AI

Training a coding model to paint watercolours with TRL and OpenEnv

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

Give Your Coding Agents a Memory You Own

Quiz: Python AI: How to Build a Neural Network & Make Predictions

Check your grasp of how neural networks make predictions in Python, from dot products and activation functions to gradient descent and backpropagation.

Jaime Buelta: The Many Challenges in Integrating Information for AI Agents

Recently I’ve been thinking quite a lot about information availability for agents, and the fact that this is a very difficult and potentially irresoluble problem. Let me try to explain myself. I talked before about a…

I built 47 client-side developer & AI tools because I'm tired of bloated, ad-heavy utility sites

Like most developers, I search Google every single week for quick utilities: Formatting, validating, or minifying dirty JSON Calculating OpenAI & Claude API prompt costs Decoding JWT payloads Converting cURL commands to…

A Storage-Retrieval Gap in Parametric Knowledge Graph Memory

arXiv:2608.25489v2 Announce Type: replace Abstract: Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and exposing source data…

Explainable Information Processing in Particle Swarm Optimization through Landscape and Search Behavior Analysis

arXiv:2509.06272v5 Announce Type: replace-cross Abstract: Swarm-based optimization algorithms have demonstrated remarkable success in solving complex problems, yet their widespread adoption remains limited due to poor…

Sample Complexity of Linear Quadratic Regulator Without Initial Stability

arXiv:2502.14210v4 Announce Type: replace-cross Abstract: Inspired by REINFORCE, we introduce a novel receding-horizon algorithm for the Linear Quadratic Regulator (LQR) problem with unknown dynamics. Unlike prior…

Gradient Prediction with Control Variates in the Cheap-Forward Regime

arXiv:2511.05187v2 Announce Type: replace Abstract: We study whether otherwise-idle inference resources could reduce the scarce-GPU cost of training. Our analysis uses a simulated compute ledger in which fleet work is…

Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing

arXiv:2609.02790v1 Announce Type: cross Abstract: Generative models have been studied experimentally and theoretically as priors for inverse problems such as compressed sensing. Recent work by Gunn et al. studied the…

A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization

arXiv:2609.02107v1 Announce Type: new Abstract: Discrete visual tokenization, predominantly driven by vector, scalar, and product quantization, lacks a unified conceptual framework for understanding quantization…

UE5M3 FP4 Block Scaling for Stable Language Model Pretraining

arXiv:2609.02846v1 Announce Type: new Abstract: Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer Engine \nv{} recipe…

Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling

arXiv:2609.01675v1 Announce Type: cross Abstract: Accurate large-scale wildfire spread modelling requires models that capture both the environmental conditions associated with fire occurrence and the local dynamics of…

Toward Explainable and Policy-Aware AI for Carbon Credit Price Prediction: A Research Framework for Emerging Carbon Markets

arXiv:2609.01765v1 Announce Type: new Abstract: Carbon markets put a price on emissions, yet that price remains hard to forecast. Work in this area clusters on the EU and Chinese schemes, compresses regulatory text into…

oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions

arXiv:2609.02672v1 Announce Type: cross Abstract: Hyper-Connections (HC) replace the single residual stream of a Transformer with $n$ parallel ones, mixing them at every layer with a learned $n \times n$ residual…

Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models

arXiv:2608.21377v2 Announce Type: replace-cross Abstract: Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied primarily in…

What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?

arXiv:2512.24497v4 Announce Type: replace-cross Abstract: A long-standing challenge in AI is to develop agents capable of solving a wide range of physical tasks and generalizing to new, unseen tasks and environments. A…

From Digital to Physical Reservoir Computing: Co-Optimizing Soft Robotic Reservoirs via Dynamics Matching

arXiv:2608.00484v2 Announce Type: replace-cross Abstract: Soft robotic substrates are promising for Physical Reservoir Computing (PRC) because their compliant nonlinear dynamics can provide temporal memory,…

SpecXMaster Technical Report

arXiv:2603.23101v4 Announce Type: replace Abstract: Intelligent spectroscopy serves as a pivotal element in AI-driven closed-loop scientific discovery, functioning as the critical bridge between matter structure and…