AI Intelligence Archive

Long contexts enlarge key--value (KV) caches, increasing memory use and attention costs during generation. Compressing these caches must preserve information for unseen questions. We introduce **Latent Compaction**, which learns a compact …

Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make …

We introduce a novel method for verifying Lean formalizations that goes beyond LLM-judged faithfulness. Unlike most verification methods, which rely on LLMs or trained models, our method combines LLM-based semantic review with mechanical n…

On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix the student writes. We call this property the recover…

Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or validate comparisons with statistical significance. We present Manacá-1B-Instruct-2, the seco…

https://x.ai/news/grok-voice-3#used-by-millions-of-customers-at-tesla--spacex

Automated research with LLM agents has shown promising results in various domains. Through iterative refinement and scored verifiers, LLM agents are capable of discovering new ideas. There are different ways to scale automated research: le…

3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models. Previous methods either leverage large language models to directly …

Understanding the social intelligence of large language models (LLMs) is increasingly important for applications involving human-AI interaction and multi-agent environments. Social intelligence comprises two aspects: cognitive intelligence…

Potato is an important food-security crop in Ethiopia, but its production is affected by foliar diseases, particularly early blight and late blight. This study develops a lightweight convolutional neural network (CNN) to classify potato le…

Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. Interest in this capability is burgeoning, as models are increasingly asked to produce charts, webpages, animations, and se…

Relational deep learning has emerged as a powerful paradigm for learning end-to-end predictive models over relational databases by representing them as temporal heterogeneous graphs. Recent advances based on graph neural networks and Trans…

We introduce an approach for self-supervised representation learning designed to be used as a tokenizer for generative modeling. Our objective supervises a representation loss by factorizing the pointwise mutual information of the data, wh…

@AnthropicAI - 排行榜：https://arcprize.org/leaderboard - 复现公开结果：https://github.com/arcprize/arc-agi-benchmarking - 测试政策：https://arcprize.org/policy - Haiku 5.5 完整结果：https://arcprize.org/results/anthropic-claude-haiku-5-5

Cool （引用推文Stories：grok bot pretty much replaced dots and muse for running my business... here is why : insanely simple to set up, a MASSIVE plugin library, generous usage. here's everything i use and what it costs: required ($165/mo + whop's cu…

https://x.com/i/broadcasts/1AJEmvrjaaXJL

My entry for the Hacktoberfest Open-Source AI Challenge, Week 2 (Side Hustle). A reseller I know got...

今天就可以在这里试用，前两个月 33% 折扣。 Video to Video： https://fal.ai/models/mirelo-ai/sfx2.0/video-to-video Video to Audio https://fal.ai/models/mirelo-ai/sfx2.0/video-to-audio Text to Audio： https://fal.ai/models/mirelo-ai/sfx2.0/text-to-audio

Anekha Sokhal spent nearly a decade trading energy derivatives at JP Morgan, then came to the US on a...

AI engineers spend enormous amounts of time tweaking small things to achieve bigger gains. Energy is...

When a coding agent investigates a production bug, it might need to read a repository, query logs,...

In the high-stakes world of enterprise AI engineering, the default assumption is that reliability...

Deeply understand the task at hand The biggest mistake teams make with agents is...

In audit, the opinion is the product, and an opinion is only as good as its basis. Being right isn’t...

Have you ever told your AI agent something important, only to realize a few conversations later that...

By Ryan Swift Yesterday, Google finally released its Gemini 4 Argon model for public use. It’s...

A scan of the Slack channels for a recent private equity deployment of Clonal (our operational...

Google mapped the complete male fruit fly brain, and my first question to an agent was “Can this run...

We spent the past few months on a question that sounds simple: what does it actually take to move a...

Many engineers rightfully view every step in a financial workflow as a potential point of failure,...

For financial technology institutions operating at enterprise scale, the initial wave of Generative...

The biggest design shift of the AI era isn’t about who writes the code. It’s about how long the code...

Getting an LLM-powered feature to work in a demo takes an afternoon. But getting it to produce the...

Someone built a torture chamber for small AI models, and the internet wanted it gone. I went through...

Imagine spending weeks agonizing over every single paragraph, polishing every example, and pouring...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...

Intro AI Avatar is a free app where your VRoid (VRM) avatar cheers you with all its...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...

The best thing I shipped last year was a diff that deleted more than it added. I don't mean that as...

Mathematical research drives scientific discovery, and recent advances in AI for mathematics have shown that language-model agents can solve challenging problems and develop substantial mathematical proofs. Yet much of today's AI-for-mathe…