AI Intelligence Archive

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

I gave Claude Code shell access to a side project last spring and watched it debug a failing OpenAI...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. I have...

We all have an engineering "horror" story. You know, the one you actually had to live through. Like...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. Draft...

Two companies. Same AI mandate, same quarter, same budget for licenses. One ends the year shipping...

Building on the web these days is as easy as using the next-best AI code generator. AI Agents now...

Publisher licensing agreements are becoming an important part of the information ecosystem behind...

Gradium open-sourced Phonon, its on-device TTS engine (https://gradium.ai/phonon). That matters less because of the model than because of what it signals: on-d…

When I wrote code by hand, a change took me hours. By the time it was done, I knew it by heart: what...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

Your Agent Deleted the Wrong Directory at 3 A.M. — and the Prompt Said "Be Careful" Every...

Perplexity 登陆 iPhone Duo

Most LLM features I see in production use one model for everything. It is usually the strong,...

OpenAI has changed how it trains and evaluates its frontier models, removing live internet access and...

The read path in Trip Workbench can erase a person’s unsaved purpose without sending a write. In a...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

I made a Claude Code plugin called Token Beggar, and today I released version 0.3.0 of it. I kept...

This article argues that instruction-fine-tuned language models should be understood as implementing a genre, what is proposed as the instructional-conversational genre. This genre is an amalgamation of discursive language from prior conve…

Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult. Vis…

Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions. Existing robust RL algorithms offer a rich set of mechanisms and principles, yet two major bar…

Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a complete robot setup and places the burden of coordinating many fing…

Few-shot industrial anomaly detection requires modeling category-specific normality from only a handful of defect-free images. Common approaches tie inference to stored exemplars, impose rigid linear structure, or risk reproducing anomalou…

Designing a progress-aware execution controller for agentic systems. Imagine asking an AI research...

Personal email agents decide, for every message, what it is, whether it is urgent, whether to draft a reply, create a task, or ignore it. Their error rate is rarely measured: the stored labels were written by the system itself. We present …

Reinforcement learning for large language models often uses separate systems for inference and training. Even with identical weights and BF16 tensors, implementation differences can make an intended on-policy update off-policy and destabil…

Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measurement targets and discrete token-based numerical prediction. Methods: Thi…

Large language model (LLM) platforms introducing advertising must decide how much capability ad revenue should fund and what consumers should pay to avoid ads. We study a monopolistic platform that jointly chooses costly response quality, …

Generative recommendation with semantic IDs represents each item as a sequence of discrete codes derived from its semantic representation and predicts these codes to generate recommendations. Existing semantic-ID recommenders are typically…

Vision-Language-Action (VLA) models perform well on robotic manipulation, yet remain brittle once their own actions carry them into states their training data barely covers. Recovering from such failures usually requires recovery demonstra…

We study the fundamental problem of PAC learning positive linear combinations of $k$ arbitrary ReLU activations on $\mathbb{R}^d$ with respect to the Gaussian distribution, in $L_2$ loss. We give the first fully-polynomial time algorithm f…

Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resources and compact embedding models. We present Yalda Embedding, …

State inference and parameter learning for nonlinear filters is a core computation for scientific machine learning with varied applications in engineering and neuroscience. The unnormalized filtering distribution is governed by the Zakai e…

Modern language models rely on subwording tokenization to define the discrete units of input processing, typically using methods like Byte Pair Encoding (BPE) that treat whitespace as a fixed semantic boundary. This design is inherently li…

Statement autoformalization translates mathematics from natural language into a proof assistant such as Lean 4, and models now do it at scale. As provers get stronger, the burden of correctness shifts from the proof to the statement, that …

Physics-constrained machine learning (PCML) integrates domain knowledge, first-principles, and physical constraints into AI/ML models. In this work, we present a step-by-step tutorial of a modular PCML framework, KKT-HardNet, and illustrat…

Regularised reinforcement learning (RL) algorithms rely on estimators, like Monte Carlo tree search or one-step look-ahead, to provide policy, value, or Q-value estimates in training and inference. However, existing bandit-based estimation…

Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We prove that this construction is structurally limited: any Lipschitz location encoder produ…

Large Language Models (LLMs) are increasingly used to optimize code for performance. This practice often assumes that improvements in execution speed naturally translate into overall lower energy consumption. We challenge this assumption e…