Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Adaptive Memory Admission Control for LLM Agents
Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study
Non-equilibrium bosonization of fractional quantum Hall edges
DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers
Evaluation of Feynman integrals via numerical integration of differential equations
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
Harnessing Synthetic Data from Generative AI for Statistical Inference
Fusion of JWST data - Demonstrating practical feasibility
Latent Policy Steering through One-Step Flow Policies
Accelerating Feynman Integral Evaluation by Avoiding Contour Deformation
OpenFrontier: General Navigation with Visual-Language Grounded Frontiers
Python Bindings for a Large C++ Robotics Library: The Case of OMPL
Non-Euclidean Gradient Descent Operates at the Edge of Stability
FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
Demonstrating Noise-adapted Quantum Error Correction With Break-Even Performance
Biased Generalization in Diffusion Models
TW-Sound580K: A Regional Audio-Text Dataset with Verification-Guided Curation for Localized Audio-Language Modeling
STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks
VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
Crab$^{+}$: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
Dissecting Quantization Error: A Concentration-Alignment Perspective
Nonlinear Dynamics in General Relativity
Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization
Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial
Underrepresented in Foundation Model Pretraining Data? A One-Shot Probe
NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training