Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Improving Image-to-Image Translation via a Rectified Flow Reformulation
Borderless Long Speech Synthesis
SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs
Cosmology and modified GW propagation from the BNS mass function at third-generation detector networks
Rethinking MLLM Itself as a Segmenter with a Single Segmentation Token
Morphology-Consistent Humanoid Interaction through Robot-Centric Video Synthesis
dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3
Integrable Systems for Generalized Toric Polygons and Higgsed 5d N=1 Theories
Deep Autocorrelation Modeling for Time-Series Forecasting: Progress and Prospects
Adaptive Greedy Frame Selection for Long Video Understanding
Structure and Classification of Matrix Product Quantum Channels
Giant graviton integrated correlators at finite coupling and all orders in $1/N$
Utility-Guided Agent Orchestration for Efficient LLM Tool Use
Continuous crossover between high-pressure ice phases VII and X driven by monopole screening: a model study
Can QCD Axions Survive the Cosmological Constant Problem?
FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow
Agentic Harness for Real-World Compilers
Ringdown modeling for effective-one-body waveforms in the test-mass limit for eccentric equatorial orbits around a Kerr black hole
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
Repurposing Geometric Foundation Models for Multi-view Diffusion
Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness
Tangent equations of motion for nonlinear response functions
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
On the Role of Batch Size in Stochastic Conditional Gradient Methods
Do World Action Models Generalize Better than VLAs? A Robustness Study
PEARL: Geometry Aligns Semantics for Training-Free Open-Vocabulary Semantic Segmentation
End-to-End Training for Unified Tokenization and Latent Denoising
VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves