Knowledge catalogue
We’re hiring for Labs! 🧪 If you’re interested in working with us to push forward Continual Learning, pls DM me with a blurb + link to the best Applied Research you’ve done (or even better shipped!) yo
we've been building agents around the llm, starting with conversations, adding tools, giving rules, logging everything, and storing a form of it as retrievable state Active Graphs flips this. what if
We've productionized query-aware compression for faster, cleaner, more-accurate search. Better context is better than more context. Our system cuts context tokens up to 70% while improving answer qual
arXiv:2605.19447v1 Announce Type: new Abstract: Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failur
arXiv:2605.19936v1 Announce Type: new Abstract: Has the style of scientific communication changed due to the growing use of large language models in the writing process? We address this question in th
arXiv:2605.20086v1 Announce Type: cross Abstract: Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have prod
What hardware actually powers open-source AI? Not benchmarks. Not vendor marketing. Real-world community usage. We’re launching @huggingface Hardware: → trending GPUs & CPUs → VRAM distribution → infe
LetsEnhance with its Digital Art model is considered best for quality, delivering sharp lines and clearest eye detail with the highest output resolution ceiling. For a free desktop option, Upscayl off
arXiv:2312.02652v2 Announce Type: replace-cross Abstract: Particle identification at the Super Charm-Tau factory experiment will be provided by a Focusing Aerogel Ring Imaging CHerenkov detector (FARI
arXiv:2605.19343v1 Announce Type: new Abstract: Single-cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approac
arXiv:2605.19289v1 Announce Type: new Abstract: Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern dif
arXiv:2605.19762v1 Announce Type: new Abstract: Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the
Model swaps look like configuration changes, but they behave more like product migrations. A new model may be cheaper, faster, easier to get capacity for, or stronger on public benchmarks.... The post
When an agent is allowed to decompose a goal into smaller sub-tasks, it frequently suffers from goal drift. Left unchecked, it will redefine the optimization metric to favor a simpler, useless sub-tas
arXiv:2605.20037v1 Announce Type: cross Abstract: Reward-poisoning attacks present a significant risk to learning-based wireless control systems. Given this, we propose a Disagreement-Guided Reward Po
arXiv:2605.20151v1 Announce Type: new Abstract: The proliferation of generative artificial intelligence has given rise to an interactive learning environment, where model parameters are continuously u
Grok Build enables users to annotate specific areas within video frames and provide instructions for AI-assisted edits, streamlining video editing workflows. This feature allows creators to visually d
arXiv:2605.18858v1 Announce Type: cross Abstract: Probabilistic prediction systems often aggregate probability estimates from multiple models into a single decision. A common assumption is that if eac
arXiv:2605.19839v1 Announce Type: new Abstract: Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existin
arXiv:2605.20023v1 Announce Type: new Abstract: Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by
arXiv:2605.19662v1 Announce Type: new Abstract: Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are
arXiv:2605.19444v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) reports substantial accuracy gains on mathematical reasoning benchmarks using majority vote as a pseudo-label
arXiv:2605.19425v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for advanced reasoning in Large Language Models (LLMs), but rol
arXiv:2605.19261v1 Announce Type: cross Abstract: Ensuring the reliability and resilience of modern web applications remains a critical challenge due to increasing system complexity and dynamic runtim
arXiv:2605.19908v1 Announce Type: new Abstract: Authorship attribution models fine-tuned with the same pretrained encoder, data, and loss can differ four-fold in performance depending only on their sc
arXiv:2602.07008v2 Announce Type: replace Abstract: Reliable models should not only predict correctly, but also justify decisions with acceptable evidence. Yet conventional supervised learning typical
arXiv:2601.22569v2 Announce Type: replace-cross Abstract: Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning e
arXiv:2605.19613v1 Announce Type: new Abstract: Color constancy aims to keep object colors consistent under varying illumination. Cross-camera generalization in color constancy remains challenging bec
wild to see a somewhat disgraced politician comment on the technical side of AI as if he has any idea about the underlying computational questions. and of course he dwells at the bottom of Paul Graham
arXiv:2602.03924v2 Announce Type: replace-cross Abstract: Deep learning has revolutionized weather forecasting, but many challenges remain, including climate modeling. Moreover, the current landscape
WisdomAI Inc., creator of an artificial intelligence-native business intelligence platform, is jumping on the agentic AI bandwagon with the latest update to its flagship Federated Agentic Intelligence
Within one 24 hour period, Trump: - got out of a 100 million IRS fine - secured 'immunity' from all future tax investigations for his family and friends - created a 1.8 billion slush fund for lawbreak
working on some hex dashboards -- this is a bummer! if you use langchain/deepagents as your agent harness, you can swap models with fallback middleware when your first choice provider is down https://
arXiv:2605.19957v1 Announce Type: cross Abstract: World models are widely explored in embodied intelligence, yet they typically predict distinct evolutions of the world and the ego within a single str
Worldlier is a Cohere language model that natively supports 48 world languages with improved efficiency, particularly for non-European languages. This represents an expansion of language coverage beyo
arXiv:2605.19214v1 Announce Type: cross Abstract: Diagnostic performance in medical AI varies systematically across demographic groups, yet subgroup AUC can mask clinically important disparities. At a
arXiv:2605.19868v1 Announce Type: new Abstract: Chronic wounds such as diabetic foot ulcers and pressure injuries require accurate tissue-level assessment to guide treatment planning and monitor heali
arXiv:2605.20073v1 Announce Type: new Abstract: This work proposes a pixel-classification approach for vessel segmentation in x-ray angiograms. The proposal uses textural features such as anisotropic
arXiv:2605.18777v1 Announce Type: cross Abstract: Mapping large origin-destination (OD) datasets remains challenging because flow maps become cluttered, meaningful patterns occur at multiple spatial s
arXiv:2603.22453v2 Announce Type: replace Abstract: Community Notes have emerged as an effective crowd-sourced mechanism for combating online deception on social media platforms. However, its reliance
arXiv:2509.19182v2 Announce Type: replace-cross Abstract: Incorporating natural language input has the potential to improve the capabilities of biomedical data discovery interfaces. However, user inte
The Software Freedom Conservancy sued Vizio in October 2021 after the company refused to share complete source code for its Linux-based SmartCast TV operating system, which the nonprofit says violates
You can also now create automations without any attached repos, like a daily Slack digest agent that prioritizes unread threads and DMs for your response. Find more templates in our marketplace: http:
you can condense long horizon evals with agents into smaller subsets that still let you test intended behavior. i'm currently evaluating an agent that runs for 30+ minutes, and analyzes thousands of t
You can now create and manage automations in the same workspace as your agents. Automations are now available in the Agents Window. For the next 7 days, all agent runs for newly created automations ar
Google announced a new YouTube Shorts Remix feature that lets users restyle clips or even insert themselves into other people's videos using Gemini Omni. Now, at the bottom of a YouTube Short, when yo
You can set up Auto-Triage for any Slack channel with just three clicks. To help get you started, we're offering $200 in credits when you create your first Devin Automation. Media Introducing Devin Au
“You want to wake up in the morning and think the future is going to be great—and that’s what being a space-faring civilization is all about. It’s about believing in the future and thinking that the f
arXiv:2605.19969v1 Announce Type: new Abstract: Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train models without a central server. However, the col
arXiv:2505.04588v3 Announce Type: replace Abstract: Effective information searching is essential for enhancing the reasoning and generation capabilities of large language models (LLMs). Recent researc
arXiv:2605.18879v1 Announce Type: cross Abstract: Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web c
arXiv:2605.17046v1 Announce Type: cross Abstract: Autonomous AI coding agents are becoming a core tool for ML practitioners in industry and research alike. Despite this growing adoption, no standardiz
arXiv:2503.14346v3 Announce Type: replace Abstract: Multi-map Sparse Monocular visual Simultaneous Localization and Mapping applied to monocular endoscopic sequences has proven efficient to robustly r
arXiv:2605.18334v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributi
arXiv:2605.16795v1 Announce Type: cross Abstract: Video generative models have made remarkable progress, yet they often yield visual artifacts that violate grounding in physical dynamics. Recent works
arXiv:2605.18074v1 Announce Type: new Abstract: We present 4DLidarOpen, a large-scale open multi-modal dataset for autonomous driving, centered on 4D frequency-modulated continuous-wave (FMCW) Lidar s
This guide provides Chief Financial Officers with strategies for financial management and performance optimization in value-based care models, which shift healthcare reimbursement from volume-based to
arXiv:2412.11149v2 Announce Type: replace Abstract: Action Quality Assessment (AQA) aims to automatically evaluate how well human actions are performed and has been widely applied in sports analysis,
arXiv:2605.17564v1 Announce Type: new Abstract: Paired RGB-thermal data has shown significant utility across a range of applications, including image fusion, object tracking, and anomaly detection; ho
arXiv:2605.17021v1 Announce Type: new Abstract: Multi-view learning has been widely applied for sleep stage classification using multi-modal data. However, existing methods typically assume that diffe