The Archive

Geometric Coding Theorem: establishes symmetry priors as universal lower semi-computable semi-measures for fix-retractable symmetry groups.

Neural-symbolic framework for automatic generation of multimodal analytic geometry problems, addressing precision gaps in diagram generation for math reasoning.

LLM predictions flip substantially under task-irrelevant context despite stable aggregate accuracy, exposing fragility masked by benchmark metrics.

Recommender-system research for Vietnamese remains limited by the absence of a public, well-documented hotel interaction resource. Building such a resource is challenging for three reasons: cross-platform hotel names must be reconciled before interactions are comparable…

Coding AI agents are becoming practical operators for long-running machine learning (ML) workflows. They can inspect repositories, set up runtimes, resolve... Coding AI agents are becoming practical operators for long-running machine learning (ML) workflows. They can inspect…

In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters. In such settings Reinforcement Learning algorithms typically determine parameters with one-shot…

CoCo loss function for learning normalized embeddings with intra-class collapse and inter-class contrast, with theoretical analysis vs. cross-entropy.

ANGLE framework applies generative learning for non-parametric distributional regression on circular/angular data in computer vision and biology.

KLLMs pretraining paradigm suppresses parametric recall via entity anonymization, forcing evidence-grounded reasoning over memorized knowledge.

PixelLoop introduces pixel-space loop closures for topological navigation, extending SLAM-style corrections to dense relative geometry representations.

Framework evolves evaluation metrics alongside agent skills using evolutionary search over drawback detectors, enabling self-improving systems without pre-defined oracles.

While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without explicit mechanisms for geometric consistency, leading to spatial hallucinations such as duplicated structures and misaligned…

Empirical study of 188 grokking runs shows representational priors must match task-relevant feature families to enable generalization; label-free invariance priors work via commutation symmetry.

OpenAI guidance on ROI metrics for enterprise AI agent deployments: measuring work-per-dollar, efficiency gains, and workflow scaling.

Codex usage grew 10x to 7M users in 6 months; article questions whether it has outpaced Claude Code amid sparse adoption metrics.

Study compares production vs. perception asymmetry in Llama-3.1-8B via token probability analysis, finding LLMs lack functional production-perception distinction.

Camera-only ground vehicle recovery using visual odometry for line-following robots in warehouses.

Graph neural network with multi-scale features for accelerating fluid dynamics simulations in complex geometries.

Geometric Dimensionality Regularization (GeomDR) controls grokking timing by leveraging representation collapse as predictive signal.

SKooP combines Koopman autoencoder with morphological symmetries to improve RL sample efficiency for legged robot locomotion.

VGGT geometric foundation model encodes co-visibility of image pairs as emergent 3D-aware representation, useful for reconstruction and robotic localization.

Multimodal RL reward hacking in MLLMs via visual misalignment; introduces NRFR metric to measure failures in improved-reward samples across VQA and chart tasks.

Microsoft may once again be struggling to keep up with its own climate goals, according to its 2026 sustainability report. As reported by GeekWire, the report states that Microsoft's carbon emissions increased 25 percent in 2025, totalling 34 million metric tons "without select…

Shows quantization from 8-bit to 2-bit induces behavioral divergence in LLMs beyond accuracy/perplexity metrics; introduces correctness agreement metric.

Multi-modal 3D terrain reconstruction for wildfire-prone regions using image-based methods with DEM priors as geometric guidance.

SolarChain-Eval benchmarks autonomous agents in decentralized energy markets with physics constraints and trustworthiness metrics.

SMetric proposes session-centric LLM scheduling for agentic workloads with 80%+ KV-cache reuse, shifting optimization from latency to tokens-per-second.

Riemann normal coordinates improve Levenberg-Marquardt optimization for nonlinear least-squares via geodesic acceleration.

Asymmetric focal loss improves graph neural network prediction of polypharmacy drug-drug interactions via difficult-example emphasis.

GIFT proposes geometry-informed gradient quantization for low-precision communication during LLM pretraining, addressing scaling bottlenecks in distributed training.