AI Intelligence Archive

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

When an AI agent commits a change to code, it makes a claim about what it changed: "fixed typos" or...

Do you also hate upgrading Angular versions? Because I do. I maintain a few open-source projects, and...

What speculative decoding is, how Gemma 4's multi-token prediction drafter rides on the main model, why you would add one, and an exact Q4_0 repack of Google's QAT drafters on Hugging Face that cuts the file to 60% of the size and the memo…

In Part 1, I wrote about the uncomfortable part of AI-assisted engineering: the tools are becoming...

https://x.ai/bot/plugin/9717366

@aiDotEngineer @vikhyatk 提到了

Why do 200-line agent prompts, Asimov's Three Laws, and sequential pre-landing checklists all fail the same way? How Fernando Flores's 1986 Committed Speech, Nuel Belnap's 1977 4-Valued Logic, and Tony Hoare's 1978 CSP turned our Makefile …

Mobile Manipulation (MoMa) is a cornerstone of autonomous robotic systems, yet real-world fine-tuning remains a formidable challenge because of high-dimensional action spaces and intricate coupling between heterogeneous modules. In this pa…

Recent advances in robot learning have driven rapid progress in humanoid control, enabling increasingly agile behaviors in the real world. However, humanoid control networks are typically obtained through conventional training procedures, …

Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused. P…

Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed sizes (e.g., S, B, L), forcing users to commit to a model bas…

An agentic market is a decentralized serving-time market where AI agents bid to claim each user prompt. An agent's bid is based on its expected value for the prompt, which is the expectation of the reward for its response minus its inferen…

We introduce Continuum Attention (CA), a causal Transformer attention operator that replaces discrete key and value lookup with integration over a continuous, piecewise linear memory curve. Each query induces an exponential relevance densi…

Current approaches for steady partial differential equations surrogate models on unstructured meshes apply a single mixing mechanism to the whole solution. This paper proposes an architecture that partitions the solution among vanilla tran…

Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remain challenging and offer a demanding nex…

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...