Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
ARTT: Augmented Reverberant-Target Training for Unsupervised Monaural Speech Dereverberation
Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
Attention Sinks Induce Gradient Sinks
dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction
Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding
RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing
GWTC-4.0: Tests of General Relativity. I. Overview and General Tests
SSP-SAM: SAM with Semantic-Spatial Prompt for Referring Expression Segmentation
V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
Anticipatory Planning for Multimodal AI Agents
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Time-Multiplexed Distributed Quantum Sensing
$R$-equivalence on Cubic Surfaces I: Existing Cases with Non-Trivial Universal Equivalence
OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation
HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory
When Does Sparsity Mitigate the Curse of Depth in LLMs
Continually self-improving AI
Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
FinTradeBench: A Financial Reasoning Benchmark for LLMs
Accelerated Rydberg-EIT quantum memory via shortcuts to adiabaticity
Workers' Incentives and the Optimal Taxation of AI
NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data
DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving
End-of-the-World Singularities: The Good, the Bad, and the Heated-up
X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving