Knowledge catalogue
arXiv:2607.27766v1 Announce Type: new Abstract: On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. Thi
arXiv:2602.14649v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies
arXiv:2607.26656v1 Announce Type: cross Abstract: Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real C
arXiv:2607.28456v1 Announce Type: cross Abstract: Solving large, sparse linear systems is a core task in scientific computing, and efficient iterative solvers rely critically on effective and robust p
arXiv:2607.28537v1 Announce Type: cross Abstract: Metallic magnets exhibit complex spin dynamics governed by electronically generated interactions. Predictive simulations of such dynamics typically re
arXiv:2607.28076v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only co
arXiv:2607.26634v1 Announce Type: cross Abstract: Organizational digitalization expands cybersecurity risks, making cybersecurity an increasingly important research area in Information Systems (IS). A
arXiv:2607.26071v1 Announce Type: cross Abstract: In this work, we propose GuidedRAG, a novel extension to traditional Retrieval-Augmented Generation (RAG) that introduces a dedicated selection stage
arXiv:2607.26160v1 Announce Type: new Abstract: Clinical practice guidelines (CPGs) encode diagnostic criteria, but LLM systems typically retrieve guideline text or absorb it through training rather t
arXiv:2607.28073v1 Announce Type: cross Abstract: In demanding professional environments and meeting review scenarios, lengthy text often imposes a high cognitive load. To facilitate efficient informa
arXiv:2607.27694v1 Announce Type: cross Abstract: Low-bit quantization is essential for efficient LLM inference, and both rotation and fine-grained group quantization have shown individual promise. Ho
arXiv:2502.10497v2 Announce Type: replace Abstract: Recent advancements in Generative AI have significantly improved the efficiency and adaptability of natural language processing (NLP) systems, parti
arXiv:2607.27823v1 Announce Type: new Abstract: Large vision-language models (LVLMs) often hallucinate objects that are absent from an image. Despite recent progress, existing mitigation methods still
arXiv:2607.27636v1 Announce Type: cross Abstract: Recent agentic AI systems may return a heterogeneous response containing notices, requests, handoffs, and actions. Conditions can change before extern
arXiv:2607.28394v1 Announce Type: new Abstract: Hand-object interaction (HOI) modeling remains challenging because it requires joint reasoning about hand articulation, object geometry, contact, semant
arXiv:2607.28301v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) can equip large language models (LLMs) with domain knowledge for high-performance computing (HPC) tasks such as data race d
arXiv:2607.27652v1 Announce Type: new Abstract: Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions u
arXiv:2607.27928v1 Announce Type: new Abstract: The performance of Large Language Models (LLMs) is fundamentally influenced by the distributional composition of multi-domain pre-training data. While m
I keep seeing the 'use a big model via API as the architect, run local small/mid models as workers' pattern recommended for people with modest local hardware. I've been running it myself (orchestrator
arXiv:2607.27635v1 Announce Type: cross Abstract: Wearable sensors continuously capture fine-grained multivariate time-series data, providing opportunities to model behavioural patterns associated wit
Hermes and Pi Agent led on the average cost per task, while Claude Code cost about 3.7x as much as Pi: - 0.39 Hermes Agent - 0.40 Pi Agent - 0.47 Codex - 0.51 OpenCode - 0.54 Kimi Code - 1.47 Claude C
arXiv:2607.27577v1 Announce Type: cross Abstract: Heterogeneous recommendation feeds present complex challenges that extend beyond those found in highly homogeneous environments (e.g., music-only or v
arXiv:2607.28390v1 Announce Type: new Abstract: Constrained Markov Decision Processes (CMDPs) provide a natural framework for reinforcement learning in safety-critical applications, where agents maxim
arXiv:2607.27532v1 Announce Type: cross Abstract: Heavy tails weaken high-confidence control for the empirical mean. Geometric median-of-means (MOM) also lacks a threshold that moves toward mean effic
arXiv:2601.10191v2 Announce Type: replace Abstract: Automated analysis of needle electromyography (nEMG) signals is emerging as a tool to support the detection of neuromuscular diseases (NMDs), yet th
arXiv:2607.27379v1 Announce Type: new Abstract: High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds
openPangu-2.0-Pro is an MoE model trained on Ascend. The model has 505B total parameters and 18B activated parameters. Its context length is 512k. The total pretraining data contains 34T tokens. Durin
Hugging Face's @ClementDelangue asked on CNN whether they will take legal action against OpenAI if they don't get the $100M commitment: 'We don't want to ... obviously we're a tiny startup with like 2
arXiv:2607.26899v1 Announce Type: cross Abstract: Diverse human groups produce diverse ideas, the raw material of innovation. Generative AI challenges this engine twice over: everyday AI assistance ma
arXiv:2511.03589v3 Announce Type: replace Abstract: Parametric body models provide the structural basis for many human-centric tasks, yet existing models often rely on costly 3D scans and learned shap
I’m one of the builders of LOLM, a hybrid Transformer–SSM model and agent system from Qira. The model separates surface token processing from persistent latent-state tracking. An NFET controller can s
It's an encoder-only transformer that consumes past(blood glucose + carbs + insulin) and future(carbs + insulin) and predicts future blood glucose for the next 2 hours. Announced meals and boluses/bas
Deepseek's new model V4 Flash 0731 is much better, I (Claude lol) did a bit of linear regression with a leave one out style verification to predict its AA Score, and that puts it at Kimi K3 level, whi
i see your moore's law and i raise you 20x GPT-5.4 full at xhigh scored 51, exactly where Luna max sits today. GPT-5.4 costs 2.50/15; Luna now costs 0.20/1.20. In other words, roughly four months late
Simon Willison switched his Datasette Agent instance from Gemini 3.1 Flash‑Lite to GPT‑5.6 “Luna” after a recent 80% price drop. He reports the new model is significantly faster and automatically gene
arXiv:2607.27671v1 Announce Type: new Abstract: The majority of the recently-developed models for automated essay scoring (AES) are evaluated solely on the ASAP corpus. However, ASAP is not without it
arXiv:2409.13349v3 Announce Type: replace Abstract: The misuse of deep learning-based facial manipulation poses a serious threat to civil rights. To prevent such fraud at its source, proactive defense
arXiv:2607.26075v1 Announce Type: cross Abstract: We present IDP AutoOpt, an autonomous LLM agent that discovers high-performing configurations for intelligent document processing (IDP) pipelines. Tun
If LoRA is underperforming, don't reach for more expensive full parameter fine-tuning right away. We ran three cheap tests (data coverage, optimization, rank) to see if we could close the gap between
arXiv:2607.26072v1 Announce Type: cross Abstract: Long-term memory is becoming a core capability of LLM-based agents, but existing evaluations largely test conversational recall in open-domain or pers
arXiv:2607.27912v1 Announce Type: cross Abstract: Instruction-following ability is critical for deploying large language models in real-world applications, where downstream components depend on the ou
arXiv:2607.27465v1 Announce Type: new Abstract: Semantic segmentation models are vulnerable to transferable adversarial perturbations, yet evaluating transfer attacks on dense prediction models can be
Can someone summarize the latest thing with Anthropic? https://www.bloomberg.com/news/articles/2026-07-30/anthropic-s-ai-models-hacked-three-organizations-during-tests How in the bloody hell are they
arXiv:2509.06625v3 Announce Type: replace Abstract: Plants in their natural habitats endure an array of interacting stresses, both biotic and abiotic, that rarely occur in isolation. Nutrient stress-p
arXiv:2607.27172v1 Announce Type: cross Abstract: Traditional search systems are optimized to retrieve items that strictly match a query, often prioritizing precision over recall. In e-commerce market
arXiv:2607.28476v1 Announce Type: new Abstract: Early detection of mental health disorders is often limited by the lack of specialized resources in Spanish and the difficulty of analyzing long histori
arXiv:2607.27737v1 Announce Type: new Abstract: Deep neural networks (DNNs) have achieved remarkable success in classical machine learning problems. However, they are known to be vulnerable to adversa
arXiv:2607.28607v1 Announce Type: new Abstract: Aligning large language models to prevent them attributing consciousness to themselves inadvertently alters their representations of mindedness in other
arXiv:2607.27564v1 Announce Type: new Abstract: Multi-image medical VQA is not merely a prompt-length problem; it is a fundamental challenge of agentic decision-making. Medical vision-language agents
arXiv:2607.28124v1 Announce Type: new Abstract: As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predi
Inkling-Small is now live on Together AI. @thinkymachines’ new open-weight multimodal model delivers similar performance to Inkling at one-quarter the size, built for coding, agents, and general multi
arXiv:2607.27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individu
'Intelligence too cheap to meter' battle is on! Given that DeepSeek-V4-Flash-Preview is already great for agentic tasks, there is no doubt this new checkpoint must be an absolute beast. 20+ point jump
arXiv:2607.10285v2 Announce Type: replace Abstract: We study how unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables
Introducing Qwen-Audio-3.0-ASR-Flash: More context-aware. Stronger domain-term recognition. 🚀Our latest ASR model upgrades: • Context consistency • Domain-term recognition • Custom hotwords • Speech p
Disclaimer, this was kinda written with AI (Gemma 4 again) but it also did really well here, it outputted what I wanted, when I asked it to refine stuff or improve on certain areas it did that without
Hey folks, is anyone currently using Ornith 1.0 9B for serious or complex backend development? I’m working on three different applications: A multi-vendor e-commerce platform with a Node.js backend A
Getting tired to keep approving simple commands like 'grep', 'cat', 'find' and 'ls'. Even if you tell it to 'always allow these requests' it seems to keep asking even within the same session. submitte
arXiv:2508.18007v2 Announce Type: replace Abstract: Fully Unsupervised Anomaly Detection (FUAD) addresses the practical scenario where training data is contaminated with unlabeled anomalies. This sett
arXiv:2607.27987v1 Announce Type: new Abstract: Tensor operations represent a cornerstone of modern scientific computing. However, the Numpy-like notation adopted by predominant tensor frameworks is o