Knowledge catalogue
Lily treats Apple silicon as a distinct inference platform and maps Qwen’s operations directly to its compute and memory architecture. Lily is now available: https://github.com/perplexityai/pplx-garde
arXiv:2609.00192v1 Announce Type: new Abstract: Public trust in Autonomous Vehicles (AVs) may depend not only on technical success but also on the fairness of their decision making. While a recent tre
Release: llm-gemini 0.34 New model gemini-3.8-flash for Gemini 3.8 Flash, with low, medium and high thinking levels. #146 Fixed async responses failing to record the resolved model version. Thanks, Ch
arXiv:2609.01182v1 Announce Type: new Abstract: Flagship language models appear saturated on benchmarks like MMLU (Hendrycks et al., 2021), scoring above 90% - yet benchmarks test only what the experi
I'm looking for a small LLM to act as a Linux command assistant. I will use llama.cpp. use case: - User asks in natural language. Model outputs only the shell command - Should work well with no reason
arXiv:2609.01014v1 Announce Type: new Abstract: Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollm
This may be somewhat specific to Qwen3.8 27b and the Apple M5 series, perhaps, but enough of us are running this combo that it's worth tossing out there. GGUF models with MTP have been the fastest way
arXiv:2609.01272v1 Announce Type: new Abstract: Prospective memory means carrying out a deferred intention at the right future cue while other work continues. Benchmarks now isolate it as an agent ski
arXiv:2609.01319v1 Announce Type: cross Abstract: At a junction, a score field can reveal weighted tangent rays, yet these first-order quantities do not determine how individual branches bend or how t
arXiv:2609.01397v1 Announce Type: cross Abstract: The Rashomon effect is a machine learning phenomenon where equally accurate models produce different predictions for the same inputs (predictive multi
Meet the team behind the Replit MCP this Friday at 9AM PT. Join the Replit community team live with Amadeo Pellicce (@amapel) and Jean-Luc Thumm (@jeanlucthumm) for a deeper dive on the Replit MCP, no
arXiv:2609.00491v1 Announce Type: new Abstract: Communicating across cultures is inherently challenging, especially through culturally dense and ambiguous formats like memes. While people expect large
arXiv:2609.00865v1 Announce Type: cross Abstract: Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning p
arXiv:2609.01306v1 Announce Type: cross Abstract: Triangle-based neural rendering bridges neural scene representations and conventional graphics pipelines by optimizing explicit geometric primitives c
arXiv:2511.16949v2 Announce Type: replace-cross Abstract: Dense 3D semantic occupancy perception is critical for mobile robots operating in pedestrian-rich environments, yet it remains underexplored c
arXiv:2601.01480v3 Announce Type: replace-cross Abstract: Traffic forecasting systems rely on fixed sensor networks that frequently exhibit contiguous blackouts. Such outages are usually treated as ig
arXiv:2609.01231v1 Announce Type: new Abstract: We prove that a multi-head scaled dot product attention can be viewed as a parameter identification strategy. The ratio of unidentified parameters to th
arXiv:2609.01036v1 Announce Type: cross Abstract: A lack of suitable datasets has limited the research into the privacy risks of novel smart city sensors, such as thermal cameras, depth cameras, and l
arXiv:2512.05658v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) with reasoning capabilities have recently demonstrated strong potential in medical Question Answering (QA). Exist
arXiv:2609.01235v1 Announce Type: cross Abstract: MutMem V1 introduced retention-preserving, cryptographically authorized mutation for persistent agent memory but did not provide a complete portable v
Alright, I posted that I had my agent test a bunch of different workflows for over 12 hours and got the 'Bro just wasted 12 hours of credits'. It was obvious the proof should come from the visual data
arXiv:2609.01338v1 Announce Type: cross Abstract: On-device mobile Large Language Model (LLM) inference is gaining significant attention. However, mobile devices operate in highly dynamic multitasking
arXiv:2609.01549v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect informatio
arXiv:2609.00389v1 Announce Type: new Abstract: We combine neural network means with exact Matern kernel regressions of their residuals and of their learned features, and evaluate the pairing on two p
arXiv:2609.01102v1 Announce Type: new Abstract: Symbolic Regression (SR) seeks to find succinct mathematical expressions that represent the fundamental relationships within data, providing interpretab
arXiv:2601.14121v2 Announce Type: replace Abstract: Identifying when and where a news image was taken is crucial for journalists and forensic experts to produce credible stories and debunk misinformat
arXiv:2510.25060v2 Announce Type: replace-cross Abstract: In this work, we study the nonlinear dynamics of a shallow neural network trained with mean-squared loss and leaky ReLU activation. Under Gaus
arXiv:2609.01207v1 Announce Type: new Abstract: This paper studies a class of uncertain multi-input multi-output (MIMO) nonlinear systems using extended PID (EPID) control. We focus on systems possess
arXiv:2601.19481v2 Announce Type: replace-cross Abstract: Evolutionary dynamic optimization (EDO) commonly assumes that environmental changes can be detected from fitness variations and handled throug
arXiv:2602.17826v2 Announce Type: replace Abstract: Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in
arXiv:2609.00015v1 Announce Type: new Abstract: AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, controll
Ivan Mehta / TechCrunch: OpenAI launches a ChatGPT Health integration with Epic's EHR system and a new Healthcare Public Data plug-in that can fetch info from sources including PubMed — OpenAI said to
Anybody else struggling with deepseek after the initial prompt? Somehow it is getting mixed up very easily, even button functionality has been PITA when doing stuff. Never had these problems with Open
openwiki 🤝 cursor we recently made openwiki more accessible than ever with coding agent integrations. our newest integration is cursor! two commands and you're ready to go: 1⃣ npm install -g openwiki@
arXiv:2609.01466v1 Announce Type: new Abstract: A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trac
arXiv:2609.00699v1 Announce Type: new Abstract: Reward models trained on human preferences are known to suffer from length, formatting, and other stylistic biases. In this paper we use patterning, whi
arXiv:2609.00906v1 Announce Type: new Abstract: High-precision insertion remains a fundamental challenge in robotic manipulation due to the strict alignment requirements and contact-rich interactions
arXiv:2510.03784v2 Announce Type: replace Abstract: Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remain
https://preview.redd.it/6h4xc5o8l6nh1.png?width=1158&format=png&auto=webp&s=b65074b6baaa1faa2347e5259229c8ba803bcd4b Here is link to repo: https://github.com/perplexityai/pplx-garden/tree/main/lily It
arXiv:2609.00958v1 Announce Type: new Abstract: We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler
arXiv:2602.09058v2 Announce Type: replace-cross Abstract: Persistent entropy is a scalar summary of persistence barcodes widely used to detect regime changes, yet there is no account of when a structu
arXiv:2609.01188v1 Announce Type: new Abstract: Large Language Models (LLMs) are revolutionizing digital communication by powering conversational agents deployed across domains such as customer servic
arXiv:2609.01379v1 Announce Type: new Abstract: Encoder-only Transformers remain effective for discriminative and representation-learning tasks, yet Polish encoders still largely rely on BERT/RoBERTa-
arXiv:2609.01244v1 Announce Type: cross Abstract: Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, whi
arXiv:2609.00555v1 Announce Type: cross Abstract: Language-driven dexterous grasp models, such as DextER, perform well when instructions specify where to grasp, but we find they fail systematically wh
arXiv:2609.00710v1 Announce Type: cross Abstract: An LLM application often sells or internally allocates several service products: a small or premium model, a short or long token cap, and possibly mul
arXiv:2603.25093v2 Announce Type: replace Abstract: Machine learning models can achieve high predictive accuracy in hydrological applications but often lack physical interpretability. The Mass-Conserv
Ollama has just announced, based on 'feedback', that they have switched to a credit model. If you're still on the old 20 Pro compute plan, DON'T SWITCH. I decided to calculate it before I risked click
(Paid 5,849 + tax, which came out to 6,279) TL;DR - Bought this 5090 prebuilt and I want to sanity check if I made the right decision and at the right time. Hey everyone. So I want to start off by say
https://preview.redd.it/74bmvel9b5nh1.png?width=1602&format=png&auto=webp&s=0d0c1adaa016a486ffd97c4c466e980dc611b139 I've only recently started looking deeper into vLLM after running llama.cpp for a g
arXiv:2609.01537v1 Announce Type: new Abstract: Q-matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires
Direct2D has always been the biggest hurdle for Paint.NET on WINE, and it's clear that it will never be completed enough for Paint.NET's use. And I can't just 'disable' the use of Direct2D. So, instea
arXiv:2609.00111v1 Announce Type: new Abstract: We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of
Extended reasoning and post-training appear to be the keys used by DeepSeek, Qwen, and GLM to boost performance (leveraging higher token counts). And Qwen 4 hasn't even been released yet. Of course, w
Hi, I've noticed that the model often sees 'garbled text' in its context. Sometimes it declare that the tools instructions are corrupted, sometimes it is the content of some .md files, ora other files
arXiv:2609.00049v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is essential for deploying large language models (LLMs) under strict resource constraints. State-of-the-art PTQ metho
arXiv:2609.00585v1 Announce Type: cross Abstract: We present the Real-Time Neuromorphic Spectrum Intelligence Simulator (RT-NuSIS), a modular framework to study spiking neural network (SNN) and memris
arXiv:2609.00194v1 Announce Type: new Abstract: Document-to-slide generation is challenging because slides are dense editable artifacts that require both faithful content selection and precise spatial
arXiv:2609.01525v1 Announce Type: cross Abstract: A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data. W
arXiv:2609.01292v1 Announce Type: cross Abstract: Relational Deep Learning (RDL) has become a powerful paradigm for learning from multi-tabular data. However, manually defining RDL prediction tasks is