: A Large Language Model for GUI Agents
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
StudentSim: Training LLM-based Student Simulators
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
CogEvol: Towards Efficient and Reliable Learning Environment Generation
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
DreamX-Creator 1.0: Democratizing Native Audio-Video Generation at 2K Resolution
SLIDING-WINDOW BEATS LINEAR ATTENTION
Fast Weight Attention for Continual Learning
SKILL.state: Scalable Long-Horizon Agent Skills
Hydra-0: Action Flow for Generalist World Modeling and Control
J-ZERO: UNIFIED CHALLENGER–SOLVER–JUDGE CO-EVOLUTION FROM ZERO DATA
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
On the Design of Qwen3.8-Next Architecture: Evaluation, Eficiency, and Training Stability
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher