Knowledge catalogue
Grok 4.6 is my daily driver now. This is why: When I’m using interactive agents in a CLI/terminal (or even Slack), what matters most to me is speed & token throughput. Intelligence and differences in
a very modular harness 👌 🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT lic
Hey everyone, I'm trying to get a better sense of where classic ML fits in the current landscape, dominated by LLMs and deep learning. Are supervised and unsupervised learning still considered importa
arXiv:2608.12710v1 Announce Type: new Abstract: Muon, a more recently developed optimizer, is useful for matrix-wise models in AI areas. Although many works have studied Muon and its variants, these m
Ollama now supports the DeepSeek Harness. ollama launch dsh Run it completely in your own environment. It comes with Ollama's web search pre-installed. You can use its trajectory view to see what is h
arXiv:2608.12984v1 Announce Type: cross Abstract: Long-form research reports generated by large language models drift, contradict themselves, and lose provenance: the same metric appears with differen
arXiv:2608.13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, b
arXiv:2604.03181v2 Announce Type: replace-cross Abstract: Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing pol
arXiv:2608.11226v1 Announce Type: new Abstract: Reinforcement-learning post-training dominates modern language-model development, yet its power behavior on GPU hardware has not been characterized, and
🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license. 🔹 Powered by the Co
arXiv:2608.11219v1 Announce Type: new Abstract: Automatic Prompt Optimization (APO) often rewrites prompts monolithically, which can improve one behavior while degrading others. We present SAPO, a seg
🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license. 🔹 Powered by the Co
arXiv:2608.10299v1 Announce Type: new Abstract: Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, s
I’m not super knowledgeable of the entire AI industry, but as we see this industry grow and the Cold War that is happening between the US and China on AI development, I can’t help but notice what US c
arXiv:2608.10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that sys
Hey Folks, I've been making quants for a while - recently I took a short break to get into hardcore research (submitted my first EMNLP paper during it!). Along the way, I built up a little arsenal of
We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B
arXiv:2608.08156v1 Announce Type: new Abstract: In evolutionary algorithms powered by language models, the LLM acts as a single operator that simultaneously updates structural components (like control
arXiv:2608.08898v1 Announce Type: cross Abstract: Characterising optimisation problem instances is a fundamental part of understanding the behaviour and performance of different algorithms as well as
arXiv:2608.08126v1 Announce Type: cross Abstract: Credit scoring increasingly relies on models whose decision logic cannot be read off their parameters, in tension with supervisory expectations that a
arXiv:2608.08163v1 Announce Type: new Abstract: The convergence of the Metaverse and Large Language Model (LLM)-based AI agent is catalyzing a shift toward autonomous, immersive, and personalized peda
arXiv:2608.09930v1 Announce Type: cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expecte
arXiv:2608.09555v1 Announce Type: new Abstract: External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effe
arXiv:2601.14609v2 Announce Type: replace-cross Abstract: Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environm
arXiv:2608.08466v1 Announce Type: new Abstract: Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the harne
arXiv:2608.08825v1 Announce Type: cross Abstract: Foundation models for time series forecasting demonstrate impressive zero-shot generalization but often underperform on specialized domains such as hi
Just downloaded the model, UD-Q5_K_XL quant, asked it to generate a long story to test out reasoning and speed with dflash (super fast btw, ~ 90 to 160 tok/s on a 5090 depending on task) and was surpr
arXiv:2608.07712v1 Announce Type: cross Abstract: A predictive model receives a self-supervised signal whenever the consequence of an action is observed. Using that signal after deployment is difficul
arXiv:2608.09590v1 Announce Type: new Abstract: Learning reliable correspondences between images and point clouds is fundamental for 2D-3D matching. Despite recent progress in detection-free methods,
arXiv:2608.07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collect
Benchmarked Muse Glimmer 30B on my RTX 5090 (32GB), 262k context, UD-Q5_K_M + dflash-kquant + mmproj. Workload Stock master + DFlash ngram-simple PR #26842 + DFlash Code patch 78 t/s 57 t/s 220-253 t/
arXiv:2602.20860v2 Announce Type: replace Abstract: While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect n
Hey LocalLlaMa, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots a
arXiv:2608.07167v1 Announce Type: new Abstract: Giving an AI agent the ability to send emails, query databases, or execute commands is useful--until the agent is tricked into doing something it should
arXiv:2509.26331v2 Announce Type: replace Abstract: The rapid advancement of LLMs sparked significant interest in their potential to augment or automate managerial functions. One of the most recent tr
arXiv:2608.06105v1 Announce Type: cross Abstract: Artificial Intelligence (AI)-assisted navigation can help Arctic shipping adapt to rapidly changing sea-ice conditions, but reliable deployment requir
arXiv:2604.01170v2 Announce Type: replace-cross Abstract: While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute
OpenAI says it is pausing 'internal activities' around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows i
arXiv:2608.06015v1 Announce Type: cross Abstract: Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch,
arXiv:2608.06288v1 Announce Type: new Abstract: This work presents a novel attention-based framework for estimating the Individual Probability of Treatment Benefit (IPTB) in survival analysis contexts
Anthropic is hiring a custom silicon team to design proprietary chips that will power its Claude models, while still planning a multi‑chip strategy that mixes internally designed hardware with compone
arXiv:2604.01730v2 Announce Type: replace Abstract: This paper investigates Koopman operator-based approaches for multivariable control of a two-spool turbofan engine. A physics-based component-level
arXiv:2607.18559v2 Announce Type: replace-cross Abstract: Gaussian graphical model selection is usually studied under independent sampling, but in many applications the data arise as a single trajecto
arXiv:2608.03524v1 Announce Type: new Abstract: AGENTONOMICS is a framework that treats AI agents as economic entities that can be designed, managed, and governed through an integrated management arch
arXiv:2602.17976v2 Announce Type: replace-cross Abstract: In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to ident
arXiv:2608.03926v1 Announce Type: cross Abstract: Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensi
arXiv:2608.02606v1 Announce Type: new Abstract: Fault tolerance in classical computing has traditionally relied on static strategies like hardware redundancy and error-correcting codes. Biological sys
arXiv:2608.03276v1 Announce Type: new Abstract: Long-context inference with large language models is constrained by the linear growth of the key-value cache to sequence length. While pruning offers mi
arXiv:2608.03675v1 Announce Type: new Abstract: Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in
arXiv:2608.03722v1 Announce Type: new Abstract: Collective intelligence research treats disagreement as evidence of epistemic diversity: if agents express different views, the group should retain capa
arXiv:2607.17244v2 Announce Type: replace Abstract: Longitudinal T cell receptor repertoires contain signals of clonal expansion, contraction, disappearance, and reappearance after immune perturbation
arXiv:2511.00382v2 Announce Type: replace-cross Abstract: Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks. Prior work sho
arXiv:2407.12288v5 Announce Type: replace-cross Abstract: The progress of machine learning over the past decade is undeniable. In retrospect, it is both remarkable and unsettling that this progress wa
arXiv:2608.01428v1 Announce Type: cross Abstract: Embodied agents replan frequently to recover from execution drift, partial observability, and coordination hazards, but each LLM-based replanning call
It's more accurate to say that many highly engaged online gamers are hostile to AI, not that 'gamers' as a whole are. Gaming is a huge community with hundreds of millions of people, and opinions vary
arXiv:2608.02271v1 Announce Type: new Abstract: Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners. This widespread practice creates a signi
arXiv:2607.28801v1 Announce Type: cross Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial
arXiv:2607.29491v1 Announce Type: cross Abstract: Reinforcement-learning-based quantum architecture search (RL-QAS) repeatedly optimizes a variational quantum eigensolver (VQE) after extending a circu
arXiv:2607.28849v1 Announce Type: cross Abstract: Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems
arXiv:2607.28855v1 Announce Type: cross Abstract: Dense 3D sensors in various real-world fields produce point clouds that are geometrically redundant for real-time processing. In this paper, we propos