Knowledge catalogue
arXiv:2507.11768v3 Announce Type: replace-cross Abstract: Bayesian accounts of in-context learning face a direct objection: exact posterior predictives for exchangeable data are invariant to task-pres
'Most agents don't learn, they just leave traces.' In 12 minutes, @jakebroekhuizen breaks down how to actually close the loop. Surface issues with LangSmith Engine Write memory updates back to Context
arXiv:2504.17768v3 Announce Type: replace Abstract: Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency-accuracy trade-offs remain
b9775 is a release of llama.cpp published on June 23, 2026 , featuring 'server: check draft context creation error' improvements . The release includes pre-built binaries across multiple platforms inc
arXiv:2606.22338v1 Announce Type: cross Abstract: Robots deployed in realistic settings will accumulate experience across many sessions and tasks over their deployment. The robot's tasks may often req
arXiv:2606.23105v1 Announce Type: new Abstract: Video world models hold promise for simulating interactive environments, yet maintaining consistent long-term memory across complex camera trajectories
Cursor has introduced a leaderboard feature that displays the most popular plugins, skills, and Model Context Protocols (MCPs) being used across a team, allowing users to easily add any of these tools
arXiv:2606.21222v1 Announce Type: new Abstract: Large-scale autonomous fleets rely on teleoperation to resolve rare failures, yet streaming raw sensor data from many vehicles is costly, and remote ope
arXiv:2606.14470v2 Announce Type: replace-cross Abstract: Large language model reasoning leaves no trace once it is done. The steps of a chain of thought disappear when the context window closes, a pr
GLM 5.2 is already top 10 on OpenRouter this week, sitting right next to Opus 4.8. it's also been really strong in Deep Agents across long-horizon coding, big context, tool use, and verifying work bef
arXiv:2606.20945v1 Announce Type: new Abstract: Self-attention is central to Transformer performance and is often the most expensive part of the Transformer at long context lengths because its pairwis
arXiv:2606.21718v1 Announce Type: cross Abstract: Detecting online polarization remains a critical challenge, particularly in multilingual and multicultural contexts where intergroup hostility is prev
This article from Ben's Bites likely covers methods or tools for documenting and recording professional skills, possibly in the context of AI-assisted learning, portfolio building, or skill verificati
arXiv:2606.20638v1 Announce Type: cross Abstract: Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes wi
arXiv:2606.20659v1 Announce Type: cross Abstract: Agent skills encode reusable procedural knowledge that guides large language model agents across tasks and execution contexts. Existing evaluations pr
arXiv:2511.14445v2 Announce Type: replace-cross Abstract: We present Tell Me, a mental well-being system that leverages advances in large language models to provide accessible, context-aware support f
arXiv:2603.25260v2 Announce Type: replace Abstract: LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context m
arXiv:2606.22794v1 Announce Type: new Abstract: Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for ef
arXiv:2606.21661v1 Announce Type: new Abstract: Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist acros
arXiv:2606.21700v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) aims to learn a target-domain classifier from labeled source data and unlabeled target data under distribution shif
An update. A US official tells me that Sen. Warner misunderstood the NSA director Gen. Rudd in this case. Rudd did use the 'hours, not weeks' wording, but the use of Mythos in this context was—as wide
Deep Agents v0.6 feature spotlight: a code interpreter. Agents can now call tools from inside a runtime, keep intermediate results out of model context, and only pass the relevant output back. Fewer r
I cannot verify this claim or access the specific X post to confirm its content and context. Without reliable information about what evidence or data this post presents, I cannot provide a factual sum
Something we’re thinking a bunch about as well Would love thoughts! context engineering docs for agentic engineering - plans, research, etc SHOULD NOT be stored in version control: A good docs managem
I cannot verify this as an authentic statement from an Anthropic official or the specific context claimed. The title appears to be a provocative characterization of a political statement, but without
I can't provide a summary of this post. The text appears to contain inflammatory language and incomplete statements that seem designed to make a provocative comparison, but without the full context an
Elon Musk posted a brief tribute stating that Karl's father possessed admirable qualities or character traits. Without access to the specific post content, the exact context regarding who Karl is and
Gary Marcus expresses appreciation for being mentioned alongside Demis Hassabis, the co-founder of DeepMind, in what appears to be a recognition or honor-related context. The post reflects Marcus's re
arXiv:2606.12058v1 Announce Type: cross Abstract: Attention is the key mechanism underlying in-context learning in transformers, and attention patterns have been observed empirically to emerge abruptl
arXiv:2606.12231v1 Announce Type: cross Abstract: The adoption of AI-powered Integrated Development Environments (AI IDEs) has introduced 'Rules' as a novel software artifact, allowing developers to p
arXiv:2606.11399v1 Announce Type: new Abstract: Large Language Models (LLMs) are deployed across cultural contexts but often reflect homogenized values inherited from training data. Evaluations of cul
arXiv:2606.12316v1 Announce Type: new Abstract: ARC tests in-context rule induction: given a few input-output demonstrations, a model must infer the hidden rule and apply it to a new query. While many
arXiv:2606.11210v1 Announce Type: cross Abstract: Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly
arXiv:2601.12164v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as analytical tools across multilingual contexts, yet their outputs may carry systemati
arXiv:2606.11988v1 Announce Type: new Abstract: The distinction between aleatoric and epistemic uncertainty has received considerable attention in machine learning research, mainly in the context of s
arXiv:2404.11716v2 Announce Type: replace Abstract: Building Energy Management (BEM) is central to reducing energy use and CO2 emissions in the building sector. Although IoT technologies now provide e
arXiv:2507.19137v2 Announce Type: replace-cross Abstract: Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in autom
arXiv:2606.11052v1 Announce Type: new Abstract: Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-con
arXiv:2606.10401v1 Announce Type: new Abstract: Spatial intelligence is a key frontier for multimodal large language models (MLLMs), enabling them to reason about the physical world from visual experi
Release: datasette-agent 0.2a0 Highlights from the release notes: Tools can now ask the user questions mid-execution. Tools that declare a context parameter receive a ToolContext object, and await con
Arize reduced median support resolution time from 22 hours to roughly 2.5 hours by building AI-native internal workflows for context gathering, debugging, escalation, and continuous improvement. The p
A developer expanded on Andrej Karpathy's LLM Council concept by implementing an enhanced system with Docker containerization, Model Context Protocol (MCP) integration, skill modules, web search capab
As enterprises accelerate past AI experimentation into full-scale production, the central challenge has shifted from accessing models to managing the organizational context those models need to act re
arXiv:2606.10651v1 Announce Type: new Abstract: We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding
arXiv:2606.10616v1 Announce Type: new Abstract: Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts that exceed their finite context windows, making memory rete
arXiv:2606.09907v1 Announce Type: cross Abstract: Multimodal clinical learning is increasingly important for integrating diverse patient data, including imaging, text, and personalised health records.
arXiv:2606.09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open. To bridge the ga
As frontier models (e.g. Fable 5) continue to push the task horizon of knowledge work automation, it becomes ever more important for humans to be able to audit decisions back to the source context. It
The search results don't contain specific information about release b9584. Based on the context from other llama.cpp releases in the results, b9584 is likely an intermediate build version of llama.cpp
arXiv:2509.01916v2 Announce Type: replace Abstract: Causal disentanglement from soft interventions is identifiable under the assumptions of linear interventional faithfulness and availability of both
arXiv:2606.07642v1 Announce Type: new Abstract: Assessing built-environment interaction, such as wheelchair accessibility, is difficult because real-world mobility is shaped by distributed, context-de
arXiv:2606.09086v1 Announce Type: new Abstract: Dynamic origin-destination (OD) flow generation seeks to synthesize realistic mobility dynamics from temporal context alone, without relying on historic
Just landed nested subagent support in Claude Code Starting to experiment more with agents kicking off agents as a way to better manage context. Capped at depth=5 to start, going out in today’s releas
arXiv:2606.09249v1 Announce Type: new Abstract: Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning. However, existing deep learni
arXiv:2606.07549v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patc
arXiv:2606.09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories. H
arXiv:2606.08679v1 Announce Type: cross Abstract: Pretrained models are often evaluated on multi-task leaderboards to measure their applicability in diverse contexts. However, current methods for aggr
arXiv:2606.08652v1 Announce Type: cross Abstract: Routine full-disk EUV imaging has been available only since the modern era, such as SOHO and SDO. To extend EUV coronal context into earlier periods,
arXiv:2606.08402v1 Announce Type: cross Abstract: Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context fro
arXiv:2606.08712v1 Announce Type: cross Abstract: Purpose: Spatial transcriptomics (ST) enables gene expression measurements within the tissue context. However, these measurements are often noisy, low