Knowledge catalogue
Fireworks AI is now live on EvoSkill v1.3.0! You can now use @FireworksAI_HQ directly with EvoSkill to run fast inference on open models as both the evolution harness backend and the LLM scorer. Along
arXiv:2606.27128v1 Announce Type: new Abstract: Wildfire monitoring from UAVs requires reliable reasoning over complex aerial scenes, where smoke, scale variation, and occlusions often limit RGB-only
arXiv:2606.26938v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have f
arXiv:2606.27199v1 Announce Type: new Abstract: Successful forecasting involves identifying patterns between historical and future states of the world which generalize to future observations. We apply
arXiv:2606.27079v1 Announce Type: new Abstract: In embodied intelligence, safety is a prerequisite for reliable robot deployment in the physical world. Current vision-language-action (VLA) models cont
arXiv:2606.26515v1 Announce Type: new Abstract: Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating it
arXiv:2606.26866v1 Announce Type: cross Abstract: Third-party vendors, such as analytics platforms, cloud services, identity providers, and software suppliers, are increasingly embedded in digital ser
Forward Deployed Engineering is the most critical ingredient for Enterprise AI adoption. It’s why the most important companies on the planet are investing so heavily into it. That’s why we put togethe
arXiv:2606.26636v1 Announce Type: new Abstract: Event cameras asynchronously report brightness changes with microsecond-level temporal resolution, but real event data remain difficult to collect at sc
arXiv:2606.27234v1 Announce Type: cross Abstract: AI nudification uses generative models to create synthetic non-consensual sexually explicit imagery (SNEACI) of real individuals. Prior work has exami
arXiv:2606.26277v1 Announce Type: cross Abstract: Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where p
arXiv:2604.01849v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated exceptional proficiency in code completion, they typically adhere to a Hard Completion (HC) par
arXiv:2606.26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnos
arXiv:2606.26112v1 Announce Type: cross Abstract: Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training cor
Traditional alerting systems often force a compromise: you can either alert immediately on simple, noisy log events, or monitor rigid, pre-configured metrics that fail when faced with data with many u
arXiv:2606.26196v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have recently made remarkable progress in unifying vision-language understanding and reasoning, especially fo
from tokenmaxxing to this in less than three months. anyone who doesn’t see this as affecting Anthropic and OpenAI is not paying attention. UBS says 60% of companies now watching AI budgets are moving
arXiv:2606.26803v1 Announce Type: new Abstract: We present a computational corpus study of vocabulary relationships across eight tradition layers of Bengali and Sanskrit devotional literature spanning
arXiv:2606.26629v1 Announce Type: cross Abstract: Weight-space regularization methods such as Elastic Weight Consolidation (EWC) are the standard approach to catastrophic forgetting in continual learn
from Write & Learn (thx @MilksandMatcha @philipkiely @swyx), my most important takeaway, 𝐛𝐮𝐢𝐥𝐝 𝐚 𝐝𝐞𝐧𝐬𝐞 𝐫𝐞𝐰𝐚𝐫𝐝 𝐟𝐨𝐫 𝐲𝐨𝐮𝐫 𝐰𝐫𝐢𝐭𝐢𝐧𝐠. fun fact. most people know @swyx as the famous podcaster, the AIE godfat
Frontier models are getting really expensive Model providers give us a bunch of features to reduce costs, but the support landscape is….inconsistent We made prompt caching support model-agnostic in de
arXiv:2606.27140v1 Announce Type: new Abstract: We develop the fTNN, a deterministic tensor neural network subspace method for problems involving the fractional Laplacian on bounded domains, taking th
SpaceX conducted a full-duration static fire test of a single Starship engine, demonstrating the vehicle's propulsion system capability on the test stand. This test, announced by Elon Musk, represents
arXiv:2606.26719v1 Announce Type: new Abstract: Unlearnable examples (UEs) protect training data by injecting imperceptible perturbations so that models fail to extract exploitable representations. In
Fun fact: Dario once delayed the release of GPT-2 back at OpenAI, claiming it was too dangerous Dario fearmogged so hard that global AI progress got halted They could have quietly released it as Opus
“Gary Marcus … says that investments into scaling AI is the “greatest capital misallocation in history” which leaves everyone “on the hook”. However, he also says that it is still early days for the A
Gary Marcus discusses fundamental challenges and limitations in current AI systems during an interview, likely covering topics such as the gap between narrow and general intelligence, reasoning limita
arXiv:2606.26923v1 Announce Type: new Abstract: Vision-language models (VLMs) often produce hallucinated or inconsistent outputs, where text and images are not properly aligned. Addressing this issue
arXiv:2606.26287v1 Announce Type: new Abstract: With the increase in model parameters and training data, the instruction following and generalization capabilities of Large VisionLanguage Models (LVLMs
arXiv:2602.00813v5 Announce Type: replace Abstract: Composed Image Retrieval (CIR) is the task of retrieving a target image from a database using a multimodal query, which consists of a reference imag
arXiv:2606.26660v1 Announce Type: cross Abstract: Triangulations, i.e., well-structured decompositions of geometric objects into triangle-like pieces, are central objects in many domains of mathematic
arXiv:2606.26111v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) has enabled users to synthesize music with text prompts, combining copyrighted lyrics, AI-composed melodies
arXiv:2606.27294v1 Announce Type: cross Abstract: Analog hardware platforms such as coupled oscillators and Analog Ising Machines naturally solve differential equations at a fraction of the energy cos
arXiv:2606.26899v1 Announce Type: new Abstract: Embedding-based retrieval ranks items by their similarity to a query in a shared vector space and usually aims to return the highest-scoring items. In m
arXiv:2506.15681v4 Announce Type: replace Abstract: Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source sy
arXiv:2606.26917v1 Announce Type: cross Abstract: Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or mi
arXiv:2606.26125v1 Announce Type: cross Abstract: Emerging 6G and edge-intelligent networks require effective and balanced routing algorithms among varied and spatially distributed devices. Existing f
arXiv:2606.26973v1 Announce Type: new Abstract: Open-set semi-supervised learning aims to leverage unlabeled data that may contain out-of-distribution outliers while maintaining performance on in-dist
arXiv:2606.26399v1 Announce Type: new Abstract: We study certain extremal problems in combinatorial geometry that ask about configurations of points in an n imes n grid that satisfy strict, global geo
arXiv:2606.20390v2 Announce Type: replace Abstract: Automated skin cancer classification from dermoscopic images remains challenging due to heterogeneous lesion structure, strong intra-class variabili
This appears to be a celebratory post by David Ha about a goal scored in a Japanese soccer/football context, likely sharing enthusiasm about a sporting achievement or milestone related to Japan's foot
Sonya Huang shared a post about a camping trip to Sequoia National Park, likely including photos or updates from her outdoor experience. The post was made on X (formerly Twitter) and appears to be a c
Good new first: Sol is a smart, efficient, and a significant step forward. It is the same price as GPT-5.5. Also launching in the GPT-5.6 family is Terra, with 5.5-level performance at half the price.
Good way to frame it. Also, if even one person had died, we would know who they were! Not one person has died from stopping waste & fraud at USAID! Obviously. One of the reasons that I don't accept th
arXiv:2606.26298v1 Announce Type: new Abstract: Autonomous AI agents may begin to perform consequential, irreversible actions such as clinical prescribing and production software deployment. This pape
GPT-5.6 Sol represents OpenAI's latest advancement in AI capabilities, specifically optimized for cybersecurity applications. The model demonstrates improved performance-efficiency tradeoffs, particul
OpenAI: GPT-5.6 Sol matches Mythos Preview on ExploitBench, adds Ultra mode with subagents for complex workflows, and max reasoning for deep problem-solving — We're beginning a limited preview of the
GPT‑5.6 Sol launches with our most robust safety stack yet. We strengthened real-time protections against high-risk cyber activity and repeated misuse, then spent weeks hardening the system with human
arXiv:2405.11454v3 Announce Type: replace Abstract: We study gradient testing and gradient estimation of smooth functions using only a comparison oracle that, given two points, indicates which one has
arXiv:2606.27202v1 Announce Type: new Abstract: Graph neural networks have moved from a niche representation-learning technique to the default model class wherever data carry relational structure. The
arXiv:2606.12816v3 Announce Type: replace-cross Abstract: Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by s
Great experiment testing how good AIs are getting at very ambitious end-to-end coding tasks. Opus 4.7, in 14 hours, was able to build a software package that would take 2-17 weeks of human engineering
Great to see the new GPT-5.6 models finally announced. Sad to see this new release strategy where only a select few get access initially. Not a win for our industry IMO. Open-source AI must win! Intro
Elon Musk claims that Grok, the AI assistant developed by his company xAI, maintains balanced perspectives and avoids excessive bias in its responses. The statement reflects Musk's positioning of Grok
arXiv:2606.27326v1 Announce Type: cross Abstract: Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fl
arXiv:2606.26643v1 Announce Type: new Abstract: This paper focuses on the hardware specifications required for a table tennis robot to beat professional players. After analyzing the motions of elite p
arXiv:2606.27187v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have recently shown immense potential in automated content moderation, sparking growing interest in developing ha
arXiv:2506.07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, th
Have been taking different local open-weight LLMs for a test drive in different harnesses (Qwen-Code, Codex, Claude Code). 30B Mixture-of-Expert models are kind of a nice sweet spot and can solve chal
It’s been hot in London this week. Really hot. A dangerous heat wave has hit Western Europe. Yesterday, the UK recorded its highest ever June temperature at 36.1 °C (about 97 °F). But as the weather a