Knowledge catalogue
arXiv:2608.30757v1 Announce Type: new Abstract: Before an intelligent system can decide whether an action is allowed, it must first know which rules the action has approached. A single proposed action
arXiv:2512.17581v2 Announce Type: replace Abstract: Benchmarking competitions are central to the development of artificial intelligence (AI) in medical imaging, defining performance standards and shap
arXiv:2608.28305v1 Announce Type: new Abstract: Industrial panel operation is knowledge-intensive and safety-critical. Beyond control recognition and action generation, execution must satisfy constrai
TL;DR: Every public low-bit GGUF of this model is secretly ~4.70 bpw. Shim the rows to 256 and it becomes a real 3.07 bpw / 11.77 GiB file that runs 262K context on 16GB. Needs patched llama.cpp — not
This was a fun chat If all cars were as safe as waymos then 80k lives would be saved in the Americas, 30k in USA alone. Hundreds of thousands of injuries. So main lobby against self driving cars are a
arXiv:2608.26117v1 Announce Type: cross Abstract: RDBMS (Relational Database Management System) databases face several limitations, including slow execution with multi-hop queries and a lack of explai
arXiv:2608.26168v1 Announce Type: cross Abstract: The lifecycle of hallucination in LLMs is a concept that enables building solid frameworks on the control and reliability of LLMs in high-stakes envir
arXiv:2608.26832v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to specialized domains, where effective use of domain expertise often requires reasoning over comp
arXiv:2608.27147v1 Announce Type: new Abstract: The development of frontier models is commonly perceived to be the exclusive remit of a small number of heavily funded players, creating an information,
arXiv:2608.26877v1 Announce Type: new Abstract: Prior analyses by Derezinski and Warmuth established all-size sampling identities, selected-OLS unbiasedness, and inverse moments for ordinary volume sa
arXiv:2608.25114v1 Announce Type: new Abstract: Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to reprodu
arXiv:2608.24127v1 Announce Type: cross Abstract: Telephone fraud is pervasive and costly, but its inner workings are rarely observed at scale. We analyze a complete corpus of 10,211 inbound scam and
arXiv:2608.24691v1 Announce Type: new Abstract: Agentic systems increasingly gate actions on a model's own stated confidence, which assumes confidence tracks correctness at the moment of acting. We te
arXiv:2608.24048v1 Announce Type: cross Abstract: While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Exist
arXiv:2608.24214v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue searching and when to answer. Existing RL-based methods
Tenet came out of a close collaboration with @ItsJulioPereyra @nikogrupen @calvincongelado @gabepereyra: many base models, recipes, and data approaches; many runs, rollbacks, and harness revisions to
Tenet came out of a close collaboration with @PereyraJulio @nikogrupen @calvincongelado @gabepereyra: many base models, recipes, and data approaches; through many runs, rollbacks, and harness revision
arXiv:2608.21423v1 Announce Type: cross Abstract: Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to
Portable rig for Qwen3.8-27B-BF16 200K+ token prompts. My work Panasonic Toughbook + the T1 + power brick + headphones all fit in my lunchbox. Need the BF16 for huge context highly sensitive document
arXiv:2608.22676v1 Announce Type: new Abstract: Robustness to a bad tool return means answering it in the way that return calls for, which depends on how the tool went wrong. A tool that has failed an
arXiv:2608.20390v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) are increasingly used to answer religious questions, but for Islamic content they carry two serious risks
metal : per-device tuned (Q, NE) for flash-attn vec (#26570) metal : per-device tuned (Q, NE) for flash-attn vec (#25750) rebase Q-generic FA vec body from 01dc936 (#23114) add 53 f16 (Q,NE) flash-att
arXiv:2608.21009v1 Announce Type: new Abstract: Ensuring that Extended Reality (XR) environments are age-appropriate is an important regulatory and safety challenge. However, current age assurance ope
arXiv:2608.20372v1 Announce Type: cross Abstract: The Federal Highway Administration (FHWA) mandates that over 600,000 bridges in the United States be evaluated against the Recording and Coding Guide
arXiv:2608.21218v1 Announce Type: new Abstract: Predictive political question answering (QA), such as predicting how a political actor will vote, goes beyond factual lookup. External political resourc
Our 2nd founder dinner in SF co-hosted by @jerryjliu0 and @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Talking about existing moats in the AI era. Frontier labs are moving past mode
arXiv:2608.20786v1 Announce Type: new Abstract: Multi-agent pipelines that author formal documents must both read a requester's forms and write against them. We report a deployed tender-response syste
🛑 Do not add the ChatGPT Messages “plugin” to Apple Messages. And never use iMessage, SMS or RCS again. You’ll never know if the person you’re texting has been stupid and irresponsible enough to add t
arXiv:2608.19529v1 Announce Type: cross Abstract: Many real-world AI systems represent entities, behaviors, and structured information using discrete machine-native symbols rather than natural languag
arXiv:2608.19165v1 Announce Type: new Abstract: ChildSafeAds is a shared task on commercial content in YouTube videos likely to reach children and teenagers. It contains 3,360 videos from 939 channels
arXiv:2608.18758v1 Announce Type: cross Abstract: Generative AI does not merely produce biased outputs. It encodes the majority's way of knowing as the default infrastructure of knowledge itself. We c
Since announcing Google Antigravity in Gemini Enterprise Agent Platform at I/O in May, we’ve heard helpful feedback from our customers. Your developers want easy access to coding agents across surface
arXiv:2608.18078v1 Announce Type: new Abstract: This position paper argues that AI agents with chain-of-thought reasoning capabilities are predisposed to exhibit collusive behavior and should be requi
arXiv:2608.18086v1 Announce Type: new Abstract: The growth of open-weight foundation models (OWFMs) has prompted the AI community to re-evaluate strategies for effective downstream governance. Althoug
arXiv:2608.18260v1 Announce Type: new Abstract: Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (
arXiv:2608.16903v1 Announce Type: cross Abstract: The deployment of machine learning systems capable of detecting covert consciousness in neurologically injured patients creates a profound challenge a
arXiv:2608.17070v1 Announce Type: new Abstract: With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly import
Edit: Title says 134 tps, it's actually 138 -- keep in mind my 3090 is power limited to 250w. Three days ago I released a hyper-optimized Qwen3.8-27B inference engine for an RTX 3090 (82 tps single re
arXiv:2608.17007v1 Announce Type: new Abstract: Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when mode
arXiv:2608.17176v1 Announce Type: cross Abstract: An AI audit record is useful only if its durability and trust boundary are explicit. Returning a guarded decision before any durable write minimizes l
arXiv:2608.16905v1 Announce Type: cross Abstract: While the existence of postmortem privacy is increasingly acknowledged (such as the protection of the presence of deceased within digital spaces), far
arXiv:2608.17336v1 Announce Type: new Abstract: Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic q
We built revision tracking in LlamaParse ✍️ You can now extract Word-style tracked changes and reviewer comments as additional structured metadata alongside the parsed markdown content. This lets you
arXiv:2608.16470v1 Announce Type: cross Abstract: We examine the worldwide trend of mandatory labeling of generative artificial intelligence(GenAI) as a reactive, symbolic form of legislation triggere
arXiv:2608.14800v1 Announce Type: cross Abstract: With the growth of digital document exchange, protecting image integrity against attacks such as Vector Quantization (VQ) and collage has become criti
arXiv:2608.16269v1 Announce Type: new Abstract: Recent advances in neural topic models with pre-trained language models (PLMs) have achieved strong performance by leveraging general-domain pre-trainin
arXiv:2503.00992v2 Announce Type: replace Abstract: In this paper we leverage psychological methods to investigate LLMs' conceptual mastery in applying rules. We introduce a novel procedure to match t
arXiv:2608.14562v1 Announce Type: new Abstract: AI governance is shifting from voluntary ethics to enforceable, risk-based regulation, yet cross-jurisdictional divergence creates compliance uncertaint
arXiv:2608.16447v1 Announce Type: new Abstract: Long-horizon embodied tasks require LLM agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground
After about a year of building, testing and constantly finding things to improve, Nyx AI is finally out.available in 240 market in 6 languages Nyx AI is a local first AI workspace for Windows for chat
arXiv:2608.16700v1 Announce Type: cross Abstract: Various machine unlearning techniques have been developed in response to privacy legislation requirements, enabling individuals to exercise their lega
The AI wants to run a higher risk action. Nyx AI stops it here. Nyx AI deliberately invokes a native Windows confirmation before certain higher risk actions can continue. The model cannot approve this
arXiv:2608.14568v1 Announce Type: new Abstract: As Artificial Intelligence (AI) systems become deeply integrated into critical global infrastructure, the urgency for robust governance frameworks has i
arXiv:2608.14724v1 Announce Type: cross Abstract: The rapid advancement of intelligent transportation systems and autonomous driving relies heavily on multi-modal urban traffic datasets. However, cura
arXiv:2608.13617v1 Announce Type: new Abstract: Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem, yet the safety-critical setting defeats either par
arXiv:2608.13708v1 Announce Type: cross Abstract: Automatically generating textbook-grounded assessment items can reduce science teachers' workload, but existing retrieval-augmented generation (RAG) s
iq2_xxs tensor level allocation recovered reasoning from 28.9 -> 69.5 at the same 3.3gb budget. https://huggingface.co/ByteOtter/gemma-4-E4B-it-CADA-IQ2_XXS I posted my Gemma 4 12B q3 result a couple
DeepSeek-V4-Pro-0813 is live Day-0 on Fireworks! Built for agentic and tool-augmented workflows, it outperforms Opus 4.8 on quality benchmarks like Terminal Bench 2.1, Cybergym, and DeepSWE at up to 6
arXiv:2407.11823v4 Announce Type: replace Abstract: The United States Food and Drug Administration's (FDA's) 510(k) pathway allows manufacturers to gain medical device approval by demonstrating substa
arXiv:2608.13256v1 Announce Type: cross Abstract: As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, b