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

Can Agent Conquer Web? Exploring the Frontiers of ChatGPT Atlas Agent in Web Games

Kimi Linear: An Expressive, Efficient Attention Architecture






























Emu3.5: Native Multimodal Models are World Learners
The End of Manual Decoding: Towards Truly End-to-End Language Models
Human-AI Complementarity: A Goal for Amplified Oversight
GPTOpt: Towards Efficient LLM-Based Black-Box Optimization
VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning
Reasoning-Aware GRPO using Process Mining
Scaling Latent Reasoning via Looped Language Models
ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
Uniform Discrete Diffusion with Metric Path for Video Generation
Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents
RoboOmni: Proactive Robot Manipulation in Omni-modal Context
AgentFold: Long-Horizon Web Agents with Proactive Context Management
Tongyi DeepResearch Technical Report
InteractComp: Evaluating Search Agents With Ambiguous Queries
VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT
TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting
FARMER: Flow AutoRegressive Transformer over Pixels
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
ReCode: Unify Plan and Action for Universal Granularity Control
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation
DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection
Sparser Block-Sparse Attention via Token Permutation
A Definition of AGI