Knowledge catalogue
arXiv:2601.03785v3 Announce Type: replace Abstract: Long-term human-agent dialogues are organized by topic continuity: adjacent turns often develop the same goal, plan, problem, or event, while relate
Our new AI policy is that the White House decides ad hoc, for whatever reasons it likes, who does and does not get access to frontier intelligence. This seems rather maximally terrible. The US Governm
arXiv:2405.17423v4 Announce Type: replace-cross Abstract: As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle p
arXiv:2606.25086v1 Announce Type: new Abstract: Many modern Language Model (LM) pipelines return an averaged model, such as an exponential moving average of the training iterates, rather than the fina
arXiv:2601.23132v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in tool-driven environments such as healthcare analytics, financial systems, retrieval-
arXiv:2606.24459v1 Announce Type: cross Abstract: Bearing fault diagnosis faces critical challenges when dataset heterogeneity, operating condition variations, and limited labeled data occur simultane
arXiv:2606.24780v1 Announce Type: new Abstract: Progress in deep learning is, at scale, more a matter of systems engineering than of modelling: the behaviour of a model in training (its throughput, it
arXiv:2606.24752v1 Announce Type: new Abstract: The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge i
arXiv:2606.23701v1 Announce Type: cross Abstract: Qualitative product feedback can reveal nuanced user experiences, but its implicit sentiment is difficult to measure. This paper presents a scalable a
Gemini 3 Pro was the first model to achieve at least 23% on ARC-AGI-2, which it did in November, 2025 (it actually scored 31%). So the 8-12 month gap between closed and open weights models still seems
arXiv:2606.16821v2 Announce Type: replace Abstract: Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that
arXiv:2606.22419v2 Announce Type: replace Abstract: A recent Nature Medicine study reports that general-purpose frontier LLMs outperform specialized retrieval-augmented clinical tools on medical bench
📣📣 Meet Qwen-AgentWorld — a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training o
arXiv:2606.24523v1 Announce Type: cross Abstract: Scam phone calls exploit vulnerable communities worldwide, yet research on detection has focused almost exclusively on English and other high-resource
arXiv:2606.23992v1 Announce Type: cross Abstract: Clinical value sets define the standardized terminology codes used in quality measurement, phenotyping, cohort construction, and clinical decision sup
arXiv:2606.24112v1 Announce Type: new Abstract: Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed proven
Right alongside Cursor, Devin Desktop (Windsurf) and CLI now support GLM-5.2 as well. FrontierCode Extended is a benchmark we care deeply about for real-world engineering tasks, so it's great to see G
arXiv:2606.23700v1 Announce Type: cross Abstract: Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates thro
simonw/browser-compat-db Inspired by Mozilla's new MDN MCP service - source code here - I decided to try converting their comprehensive mdn/browser-compat-data repository full of browser compatibility
This is the strongest ARC-AGI-2 performance to date by an open-source model. GLM-5.2 from @Zai_org on ARC-AGI (Verified) - ARC-AGI-2: 22.8%, 0.25 - ARC-AGI-1: 77.0%, 0.19 Performance is comparable wit
arXiv:2606.23759v1 Announce Type: cross Abstract: Verilog debugging remains one of the most time-consuming stages in digital circuit design. Recent advances in Large Language Models (LLMs) have enable
arXiv:2606.24370v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into decision-support roles in business and policy contexts. While prior benchmark studies have
arXiv:2606.20657v1 Announce Type: cross Abstract: Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to kee
arXiv:2606.20668v1 Announce Type: cross Abstract: LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI appli
arXiv:2606.22497v1 Announce Type: new Abstract: Microscopic imaging provides essential visual evidence for studying plant biology and pathology at the cellular and subcellular levels. However, existin
arXiv:2606.15127v2 Announce Type: replace Abstract: Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students inte
arXiv:2606.20678v1 Announce Type: cross Abstract: Mechanistic interpretability methods summarize a transformer component by a single importance score, conflating two distinct roles: a component may ma
DFlash is an open source block diffusion model for speculative decoding that significantly accelerates LLM inference on NVIDIA Blackwell GPUs by drafting entire token blocks in parallel and verifying
arXiv:2606.20785v1 Announce Type: cross Abstract: Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires tw
arXiv:2606.20707v1 Announce Type: new Abstract: While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow
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:2606.22409v1 Announce Type: new Abstract: Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occu
arXiv:2601.12879v2 Announce Type: replace Abstract: Extracting sparse circuits from billion-parameter transformers is constrained by O(2^n) search cost and pervasive feature reuse across co-active pat
arXiv:2601.07298v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image r
arXiv:2602.09012v2 Announce Type: replace Abstract: The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a
arXiv:2503.10251v2 Announce Type: replace-cross Abstract: Transformers are the state-of-the-art architecture for large language models, and a key to their scalability is the strategic usage of low-pre
arXiv:2606.20587v1 Announce Type: cross Abstract: What matters more for building foundation models for wireless packet traces: the tokenizer or the architecture or both? To answer this question, we bu
arXiv:2606.22402v1 Announce Type: cross Abstract: Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucin
arXiv:2606.17702v2 Announce Type: replace Abstract: Characterising the tumour microenvironment (TME) from routine H&E-stained histology images requires simultaneous cell segmentation, feature extracti
arXiv:2606.15678v2 Announce Type: replace Abstract: A feasibility and dynamics study of the Reservoir Attention Network (RAN), an architecture that injects a fixed, randomly-initialized reservoir into
arXiv:2606.20724v1 Announce Type: cross Abstract: Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate
arXiv:2606.23057v1 Announce Type: cross Abstract: Large language models now mediate how buyers discover products and services, making the competitive structure of AI-generated recommendations a strate
GLM-5.2 leads open weights models and sits at #3 overall on GDPval-AA, a real-world agentic work benchmark GLM-5.2 from @Zai_org scores 1524 Elo on GDPval-AA, which measures performance on real-world,
The advanced civilizations of sci-fi legend (Banks, Asimov, etc) have some form of simulation to guide society. @joon_s_pk is taking a crack at building that simulator with @simile_ai. As Joon's cofou
We’re expanding OpenAI Daybreak to help democratize patching vulnerable software at machine speed: - Codex Security plugin: find, validate, and fix vulnerabilities right inside Codex - The full versio
Temporary Cloudflare Accounts for AI agents The announcement says this is 'for AI agents' but (as is pretty common these days) the AI hook isn't really necessary, this is an interesting feature for ev
Yeah I agree. The big winner is going to be Ollama: I've offloaded all my supervisory, code review, and ontology learning agents to my $20 a month Ollama subscription, because I keep getting weight li
arXiv:2606.11324v1 Announce Type: cross Abstract: We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied
arXiv:2606.11257v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generati
arXiv:2606.11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs. For large reasoning
arXiv:2606.12407v1 Announce Type: new Abstract: General-purpose large language models (LLMs) are routinely used as baselines when evaluating specialized pathology models on whole-slide images (WSIs).
arXiv:2606.11875v1 Announce Type: new Abstract: Emotional validation - explicitly acknowledging that a user's feelings make sense - has proven therapeutic value but has received little computational a
arXiv:2606.11722v1 Announce Type: cross Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (
arXiv:2606.11520v1 Announce Type: cross Abstract: Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution
arXiv:2603.06910v2 Announce Type: replace Abstract: Multilingual large language models (LLMs) are increasingly used in socially sensitive mental health contexts, including support chatbots, screening,
arXiv:2603.24080v2 Announce Type: replace Abstract: Benchmarks like MMLU suggest flagship language models approach factuality saturation above 90%. LLMpedia shows this picture is incomplete. We materi
arXiv:2606.11724v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Ex
arXiv:2512.08211v2 Announce Type: replace Abstract: Large language models (LLMs) are moving from cloud-centric services toward on-device embedded AI, where models interact with private, longitudinal s
Pop quiz, which of these is no longer true (or at least directionally true), two years later? 9 reasons that OpenAI could someday be seen as the WeWork of AI: 👉 Lots of competitors are catching up. 👉
arXiv:2606.11196v1 Announce Type: cross Abstract: Decentralized LLM inference networks need lightweight, reference-free quality evaluation for Proof of Quality (PoQ). We present PoQ-Judge, a framework