Knowledge catalogue
arXiv:2608.18816v1 Announce Type: cross Abstract: AI hallucinations - that is, outputs which are made up, cannot be verified, or contradict the source material - are generally regarded as an engineeri
arXiv:2608.18736v1 Announce Type: new Abstract: Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimi
arXiv:2608.18097v1 Announce Type: new Abstract: We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corp
I build LoRA Dataset Studio — free, open source, self-hosted, no account and no telemetry. It is not a competitor to ai-toolkit: it orchestrates it. ai-toolkit is the trainer; this is everything befor
I know so many first-time entrepreneurs building on Replit who simply don’t have the funds to spend heavily on usage, but are working on great projects. I’ve been fortunate enough to be able to spend
arXiv:2608.19168v1 Announce Type: new Abstract: A single training example's contribution to a finished model is normally estimated rather than measured, because measuring it takes two expensive full p
arXiv:2608.18085v1 Announce Type: new Abstract: Prior work has shown that large language models (LLMs) can express diverse personality traits in open-ended text generation. However, it remains unclear
arXiv:2608.18523v1 Announce Type: cross Abstract: Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and s
The real lesson here is that if you pick and choose your stats (and which quarters to show, and so on) you can tell any story you like. May startle the markets with this but: OpenAI is growing faster
arXiv:2601.17178v3 Announce Type: replace-cross Abstract: Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, s
arXiv:2608.17956v1 Announce Type: cross Abstract: In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it rep
arXiv:2608.17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts
arXiv:2608.17911v1 Announce Type: new Abstract: As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant ev
arXiv:2608.17168v1 Announce Type: cross Abstract: Reasoning has become a standard technique and feature for contemporary LLMs; however, its application and quality in the context of demanding legal-or
arXiv:2608.18027v1 Announce Type: new Abstract: Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inf
arXiv:2511.23119v3 Announce Type: replace Abstract: High-quality main content extraction from web pages is a critical prerequisite for constructing large-scale training corpora. While traditional heur
arXiv:2608.17360v1 Announce Type: cross Abstract: Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate (ASR) without accoun
Grok 4.6 is #1 on healthcare questions Grok 4.6 just took the #1 spot on MedAgentBench....one of the most interesting benchmarks for real-world agentic healthcare tasks and Grok now has two generation
arXiv:2608.16890v1 Announce Type: new Abstract: Clinical trial programming -- transforming study protocols into analysis-ready datasets under CDISC standards -- is a bottleneck in regulatory submissio
hot take: you shouldn’t have to know whether an idea is worth building before you get to try it 😅 I find that when every build has a cost, you start judging your ideas before you know what they could
arXiv:2608.18009v1 Announce Type: new Abstract: Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources f
arXiv:2608.17607v1 Announce Type: new Abstract: Whole-slide pathology reasoning requires models to integrate gigapixel-scale visual evidence across complete case-linked slides, yet current question-an
Howdy, I'm back again - running my favorite benchmark (it's still unsaturated for the time being so might as well!) previous runs a b https://github.com/michaelasper/benchmarks/blob/main/qwen3.8-27b-p
arXiv:2510.01832v2 Announce Type: replace Abstract: Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complic
arXiv:2608.18050v1 Announce Type: new Abstract: AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets,
arXiv:2205.11930v3 Announce Type: replace-cross Abstract: Human ratings are the gold standard in NLG evaluation. The standard protocol is to collect ratings of generated text, average across annotator
Thoughts About Scaling Law Scaling, but not only of parameters. Every model release now ends with the same question: how many parameters? It isn't a question that can be answered on its own. Parameter
Top 15 models in Agent Arena vs. median task cost: who's delivering the most for their price? Key findings: Even within the top 5, median cost per task ranges from 0.62 for Kimi K3 (Max) to 3.37 for C
A local 27B model scoring frontier performance! Huge thanks to @cline for the shoutout.🥳 This is just the beginning — Qwen3.8-27B will keep finding its way into more fields.🌱 Artificial Analysis Intel
arXiv:2608.14689v1 Announce Type: new Abstract: Residual connections are a fundamental component of transformer architectures, yet the roles of the attention and feed-forward residual pathways remain
arXiv:2608.15145v1 Announce Type: new Abstract: Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inf
arXiv:2602.10204v2 Announce Type: replace Abstract: We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two
arXiv:2608.14551v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for title-abstract screening in systematic reviews, but their decisions lack calibrated uncertainty.
arXiv:2608.14976v1 Announce Type: new Abstract: Text-to-image models are typically reported on average-case prompts, which understates the gap between systems on compositionally demanding requests inv
arXiv:2608.16663v1 Announce Type: cross Abstract: Direct text-to-SQL asks a language model to do two jobs: interpret the business question and construct the complete relational query. In enterprise sc
arXiv:2608.14617v1 Announce Type: cross Abstract: A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequentia
arXiv:2608.15539v1 Announce Type: new Abstract: Video understanding benchmarks have long centered on single-camera settings, where modern multi-modal language models achieve strong performance across
Does your context compactor actually save anything? If you built or tuned one, this one is worth your time. (bookmark it) Task completion is the standard way to validate compression, and it hides the
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:2608.16416v1 Announce Type: new Abstract: Automated machine learning (AutoML) systems search for pipelines within a space of preprocessing operators, learners, and hyper-parameters specified in
arXiv:2608.15004v1 Announce Type: cross Abstract: Lung cancer remains one of the leading causes of cancer-related mortality worldwide, and Computed Tomography (CT) is a primary imaging tool for screen
GLM-5.3 achieves 60 on the Artificial Analysis Intelligence Index, on par with Kimi K3 and up 7 points from GLM-5.2. Once the weights are released it will be tied as the leading open weights model @Za
arXiv:2608.16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task. We ask whether it finished it within policy. We introduce Fiducia-bench, a benchmark
Grok 4.6 takes top spot on this benchmark 🥇 We evaluated Grok 4.6 on MedAgentBench, a benchmark for agentic clinical EHR tasks, and it took the top spot. Grok 4.6 posts the highest pass@1 we've measur
arXiv:2608.15840v1 Announce Type: cross Abstract: We study how many observations are needed to determine the causal direction between two linearly related variables. Classical LiNGAM theory shows that
arXiv:2608.16114v1 Announce Type: new Abstract: As agentic tasks grow in complexity, LLM agents increasingly rely on experiential memory to reuse procedural knowledge across tasks. Effective memory de
arXiv:2608.15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A mode
arXiv:2608.16465v1 Announce Type: new Abstract: Automated red-teaming has produced a growing collection of attack strategies, yet they typically remain scattered across prompts and workflows, making t
arXiv:2608.14552v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated and used in medicine, but clinical usefulness depends on answer accuracy and whether confidence
arXiv:2608.15445v1 Announce Type: new Abstract: When a reward is correct on every training example yet consistent with more than one goal, a model can acquire an unintended one, a failure known as goa
arXiv:2608.16386v1 Announce Type: new Abstract: Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executi
arXiv:2608.14684v1 Announce Type: cross Abstract: LLM judges increasingly evaluate responses against fine-grained rubric checklists. When a sample requires multiple rubrics, current methods typically
arXiv:2411.15041v2 Announce Type: replace Abstract: Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based Visual Question Answering (VQA) tasks, such as INFOSEEK and E
arXiv:2608.15919v1 Announce Type: cross Abstract: Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-spec
arXiv:2608.16831v1 Announce Type: new Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a f
arXiv:2608.14741v1 Announce Type: cross Abstract: We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning. In each p
arXiv:2608.14664v1 Announce Type: new Abstract: How can we determine whether a trained neural network is already deep enough? We study this under a fixed function-preserving residual-growth protocol s
I've been experimenting with Qwen3.8-27B using DeepSeek Harness. It's a monster at long-horizon tasks, and the results were pretty wild. DeepSeek Harness ran on my Windows PC and connected over LAN to
Alex Heath / Time: Sam Altman says OpenAI's decision to pace its AI development was caused by a collection of research observations showing “various degrees of misalignment” — “I think it is a good ti
arXiv:2608.14579v1 Announce Type: new Abstract: Logic synthesis optimization poses significant challenges due to exponentially growing search spaces, sparse reward signals, and diverse logic structure