Frozen in Place
βalgorithms
Flag this post
We found embedding indexing bottleneck in the least expected place: JSON parsing
β±οΈComputational Complexity
Flag this post
H-FA: A Hybrid Floating-Point and Logarithmic Approach to Hardware Accelerated FlashAttention
arxiv.orgΒ·11h
π¨Computer Graphics
Flag this post
PAINT25 Invited Talk transcript: βNotational Freedom via Self-Raising Diagramsβ
programmingmadecomplicated.wordpress.comΒ·4h
π¬Static Analysis
Flag this post
What Are Auto-regressive Models? A Deep Dive and Typical Use Cases
blog.pangeanic.comΒ·1d
πOptimization
Flag this post
Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
arxiv.orgΒ·11h
Ξ»Functional Programming
Flag this post
Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems
arxiv.orgΒ·11h
πOptimization
Flag this post
π Brent's Algorithm Explained β Faster Cycle Detection for Beginners
βalgorithms
Flag this post
IVGAE-TAMA-BO: A novel temporal dynamic variational graph model for link prediction in global food trade networks with momentum structural memory and Bayesian o...
arxiv.orgΒ·11h
πΈοΈGraph Theory
Flag this post
This is a description of a test for markov chain program in a book I'm reading...
βalgorithms
Flag this post
Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
arxiv.orgΒ·11h
Ξ»Functional Programming
Flag this post
Token-Regulated Group Relative Policy Optimization for Stable Reinforcement Learning in Large Language Models
arxiv.orgΒ·11h
πOptimization
Flag this post
Gated DeltaNet (Linear Attention variant in Qwen3-Next and Kimi Linear)
πOptimization
Flag this post
flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R
arxiv.orgΒ·11h
Ξ»Functional Programming
Flag this post
LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers
arxiv.orgΒ·11h
πOptimization
Flag this post
Prog8
π»programming
Flag this post
AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
arxiv.orgΒ·11h
πOptimization
Flag this post
DynBERG: Dynamic BERT-based Graph neural network for financial fraud detection
arxiv.orgΒ·11h
πΈοΈGraph Theory
Flag this post
Loading...Loading more...