Knowledge catalogue
If you missed today's K3 on Fireworks webinar, we've got you covered. We'll be partnering with @arizeai to chat more models on Thursday, August 6th. Sign up below! Next session, August 6 we'll be co l
arXiv:2608.01562v1 Announce Type: new Abstract: Optimal trajectory generation for rigid-body motions on Lie groups can be formulated as a variational problem that minimizes energy functionals defined
arXiv:2608.00107v1 Announce Type: new Abstract: Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an in
In the Medium blog post, 'From MARS to SETOF REFCURSOR: Migrating Multi-Result Stored Procedures to PostgreSQL,' we explored the fundamental architectural differences between SQL Server and PostgreSQL
arXiv:2608.00012v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster
arXiv:2608.01427v1 Announce Type: new Abstract: 3D bin packing rectangular items into standardised containers to maximise space utilisation under geometric shipping automation. Loading a furniture pur
arXiv:2409.15600v3 Announce Type: replace Abstract: A representation of a molecule or material should be invariant to the symmetries of physics, unique, continuous, efficient and general. These proper
arXiv:2608.01810v1 Announce Type: new Abstract: Rubric-based LLM-as-judge pipelines often assume that evaluation criteria provide independent signals. In practice, however, criteria can be behaviorall
arXiv:2608.01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models. Reusing each rollout batch for ad
arXiv:2608.00621v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), whose nodes carry heterogeneous attributes such as text and images over a relational structure, have become a funda
arXiv:2209.03282v5 Announce Type: replace-cross Abstract: Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic resear
arXiv:2606.13993v2 Announce Type: replace Abstract: A crucial aspect of linguistic capability is the ability to trade off between stored representations and abstract knowledge: one must retrieve learn
arXiv:2608.02302v1 Announce Type: cross Abstract: Long-horizon coding-agent trajectories are poorly matched to the credit units available to train on: a single action has no stable value, an episode l
ChatGPT Work was launched by OpenAI on July 9, 2026 as an agent‑oriented knowledge‑work platform that combines chat, Codex tools and cloud agents across fourteen model configurations. Within three wee
arXiv:2607.17017v2 Announce Type: replace-cross Abstract: As scalability becomes increasingly important in recommendation modeling, recent architectures have advanced the modeling of two broad sources
arXiv:2602.10429v2 Announce Type: replace-cross Abstract: AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox with a unified LLM-agent arc
arXiv:2607.28662v1 Announce Type: new Abstract: Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across docu
arXiv:2607.28840v1 Announce Type: new Abstract: Large language models are increasingly deployed in financial applications that combine retrieval, proprietary data, tool use, orchestration logic, monit
Networking and security company Cato Networks Ltd. today introduced Cato Agentic Threat Prevention, a capability that uses autonomous agents to predict the route an attacker is likely to take through
arXiv:2604.05150v2 Announce Type: replace-cross Abstract: We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which wor
arXiv:2607.19345v2 Announce Type: replace-cross Abstract: Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to lon
arXiv:2607.28848v1 Announce Type: cross Abstract: LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below pe
arXiv:2607.28904v1 Announce Type: cross Abstract: This paper presents a speculative Human-Computer Interaction design proposal for encouraging geopolitical reflexivity amongst tech workers at geopolit
arXiv:2607.28971v1 Announce Type: cross Abstract: Contrastive learning is widely used for user modeling in large-scale recommender systems, where standard in-batch negatives implicitly assume universa
arXiv:2607.28750v1 Announce Type: cross Abstract: As mobile applications grow in complexity, traditional End-to-End (E2E) testing frameworks struggle with UI volatility, maintenance overhead, and cros
arXiv:2607.29581v1 Announce Type: new Abstract: A marketplace review photograph is a document: platforms approve refunds on it, and generative models drove the cost of forging one to zero. We study th
arXiv:2607.29627v1 Announce Type: new Abstract: Generative video compositing, which involves inserting external assets seamlessly into existing video sequences, is essential for content creation and v
arXiv:2607.29213v1 Announce Type: cross Abstract: Modern recommender systems in food delivery increasingly leverage multimodal signals, including images, text, and user interaction histories, to enhan
arXiv:2505.21736v2 Announce Type: replace Abstract: Translation equivariance is a central reason convolutional neural networks have been successful in computer vision. Other symmetries, such as rotati
“poorly evidenced sensationalism makes for bad policymaking, politics, philanthropy and much else.” beautiful coda for a weekend in which people went completely nuts without even asking for a control
arXiv:2410.06665v4 Announce Type: replace-cross Abstract: This paper explores the characterization of equivariant linear layers for representations of permutations and related groups. Unlike tradition
The Inference Engineering Masterclass: 10x faster models, quantization, speculative decoding, Rubin, & self-optimizing AI https://www.latent.space/p/inference-eng @Baseten @philipkiely and @waterloo_i
This is a wild result. Locus, the automated research system from @intology, post-trained Qwen3 base models that beat the official human-tuned Qwen3 1.7B Instruct release. SoTA on PostTrainBench! The m
arXiv:2607.28633v1 Announce Type: cross Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly. When prefill and decode run on separate
two weeks ago i went on @swyx's pod and said some things that i... should not have said. a lot has happened since then, i owe you all an apology. i'm sorry that i was right about every single thing. a
To make informed decisions, businesses often need to connect their internal data with public reference data, to create a knowledge graph that connects real-world things and their relationships. Howeve
arXiv:2604.04468v2 Announce Type: replace Abstract: Evaluating retail strategies before deployment is difficult, as outcomes are determined across multiple stages, from seller-side persuasion through
You probably used @FireworksAI_HQ this week. The cool part is that you just did not know you did. 🎆 Open-source models are free, sure... but the hard part is tailoring them so they perform best on you
According to rumors (spread by myself) Le Chaton FAT will be 26T-a3b and I AM READY for it. Let's be real, I can't afford that many 5060Ti, so I got 12x Gen 4 3.2 TB (two per card). This gives me abou
metal: implement DeepSeek V4 hyper-connections (#26459) Implement GGML_OP_DSV4_HC_COMB, GGML_OP_DSV4_HC_PRE, and GGML_OP_DSV4_HC_POST with SIMDgroup register and shuffle optimized kernels. Add Metal d
It's not time to slow down but to accelerate! The recent AI-powered cyberattacks have everyone talking about the risks of AI. We should. But let's not lose sight of the bigger picture! If we work hard
# Running DeepSeek-V4-Flash-0731 (155 GB MoE) on a DGX Spark with vLLM-Moet 2-bit quantization I used Deepseek-v4-Flash-0731 cloud API settig up vllm-moet to run deepseek-v4-flash with MTP locally on
Top eight misconceptions about OpenAI’s amazing new Astra math results. 1. Expertise in one domain does not at all guarantee expertise in all or even most domains. There is an important, principled re
audio.cpp 0.5 is out :) The most fun new model in 0.5 is DramaBox. It is closer to prompt-directed voice acting. DramaBox is built on the LTX-2.3 audio architecture, and prompts can control emotion, d
**Kimi K3 is Moonshot AI’s 2.8‑trillion‑parameter open‑weight language model—the largest ever released—designed for frontier tasks such as long‑horizon coding and deep reasoning.** Its architecture us
so much for the “general” part of general intelligence I have tried many times to get ChatGPT, Claude, Grok or Gemini to write scripts for my YouTube videos. It is still a complete failure. For one th
arXiv:2505.10300v2 Announce Type: replace-cross Abstract: Responsible AI (RAI) efforts increasingly emphasize the importance of addressing potential harms early in the AI development lifecycle through
Artificial intelligence has quickly become a standard part of modern software development. Coding assistants, code completion tools and AI-powered integrated development environments are now widely av
GPU utilization can read healthy while your queue backs up, and a new replica takes minutes to warm. Here's how to pick autoscaling metrics, tune scale-up/down windows, and budget for cold starts on d
SYCL: add oneMKL GEMM flash attention for XMX-accelerated prompt proc… (#25025) SYCL: add oneMKL GEMM flash attention for XMX-accelerated prompt processing fattn-mkl: fix interleaved dst layout in nor
arXiv:2607.27773v1 Announce Type: new Abstract: LLM agents increasingly rely on long-term memory to support multi-session interaction and personalization. However, existing agent memory systems are de
arXiv:2607.28567v1 Announce Type: cross Abstract: Longitudinal causal studies often record histories as irregular functional fragments: laboratory values, physiologic signals, sensor streams, and imag
arXiv:2512.15011v3 Announce Type: replace Abstract: Artificial intelligence (AI) increasingly generates the very content used to train future AI systems. This feedback loop can degrade model quality,
arXiv:2607.27290v1 Announce Type: new Abstract: Modern telecommunication, cloud, and microservice systems emit correlated alarm cascades when components fail. Root cause analysis (RCA) aims to identif
arXiv:2607.26075v1 Announce Type: cross Abstract: We present IDP AutoOpt, an autonomous LLM agent that discovers high-performing configurations for intelligent document processing (IDP) pipelines. Tun
Microsoft Corp.’s LinkedIn is making a concerted effort to combat “AI slop,” or the low-quality, artificial intelligence-generated content that has been increasingly dominating user’s feeds. In a blog
arXiv:2511.21007v2 Announce Type: replace Abstract: Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Est
arXiv:2607.28093v1 Announce Type: cross Abstract: Accurate Surface Solar Irradiance (SSI) estimation is increasingly important for photovoltaic energy monitoring and forecasting. The recently introduc
Just saw this posted by Fal.ai and then by Hailuo themselves, the next video model will be open weight released! Here's the blurb and link to to the feature post: Today, we're launching MiniMax H3, a
https://x.com/MiniMax_AI/status/2083006198828417501?s=20 Quote from their article: Today, we're launching MiniMax H3, a general-purpose multimodal generation model. H3 understands unified context acro