Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
Agents of Chaos
How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1
SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model
World Guidance: World Modeling in Condition Space for Action Generation
Solaris: Building a Multiplayer Video World Model in Minecraft
ConstraintBench: Benchmarking LLM Constraint Reasoning on Direct Optimization
Test-Time Training with KV Binding Is Secretly Linear Attention
Generative Recommendation for Large-Scale Advertising
PyVision-RL: Forging Open Agentic Vision Models via RL
veScale-FSDP: Flexible and High-Performance FSDP at Scale
On Data Engineering for Scaling LLM Terminal Capabilities
OmniGAIA: Towards Native Omni-Modal AI Agents
GeoWorld: Geometric World Models
Aletheia tackles FirstProof autonomously
LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
SkillOrchestra: Learning to Route Agents via Skill Transfer
Imagination Helps Visual Reasoning, But Not Yet in Latent Space
Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
The Trinity of Consistency as a Defining Principle for General World Models
Some Simple Economics of AGI
Muon+: Towards Better Muon via One Additional Normalization Step
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors
GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training
Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem
Interleaved Head Attention
Revisiting Text Ranking in Deep Research
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization