Knowledge catalogue
Behold, workflow whisperers! YuE2 was released a week ago and I gotta say it's splendid for its size (3B). My favourite local music generation model at the moment, no doubt. The good news is, I've fou
TL;DR: I run a mismatched Tesla V100-PCIE pair—one 16 GB card and one 32 GB card, 48 GB total—in a Proxmox/LXC-based local-inference lab. The practical winner so far is a recent CUDA build of llama.cp
Live now: our Inference Engineering Track from AI Engineer World's Fair 2026. A benchmark tool told to run 200 queries a second that ran 38 and reported 200. A model that answered one prompt in a thou
The goal of this post is 2 fold. First, I wanted to show what a local model like Qwen 3.8 27B running on a single RTX 5090 GPU in a harness like Row-Bot can do. Second, I wanted to create a full featu
Since OpenAI retired SWE-bench Verified in February (every frontier model tested could reproduce reference fixes for some tasks; underspecified tests rewarded knowing the intended fix), I've been tryi
arXiv:2609.20562v1 Announce Type: new Abstract: Automated quality assessment, enhancement, and segmentation of multiple structures in 0.064,T ultra-low-field pediatric MRI are limited by a low signal-
arXiv:2609.20620v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate a
arXiv:2609.20625v1 Announce Type: cross Abstract: Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitw
arXiv:2607.09678v2 Announce Type: replace Abstract: When LLM agents hand information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that str
arXiv:2609.19630v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into vehicle voice assistants. But linking natural-language requests to vehicle functions creat
arXiv:2607.15394v2 Announce Type: replace Abstract: Black-box models limit the adoption of artificial intelligence in medicine because their predictions are difficult to interpret and reproduce. We pr
arXiv:2609.19569v1 Announce Type: cross Abstract: Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial
arXiv:2609.20252v1 Announce Type: cross Abstract: High-quality representations are essential for a wide range of downstream tasks. Dedicated embedding models are explicitly optimized for representatio
arXiv:2609.19156v1 Announce Type: new Abstract: Data-driven fine-tuning is widely adopted to enhance reasoning in Large Language Models (LLMs) due to its simplicity and efficiency. However, mainstream
arXiv:2609.19291v1 Announce Type: cross Abstract: Large Language Models (LLMs) have made remarkable progress in the processing and modeling of many languages. Yet, unlike human multilinguals, they exh
arXiv:2509.21891v3 Announce Type: replace-cross Abstract: Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been t
arXiv:2609.18516v1 Announce Type: new Abstract: While Large Language Models excel in natural language processing, efficiently extending their capabilities to spoken input remains a significant challen
arXiv:2609.18203v1 Announce Type: new Abstract: Human values are deep motivational orientations that shape human behaviors. In e-commerce, they reveal the stable drivers behind users' purchase decisio
https://www.curseforge.com/minecraft/mc-mods/verity-je Hi guys <3 What is the best performing ai agent that works with this mod? its called the verity mod. to be more general for anyone who doesnt kno
arXiv:2609.18306v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in applications involving interaction between agents, where their output plays a role in collecti
arXiv:2609.17708v1 Announce Type: cross Abstract: Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated estimate of the probability that
arXiv:2609.17549v1 Announce Type: new Abstract: Cyberbullying (CB) is a complex social phenomenon characterized by repeated aggression, power imbalance, and multi-party interaction. Although large lan
arXiv:2609.18935v1 Announce Type: new Abstract: A game character should not have to reread its entire life before every conversation. For locally deployed language-model characters, however, revising
arXiv:2609.17868v1 Announce Type: new Abstract: Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathol
I've been building Selfcoder, a VS Code coding agent focused specifically on local models. I originally started working on it because I was frustrated with the context management when using local mode
arXiv:2609.19070v1 Announce Type: new Abstract: This paper introduces ``question archaeology'', a specific evaluation task focused on inferring the single, authentic 'genesis question' that motivated
arXiv:2609.17788v1 Announce Type: cross Abstract: We present SAiFE_gym, a Python module that provides a collection of simulation environments for studying trading problems in Constant Product Markets
arXiv:2609.18985v1 Announce Type: new Abstract: Knowledge-editing benchmarks certify local correctness, whether an edited model produces the new fact on near-edit prompts but not how much of the origi
arXiv:2609.18156v1 Announce Type: new Abstract: Teochew has a substantial speaker community and exhibits distinctive lexical, syntactic, and pragmatic features, yet textual resources for evaluating la
arXiv:2609.18341v1 Announce Type: cross Abstract: When someone asks an AI assistant which doctor to see or which firm to trust with their savings, the answer is a referral. We audit AI provider recomm
arXiv:2609.18565v1 Announce Type: cross Abstract: We propose a compact NISQ-compatible quantum transformer architecture for synthetic QNLP sequence modelling. The model preserves the autoregressive ne
arXiv:2609.18521v1 Announce Type: cross Abstract: Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing bench
arXiv:2609.18283v1 Announce Type: new Abstract: As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large langua
arXiv:2609.16793v1 Announce Type: cross Abstract: People increasingly reason with large language models (LLMs), yet complementary capabilities do not guarantee outperforming both components. In a betw
arXiv:2609.17014v1 Announce Type: cross Abstract: Machine learning (ML) has become the dominant approach for network traffic classification, achieving very high predictive performance. However, a mode
arXiv:2609.16338v1 Announce Type: new Abstract: Ternary Large Language Models (LLM) store every weight as one of three symbols {-1,0,+1}, so the cost of a ternary model is conventionally referenced to
arXiv:2609.16096v1 Announce Type: cross Abstract: Large language model coding agents have recently become useful for software tasks, but weaker or open-weight agents still struggle to reliably interpr
arXiv:2609.16567v1 Announce Type: new Abstract: Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generaliza
arXiv:2602.05718v2 Announce Type: replace Abstract: Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (extit{i.e.}, labeling only a single frame per action
arXiv:2609.16528v1 Announce Type: new Abstract: Building accurate decision-support tools for next-generation air traffic control requires robust trajectory prediction models. We present a flow-matchin
arXiv:2609.16012v1 Announce Type: new Abstract: Despite significant progress in general visual question answering and cross-modal understanding, multimodal large language models still face a pronounce
arXiv:2609.17223v1 Announce Type: new Abstract: Medical AI models hold immense potential to improve patient outcomes, but they are also known to unintentionally memorise individual records from their
arXiv:2609.16548v1 Announce Type: new Abstract: Post-click conversion rate (pCVR) prediction requires jointly modeling feature interactions and sequential user behaviors. The KDD Cup 2026 Tencent UniR
arXiv:2605.05616v2 Announce Type: replace Abstract: Rheumatoid arthritis (RA) assessment from hand radiographs requires multi-level analysis and modeling of anatomical structures and fine-grained loca
arXiv:2603.02227v2 Announce Type: replace-cross Abstract: Learned gates can approximate sparse attention patterns on frozen transformers, yet provide limited benefit over random gates when trained joi
arXiv:2609.16071v1 Announce Type: cross Abstract: Cross-machine deployment of industrial world models requires transfer across changes in dynamics, sensing interfaces, sampling regimes, and control un
arXiv:2609.16737v1 Announce Type: cross Abstract: Generative video models can serve as a promising backbone for robot navigation by predicting future observations as video plans. Recent approaches oft
arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasoning
arXiv:2609.16864v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks beca
arXiv:2609.17421v1 Announce Type: new Abstract: Audio-Visual Navigation (AVN) requires an agent to localize and navigate toward a continuously vocalizing target relying solely on visual observations a
With the recent Nvidia Huggingface acquisition and frontier AI labs screaming about safety and putting guardrails everywhere, I think it's important that we have local models that aren't affected by a
arXiv:2609.17346v1 Announce Type: cross Abstract: To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the con
I implemented expert lookahead, a trick that gets a 10%+ performance improvement on MoE models running on low-memory macs (Qwen 3.8 flash in this case) while using expert-offloading/ssd-streaming (usi
arXiv:2609.13878v1 Announce Type: new Abstract: Spatio-temporal traffic data are central to intelligent transportation systems, yet their heterogeneity poses significant challenges for large-scale mod
arXiv:2609.13239v1 Announce Type: new Abstract: Diffusion models represent one of the most advanced paradigms in generative modeling. Leveraging their development, a growing number of style transfer m
arXiv:2609.13345v1 Announce Type: cross Abstract: Probabilistic forecasting is central to decision-making under uncertainty, yet its methodological landscape has become increasingly fragmented across
arXiv:2609.15478v1 Announce Type: new Abstract: Multimodal agents can create complex videos in software such as Blender by coding without relying on diffusion models. Yet video understanding benchmark
arXiv:2510.09302v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in difficult purely textual mathematical reasoning tasks, even
arXiv:2609.13230v1 Announce Type: cross Abstract: Predicting drug--target binding affinity (DTA) requires models to distinguish subtle chemical and structural determinants underlying molecular recogni
arXiv:2609.14657v1 Announce Type: cross Abstract: While Vision-Language Models (VLMs) excel at visual reasoning, generating structured, editable Scalable Vector Graphics (SVG) remains a fundamental ch