Knowledge catalogue
arXiv:2605.14257v1 Announce Type: new Abstract: We describe two types of models for vocabulary difficulty prediction: a high-accuracy black-box model, which achieved the top shared task result in the
What we find most useful about Lighthouse is the architectural decoupling. The selection logic is fully separated from the attention kernel, which means every upstream software or hardware attention i
arXiv:2605.14449v1 Announce Type: cross Abstract: Hallucination detection in large language models (LLMs) requires balancing accu racy, efficiency, and robustness to distribution shift. Black-box cons
arXiv:2605.15183v1 Announce Type: new Abstract: Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite.
arXiv:2605.14115v1 Announce Type: new Abstract: Biomedical retrieval-augmented large language models (LLMs) often face evidence that is incomplete, misleading, or internally contradictory, yet evaluat
arXiv:2605.14478v1 Announce Type: cross Abstract: Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Ob
arXiv:2605.14504v1 Announce Type: new Abstract: Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied A
arXiv:2605.14368v1 Announce Type: cross Abstract: Continuous diffusion language models lag behind autoregressive transformers, partly because diffusion is applied in spaces poorly suited to language d
I can't provide a summary for this entry. The source URL appears invalid, and the framing contains charged language rather than factual content. If you're interested in the Academy Awards eligibility
arXiv:2512.06471v2 Announce Type: replace-cross Abstract: Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal sta
arXiv:2605.15109v1 Announce Type: new Abstract: Retrieval-Augmented Generation can improve factuality by grounding answers in external evidence, but Agentic GraphRAG complicates what it means for cita
arXiv:2605.14192v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in ret
arXiv:2605.15152v1 Announce Type: cross Abstract: LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risk
arXiv:2603.09921v3 Announce Type: replace Abstract: Open-domain visual entity recognition (VER) seeks to associate images with entities in encyclopedic knowledge bases such as Wikipedia. Recent genera
arXiv:2605.13979v1 Announce Type: cross Abstract: Quantum machine learning (QML) aims to accelerate machine learning tasks by exploiting quantum computation. Previous work studied a QML algorithm for
Cognition AI reports that Devin, their AI coding assistant, enabled AngelList to complete a data migration 5.2 times faster than their original project timeline. The case study highlights Devin's effe
arXiv:2605.14578v1 Announce Type: new Abstract: Partial Dependence Plots (PDPs) visualize how changes in a single feature affect the average model prediction. They are widely used in practice to inter
This entry documents a Wordle game result (puzzle #1,790) played by Anthropic, showing a failed attempt marked as X/6, meaning the player did not solve the puzzle within six tries. The color-coded emo
This post documents a Wordle game result where the player successfully solved puzzle #1,791 in four attempts, using color-coded emoji feedback (black for incorrect letters, yellow for correct letters
Wow! What a week! Lots of new things to learn - new ideas to form The complete Agent Development Life Cycle 🎯 ❤️ SF but can’t wait to get home and back to building! Thanks for the warm welcome and fun
🚨 WOWWW — UTAH — the brilliant young women @kevinolearytv 🤥 accused of being Chinese ops just discovered Utah speaker of the house Mike Schultz (Republican) bought 640 acres of land right next to the
X is the most powerful platform in the world. Today, the Prime Minister of India himself used X to fact-check a major news claim and directly tell people the truth. That’s the power of X. X is not jus
arXiv:2605.13922v1 Announce Type: cross Abstract: During the last few years, the term Mechanistic Interpretability, a specific area, under the umbrella of explainable artificial intelligence (XAI), ha
Carmen Arroyo / Bloomberg: xAI launches Grok Build, an agentic CLI for coding, building apps, and automating workflows, in beta for SuperGrok Heavy subscribers — Elon Musk's xAI is rolling out its fir
arXiv:2605.14754v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowle
arXiv:2605.14844v1 Announce Type: cross Abstract: We introduce XFP, a dynamic weight quantizer for LLM inference that inverts the conventional workflow: the operator specifies reconstruction quality f
arXiv:2511.02776v2 Announce Type: replace Abstract: Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. Howe
Yann LeCun says LLMs are strongest in domains where language itself is the substrate of reasoning, like math and code They can solve problems, prove theorems, and write programs — but they are not cre
SolveIt now supports real-time voice editing of messages during conversations, allowing users to make changes through spoken commands. The platform can optionally track these edits as diffs, enabling
Nous Research has integrated Grok, xAI's large language model, into the Hermes Agent framework, allowing users with active @grok subscriptions to leverage Grok's capabilities within the Hermes Agent e
arXiv:2605.14166v1 Announce Type: new Abstract: Face image super-resolution aims to recover high-resolution facial images from severely degraded inputs. Under extreme upscaling factors, fine facial de
arXiv:2605.14893v1 Announce Type: cross Abstract: Contrastively pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors. Yet, their shared latent spaces are prone to structural
Mia Sato / The Verge: YouTube expands its AI likeness detection program to users over the age of 18, after rolling it out to select creators, politicians, journalists, and others — Likeness detection,
YouTube is expanding its AI likeness detection program to all users over the age of 18 - meaning just about anyone can have the platform hunt for potential deepfakes of themselves. The likeness detect
Gary Marcus highlighted a concerning problem in 2025 where approximately 140,000 fabricated citations were identified, likely referring to false or hallucinated references generated by AI systems in a
This post discusses how traditional caching mechanisms assume deterministic behavior (identical inputs producing identical outputs), an assumption that breaks down with large language models and espec
arXiv:2605.12586v1 Announce Type: cross Abstract: Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives wit
arXiv:2605.12689v1 Announce Type: new Abstract: In this paper, we present a novel hybrid approach that combines Reinforcement Learning (RL) with Dynamic Window Approach (DWA) for adaptive 3D local nav
arXiv:2505.21238v3 Announce Type: replace Abstract: Novel view synthesis for underwater scene reconstruction presents unique challenges due to complex light-media interactions. Optical scattering and
4/5 The fix: stop encoding execution order, encode graph position instead. Now you get two independent controls: experiment name (controls the key) and component code (controls the prompt). Change eit
5/5 What this unlocks: - Change one prompt, serve cached results for all other components. - A/B test any component against identical upstream outputs. - Run best-of-N inference without N branches col
At the tech world’s poker table, Coupa Software Inc. is betting that 10 trillion in cumulative spend gives it an edge in artificial intelligence. Who’s to say it’s wrong? That’s how much Coupa’s execu
A 41yo mom told me this week that she's raising her daughter as a '90s kid' 😮 Her 10yo has an android that can only call and send texts (no browsing, no uber, nada). She plays the original Mario. When
arXiv:2603.14066v2 Announce Type: replace-cross Abstract: Many real-world multi-party negotiations unfold as sequences of binding, action-level commitments rather than a single final outcome, yet this
arXiv:2605.13142v1 Announce Type: new Abstract: In professional sports, a team has clinched the playoffs if they are guaranteed a postseason spot, regardless of the outcomes of any remaining games. As
A conversation with @sirupsen on scaling Shopify, building turbopuffer, and the future of databases. 0:00 - Scaling Shopify through flash sales and outages 8:13 - How top infrastructure teams collabor
arXiv:2605.12608v1 Announce Type: new Abstract: Object detection in adverse weather is critical for the safety of autonomous vehicles; however, the scarcity of labelled, real-world foggy data remains
arXiv:2506.04165v3 Announce Type: replace Abstract: We consider the Top-K selection problem, which aims to identify the largest K elements in an array. Top-K selection arises in many machine learning
arXiv:2605.12719v1 Announce Type: cross Abstract: The continual assurance of safety and performance of automated driving systems (ADSs) poses significant challenges. ADSs operate in complex, dynamic,
arXiv:2605.13015v1 Announce Type: cross Abstract: The geometry of the retinal vessel is a key biomarker of vascular diseases, yet clinical evidence remains primarily observational. Existing generative
arXiv:2605.13687v1 Announce Type: cross Abstract: We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context
arXiv:2605.13367v1 Announce Type: cross Abstract: The literature on ontology-mediated query answering (OMQA) has been shaped by two key results: first-order rewritability for DL-Lite, and PTime-hardne
arXiv:2605.13200v1 Announce Type: new Abstract: Accurate state of charge estimation is critical for the success of electric vehicle battery management strategies, but it is well known that conventiona
Matt Levine / Bloomberg: A look at GameStop's takeover bid for eBay, a bizarre job application by GameStop CEO Ryan Cohen, who does not have the money to buy eBay, to become eBay's CEO — Also Adani Gr
arXiv:2507.19247v5 Announce Type: replace-cross Abstract: Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes
arXiv:2605.13110v1 Announce Type: cross Abstract: We present a fully automated multi-agent framework for corporate due diligence and market analysis in venture capital. The system runs on an event-dri
arXiv:2605.12706v1 Announce Type: new Abstract: RSNet is an open-source R package that provides a resampling-based framework for robust and interpretable network inference, designed to address the lim
An attacker exploited a misconfigured GitHub Actions workflow in the Tanstack project by creating a pull request from a fork that triggered the publish workflow with full project permissions, allowing
A small hack for my AI multi-taskers out there: I have so many Claude Code conversations running at once that I ask it to synthesize all of its action or my next action into single go/no-go sentences.
arXiv:2605.12697v1 Announce Type: cross Abstract: Length-dependent logit rescaling is widely used to stabilize long-context self-attention, but existing analyses and methods suggest conflicting invers