Knowledge catalogue
Hey everyone, After wrestling with hardware and engine issues for days, I finally got Qwen 3.8 Next running properly on my multi-GPU rig. Thought I’d share the setup journey, benchmarks, and thermal r
we're a small lab (switzerland + south africa) and just open-sourced our first model: a 27b fine-tune of qwen3.8-27b specialized for creative writing and short-form personal text (stories, dialogue, r
I gave Jev, Laya, a finetuned ModernCE-base-nli and a finetuned Qwen3.5-4B the controls to Doom. Thanks to TypeSafe AI for Jev access. The video lines up the starts of four separate games with the sam
First time trying something like this. I asked chatgpt and it told me there are mcp server plugins for both ghidra and ida pro as well as RE-MCP which has support for both. I could run that on my low
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
full disclosure, i am the developer of locally uncensored :) i use ollama myself and honestly ollama was never really the problem. the problem was everything around it. one app for local chat, another
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
Okay, this one seems probably really odd (or maybe not), but most harnesses operate within token spaces. That is, every tool output, even batching of tool outputs, go back up into inference calls. Lea
Took me a while since I'm on a family trip and have limited hardware, but here it is! Von: Open-source 'System One' drop-in replacement for TypeSafe's JEV. https://github.com/wfzyx/von https://hugging
arXiv:2609.19538v1 Announce Type: new Abstract: Low-altitude wireless networks (LAWNs) are emerging as a key infrastructure for heterogeneous unmanned aerial systems that support concurrent services w
arXiv:2609.19789v1 Announce Type: new Abstract: Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial i
So I know that Ollama is built on top of llama.cpp, I decided to run a model on both and applied settings on llama.cpp like flash attention and q8/q4 kv cache. On Ollama (using the Python package) I w
arXiv:2609.19347v1 Announce Type: cross Abstract: Robotic additive manufacturing (AM) extends material-extrusion printing beyond gantry kinematics but makes process planning robot-dependent. A slicer-
Reuters: Mistral and other European AI startups accuse US rivals of using safety concerns to entrench their dominance, rejecting Anthropic's calls to pace the frontier — Europe's leading AI company Mi
Hi everyone, I’ve been experimenting with local LLMs on my 48 GB RAM MacBook Pro and I’m still trying to figure out what the best setup is. Ollama feels very fast, which I really like. The problem for
arXiv:2606.18372v2 Announce Type: replace-cross Abstract: Educational dialogue is a valuable but sensitive resource for research: the same transcripts that capture authentic learning often capture per
arXiv:2609.18005v1 Announce Type: new Abstract: Large language model optimization is an active research area, spanning quantization of model weights, early-exit methods for skipping layers, and specul
arXiv:2609.18520v1 Announce Type: new Abstract: Collective intelligence is a collaborative autonomy paradigm in which multiple agents pursue shared objectives through local perception, information exc
arXiv:2601.00743v2 Announce Type: replace Abstract: Integrating symbolic constraints into deep learning models could make them more robust, interpretable, and data-efficient. Still, it remains a time-
I let AI run my phone 60 real tasks, back to back, on the OnePlus I use every day - Best text model still failed 43% of them - Peak chip temp 98.2 C - 69% of the battery gone The benchmark is AndroidL
arXiv:2609.18849v1 Announce Type: cross Abstract: An agentic request spends substantial wall-clock time waiting for tools, and its KV cache holds GPU memory the whole time. Serving systems decide whet
arXiv:2609.18673v1 Announce Type: cross Abstract: Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluation
Hey all, Henry from Cactus Compute here, I kinda wanted to share our latest model and get feedback from the family :) Needle 3 is a small foundation model for automation: you give it the functions you
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:2609.17601v1 Announce Type: cross Abstract: This paper studies decentralized learning of socially optimal equilibria in finite normal-form games over dynamic communication networks. Each agent o
arXiv:2609.17620v1 Announce Type: cross Abstract: Whole genome sequencing (WGS) is essential for precision oncology, yet its clinical adoption remains limited by prohibitive computational costs and mu
arXiv:2609.18392v1 Announce Type: new Abstract: Vision-language-action models (VLAs) have trans- formed the field of robotic manipulation in recent years by combining the semantic understanding of LLM
arXiv:2609.18706v1 Announce Type: cross Abstract: Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust. Matching decompil
arXiv:2609.17755v1 Announce Type: cross Abstract: The analysis of US political language is usually based on the written form (e.g. presidential addresses) or posts broadcasted on various social networ
arXiv:2505.15918v3 Announce Type: replace-cross Abstract: In this work, we evaluate the potential of Large Language Models (LLMs) in building Bayesian Networks (BNs) by approximating domain expert pri
At Google, we see firsthand how the speed, scale, and sophistication of cyber threats continue to challenge traditional enterprise defenses. Today’s defenders can’t rely on reactive triage or fragment
arXiv:2609.17696v1 Announce Type: new Abstract: Document repositories evolve continuously. Guidelines and policies are revised, superseded, and re-uploaded, so the same content recurs in different wor
arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination
arXiv:2609.17764v1 Announce Type: new Abstract: Attention-based rerankers score documents by aggregating query-to-document attention and subtracting a null-query calibration pass to remove positional
arXiv:2609.18908v1 Announce Type: new Abstract: Existing legal benchmarks cover diverse tasks, while continuous monetary remedies remain comparatively underexplored. We introduce ECtHR-NPD, to the bes
arXiv:2609.18991v1 Announce Type: new Abstract: Multimodal LLMs report strong performance on scientific reasoning benchmarks, yet most treat perception and reasoning as a single measurable process. We
arXiv:2609.17602v1 Announce Type: new Abstract: Computational text-based ideal point estimation (CT-IPE) methods are usually compared as named algorithms, yet applying them involves numerous researche
arXiv:2609.17969v1 Announce Type: new Abstract: Long-term memory is becoming a core substrate for personalized AI, yet most systems still represent personalization as discrete records in a largely sta
arXiv:2609.17709v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems typically employ fixed retriever and generator configurations across queries, despite substantial differe
arXiv:2609.18861v1 Announce Type: new Abstract: Adaptive learning systems commonly formulate learning path planning as Exercise-Centric (EC) recommendation, where the next step is inferred from item-l
arXiv:2602.02377v3 Announce Type: replace Abstract: While large language models (LLMs) have achieved strong performance on mathematical problems with verifiable answers, many advanced problems are pro
arXiv:2609.18249v1 Announce Type: new Abstract: Real-world recommendation scenarios are commonly grounded in shared physical environments during user-recommender interactions. This motivates situated
arXiv:2609.17817v1 Announce Type: cross Abstract: Thompson's 'Reflections on Trusting Trust' showed that a compiler can be poisoned to reinsert its own backdoor, so that even recompiling clean source
arXiv:2609.19093v1 Announce Type: cross Abstract: Radiologists follow heterogeneous reporting practices. Two radiologists examining the same image and identifying the same clinical findings might neve
arXiv:2609.18905v1 Announce Type: new Abstract: Health discourse in social media videos often contains densely entangled claims spanning multiple thematic aspects, stances, evidential frames, and rhet
arXiv:2609.18676v1 Announce Type: new Abstract: Generative artificial intelligence (GenAI) is changing how students learn, yet the roles of course context, cognitive reliance, evaluation literacy, and
arXiv:2609.17536v1 Announce Type: new Abstract: Cognitive Stimulation Therapy (CST) offers non-pharmacological support for elders with cognitive impairment, yet scalability remains constrained by reli
arXiv:2602.00408v3 Announce Type: replace-cross Abstract: This paper proposes a novel Variational Graph-to-Scheduler (VG2S) framework for solving the Job Shop Scheduling Problem (JSSP), a critical tas
We've been tuning vLLM/SGLang/llama.cpp setups for a long time and got tired of the profiling part: nsys trace, open the GUI, squint, change a flag, repeat. The profilers assume a human is looking at
arXiv:2609.17274v1 Announce Type: cross Abstract: AI agents increasingly act through agent skills, i.e., natural-language instructions, that direct a host agent toward shell, network, credential, file
arXiv:2609.16302v1 Announce Type: cross Abstract: When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, and
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:2609.16407v1 Announce Type: cross Abstract: On a delivery platform, personalized store ranking greatly influences what users find and order. Unlike digital-only domains, candidate stores are loc
arXiv:2609.16069v1 Announce Type: cross Abstract: Synthetic tabular data can match real data distributions while still violating the semantic constraints that govern valid tabular rows. This reveals a
arXiv:2609.16937v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off bet
arXiv:2609.15995v1 Announce Type: new Abstract: Emerging AI regulation mandates bias audits of high-risk systems, and audit scores are beginning to be used to rank models. Both uses assume different a
Hey experts! I genuinely have this question and would love a general consensus from people actually using these models. LLMs have advanced a lot in benchmarks and in practical usage. Even GPT-4o and G
arXiv:2609.16503v1 Announce Type: new Abstract: Vision language action (VLA) policies continue to grow in parameter count, making deployment on resource-constrained robot platforms difficult. The cent
arXiv:2609.16907v1 Announce Type: cross Abstract: AI companions can provide meaningful relationships, yet these relationships remain vulnerable to platform-initiated changes. We study AI companion dis
arXiv:2609.16058v1 Announce Type: cross Abstract: Red-light violations and harsh braking at signalized intersections are major contributors to traffic accidents. This paper analyzes and predicts human