Not all tokens contribute equally to diffusion learning

TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification

Towards Generalizable Robotic Data Flywheel: High-Dimensional Factorization and Composition

Hessian-informed machine learning interatomic potential towards bridging theory and experiments

SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

Development and large-scale benchmarks of a protein-ligand absolute binding free energy toolkit

Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression

Mixture-of-Depths Attention

Disentangling Tensor Network States with Deep Neural Network

Permutation invariant multi-scale full quantum neural network wavefunction

Learn Hard Problems During RL with Reference Guided Fine-tuning

How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation