Knowledge catalogue
arXiv:2602.20207v3 Announce Type: replace-cross Abstract: Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserv
arXiv:2605.15723v1 Announce Type: cross Abstract: Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities la
arXiv:2605.15290v1 Announce Type: cross Abstract: Hyperparameter transfer across model architectures dramatically reduces the amount of compute necessary for tuning large language models (LLMs). The m
arXiv:2605.15250v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the H10
arXiv:2511.14482v2 Announce Type: replace-cross Abstract: Join ordering is the NP-hard problem of selecting the most efficient order in which to evaluate joins (conjunctive, binary operators) in a dat
arXiv:2512.06655v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity obj
arXiv:2605.15764v1 Announce Type: cross Abstract: Understanding social interactions requires reasoning over subtle non-verbal cues, yet current multimodal large language models (MLLMs) often fail to i
arXiv:2605.15365v1 Announce Type: new Abstract: Communicating using only a limited vocabulary is a common but challenging cognitive phenomenon, requiring an ideal communicator to plan carefully to opt
arXiv:2605.15464v1 Announce Type: cross Abstract: Post-training has become a crucial step for unlocking the capabilities of large language models, with reinforcement learning (RL) emerging as a critic
Grok agent mode is a major ability unlock I've finished a video of just over 4 minutes, entirely created using Grok Imagine's Agent mode (see image). It's a much smoother way to make videos because yo
Grok Build, a development tool, features a Command Palette accessible via the Ctrl+P keyboard shortcut, enabling users to quickly access commands and functions. This functionality is similar to comman
Grok groks videos You can now upload entire videos to Grok and have it analyze, summarize, translate, explain scenes, or extract important context for you in real time Grok can understand full videos
Grok Summary of Elon Musk’s interview at the Samson International Smart Mobility Summit today. 1. Strong praise for Israel’s innovation edge Elon called out Israel’s outsized impact, saying it “punche
arXiv:2605.15787v1 Announce Type: cross Abstract: Why does a Transformer that has memorized its training set wait thousands of steps before it generalizes? Existing accounts locate this delay in norm
arXiv:2505.23678v3 Announce Type: replace Abstract: While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual
A new Lanterns teaser trailer features Nathan Fillion returning as Guy Gardner , the character introduced in the 2025 Superman movie . Showrunner Chris Mundy confirmed Gardner will 'be in the show a f
arXiv:2605.15701v1 Announce Type: cross Abstract: Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'
arXiv:2512.04111v2 Announce Type: replace-cross Abstract: LLM-powered coding agents are reshaping the development paradigm. However, existing evaluation systems, neither traditional tests for humans n
arXiv:2502.12187v3 Announce Type: replace Abstract: Hallucinations, a phenomenon where a language model (LM) generates nonfactual content, pose a significant challenge to the practical deployment of L
arXiv:2605.15216v1 Announce Type: cross Abstract: Always-on AI applications, from environmental sensors to biomedical implants, require ultra-low power consumption. Analog circuits offer a path to sub
arXiv:2605.15411v1 Announce Type: cross Abstract: We study contextual dynamic pricing in a semiparametric scalar-index valuation model where the latent value is v_t=mu_ast(mathsf c_t)+xi_t, with an un
arXiv:2605.16056v1 Announce Type: new Abstract: Research on Vision Language Action (VLA) models has been increasing rapidly in recent years. Although some of them focus on detecting, preventing, and r
arXiv:2508.01014v4 Announce Type: replace-cross Abstract: Advances in 3D reconstruction and novel view synthesis have enabled efficient and photorealistic rendering. However, images for reconstruction
arXiv:2605.15832v1 Announce Type: cross Abstract: This work extends a framework for predicting the performance of High-Performance Computing (HPC) workloads using Machine Learning (ML). A common limit
Swyx posted about reconnecting with multiple acquaintances from Singapore's tech community during a trip, expressing appreciation for seeing old friends. The post reflects on the density and interconn
arXiv:2605.15338v1 Announce Type: cross Abstract: Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for pe
arXiv:2605.15753v1 Announce Type: cross Abstract: Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes,
arXiv:2602.14342v2 Announce Type: replace-cross Abstract: We show that high-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as polylog(1/elta), wh
arXiv:2605.15673v1 Announce Type: cross Abstract: We present a highly detailed instance segmentation model for delineating individual tree crowns in natural broadleaf forests using aerial imagery acqu
arXiv:2605.15336v1 Announce Type: cross Abstract: In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1
🚨 holy shit.. a woman just pleaded guilty to running a voter fraud scheme on Skid Row for 20 years and nobody caught her until a guy with a hidden camera showed up Brenda Lee Brown Armstrong.. caught
arXiv:2603.03243v2 Announce Type: replace Abstract: We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulat
arXiv:2506.06739v3 Announce Type: replace Abstract: Inductive logic programming (ILP) is a form of logical machine learning. The goal is to search a hypothesis space for a hypothesis that generalises
Tim Higgins / Wall Street Journal: How Amazon, which took a measured tone to AI, went from an AI also-ran to a real contender, thanks to 200B in spending, custom AI chips, and savvy deals — The pieces
arXiv:2605.15306v1 Announce Type: new Abstract: Data augmentation is widely recognized for improving generalization in deep networks, yet its impact on the geometry of learned representations remains
How do you know your document parser is ready for production? 🤔 Existing benchmarks miss what AI agents actually need. That's the gap ParseBench, the first doc OCR benchmark for AI agents, fills. We'l
Emily Birnbaum / Bloomberg: How gambling companies like FanDuel and DraftKings, as well as Meta and a16z's founders, are pouring millions into state-level election campaigns via super PACs — With Cong
When most people think of A/B experimentation, they think of button colors, landing page layouts, or checkout flows. At Google, many fundamental infrastructure improvements also need the rigor of A/B
How it is supposed to be James Madison described the powers of the federal government as “few and defined” and those reserved to the states as “numerous and indefinite.” We’ve been dangerously driftin
How one NGO spun a spiders web of 40 activist orgs, gov't officials, legislators & lawyers into passing the UK Online Censorship Act suppressing every US platform and millions of British citizens toda
Alessandra Ram / Wired: How the AI industry's intense pressure to keep up and its financial rewards are creating “walls of resentment” between Silicon Valley workers and their spouses — Are you marrie
arXiv:2605.15689v1 Announce Type: new Abstract: Fine-grained image recognition classifies subcategories such as bird species or car models. While state-of-the-art (SOTA) models are accurate, they are
arXiv:2510.02453v3 Announce Type: replace-cross Abstract: Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting.
LTX-2.3 is Lightricks' latest open-source audio-video generation model natively supported in ComfyUI, delivering major quality improvements including enhanced details, portrait video support, and impr
arXiv:2605.15486v1 Announce Type: cross Abstract: This study introduces intelligent frameworks that use Large Language Models (LLMs) to improve task scheduling for construction robots. The LLM is fed
arXiv:2605.15238v1 Announce Type: cross Abstract: Large language models are increasingly used for code generation, but many generated programs fail to compile, a prerequisite for further correctness c
arXiv:2605.15741v1 Announce Type: new Abstract: Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental 'granularity dilemma': captu
arXiv:2605.16211v1 Announce Type: new Abstract: Traditional scientific modeling typically begins with fixed, instance-wise effective equations and then carries out equation-specific analysis and compu
I believe on-prem and local AI - based on @huggingface open-source models - will be an important answer to the GPU shortages this year (because they are cheaper, faster, safer than cloud APIs)! Great
I broke my own rule to never post about AI detection as it is fraught in many ways. The problem is that if you use AI a lot, you know AI writing on sight, which makes the difficulty of objectively pro
I love AI, it’s pure LLMs I hate. Pure LLMs *are* basically just autocomplete. Recent progress (e.g. Claude Code) doesn’t show otherwise Rather, lot of the progress in the last two years has come from
I resurrected my 8-year-old phone into a Hermes Agent server⚕️ Replaced Android with postmarketOS (Alpine Linux on ARM64), runs Hermes as a systemd service. I chat with it over Matrix (E2E encrypted)
GPT Image 2 delivers significant improvements for food infographics, rendering dense, legible text inside layouts with clean results for recipes, instructional flows, and step-by-step guides without t
arXiv:2605.15224v1 Announce Type: new Abstract: Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed,
ICYMI: SmithDB is our purpose-built data layer for agent observability + eval workloads. Supporting increasingly complex query patterns at low latency, over large traces, with self-hosting + multi-clo
LangChain released Deep Agents v0.6, described as their largest release to date. The announcement was made by Harrison Chase on X (formerly Twitter), indicating a significant update to the Deep Agents
If you're a R user: the R edition of the book is out now! AI hype can be pretty easy to find. But clear explanations are definitely harder. Deep Learning with R, Third Edition by @fchollet and Tomasz
arXiv:2602.21536v2 Announce Type: replace Abstract: Retrospective MRI harmonization is limited by poor scalability across modalities and reliance on traveling subject datasets. To address these challe
arXiv:2605.16175v1 Announce Type: new Abstract: Pediatric critical care is a dynamic, high-stakes process involving constant monitoring and adjustments in life-saving treatments. Modeling these interv
arXiv:2605.15960v1 Announce Type: new Abstract: We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy sh