Knowledge catalogue
arXiv:2608.12328v1 Announce Type: new Abstract: Parameter-efficient fine-tuning methods such as LoRA have transformed the adaptation of large autoregressive language models, enabling task-specific cus
arXiv:2608.12990v1 Announce Type: new Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consol
arXiv:2608.12724v1 Announce Type: new Abstract: Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance
arXiv:2608.13478v1 Announce Type: new Abstract: We present our submission to Task 3 of the Genmu 2.0 Challenge on visual concept unlearning. Building on MapRoute, we introduce task-specific training o
arXiv:2608.13141v1 Announce Type: new Abstract: Vision Transformers (ViTs) demonstrate exceptional performance in computer vision but suffer from large parameter counts and quadratic computational com
arXiv:2608.12339v1 Announce Type: cross Abstract: Large Language models (LLMs) were found to be susceptible to a host of social, affective, and cognitive biases. We examined two mechanisms through whi
arXiv:2603.19703v2 Announce Type: replace-cross Abstract: Estimating covariance matrices is fundamental to a wide range of statistical applications. This paper studies minimax and adaptive estimation
Not directly LOCALLlama related but I thought it was interesting since Mistral and Z.ai are competitors, and more surprisingly they are pricing it (GLM-5.2) even cheaper than their current flagship mo
arXiv:2608.13277v1 Announce Type: cross Abstract: We ask whether language-model pre-training can be decomposed into smaller, independently trainable jobs that can later be recomposed into a coherent l
arXiv:2603.00048v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in sensitive applications including psychological support, healthcare, and high-stakes
arXiv:2608.12442v1 Announce Type: new Abstract: Differentiable rendering has advanced novel view synthesis (NVS), yet applying it to real-world driving remains difficult due to sparse capture viewpoin
My Al Agent Workshop with @mcuban might be the best workshop we've ever had. Over 20,000 people registered and my inbox is filled with people making REAL CHANGE in the way they work and what they're a
arXiv:2608.13210v1 Announce Type: cross Abstract: Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting s
arXiv:2608.13335v1 Announce Type: new Abstract: Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops ab
new langchain oss release! What's new in LangChain? 🚀 🔌 Support for OpenAI's 3.0 SDK (using httpx2) ✨ Support for gemini-3.7-flash Plus a wave of core reliability fixes from external contributors: 🛠️
arXiv:2608.13256v1 Announce Type: cross Abstract: As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, b
arXiv:2608.12630v1 Announce Type: cross Abstract: While large language models can generate entire novels, there is little information about the level of formal variation in their output over many gene
Ollama now supports the DeepSeek Harness. ollama launch dsh Run it completely in your own environment. It comes with Ollama's web search pre-installed. You can use its trajectory view to see what is h
Georgi Gerganov showcased running a LLaMA server on an NVIDIA DGX‑Spark, serving the Qwen 3.8‑27B model in GGUF format (`ggml-org/Qwen3.8-27B-GGUF`). The command demonstrates two quantization options—
One GPU, 1M context, Day-0 ready. Big props to the vLLM team for the seamless integration!👍 Try Qwen3.8-27B on vLLM: @vllm_project https://recipes.vllm.ai/Qwen/Qwen3.8-27B 🎉 Qwen3.8-27B is here from @
arXiv:2512.19799v2 Announce Type: replace Abstract: Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because
arXiv:2608.12789v1 Announce Type: cross Abstract: Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or
arXiv:2608.13552v1 Announce Type: new Abstract: Video world models simulate future states conditioned on current observations and user actions. Recent systems have demonstrated impressive video consis
arXiv:2608.12928v1 Announce Type: new Abstract: We introduce a Polish-language medical visual question answering (VQA) benchmark, built from Polish Board Certification Examination questions for licens
arXiv:2608.12344v1 Announce Type: new Abstract: We test whether the perceived attributes of a consumer technology predict how widely it is owned. In a 2022 Prolific survey of US adults (n = 678), resp
arXiv:2608.12597v1 Announce Type: cross Abstract: Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a ful
arXiv:2608.11506v1 Announce Type: cross Abstract: Adaptive behavior under partial observability depends on internal organization that carries information beyond the current observation. Drawing on Bar
arXiv:2608.12675v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing priva
I've downloaded qwen3.8:27b-mlx through ollama and attempting to run it with Claude Code. On any command, I'm getting 'API Error: 500 system message must be at the beginning. This is a server-side iss
arXiv:2608.13547v1 Announce Type: new Abstract: LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot disti
So, I have been dreaming of getting 17 tokens per second using my RTX 3050 6GB version on a decent context window for Hermes needed above 60k. The hope is that has was a 22GB of DDR 4, hoping they can
Tested this prompt on the full version (BF16). Though this was a single prompt, I executed using vscode GH copilot extension on agent (allow all) mode and let it do its thing. So there were 54 model t
Qwen 3.8 27B is now available on Ollama. It's one of the best open models at this size, and made for agentic tasks and professional work. Try it directly with the apps & harnesses you use: Claude Code
Qwen 3.8-Max is live on Modal, with the full 1M context window and a custom DFlash speculator under the hood. Love seeing our launch partner Modal go all in from Day 0!⚡️ 2.4T parameters. 1M context.
Possibly best way to spend current hour before grabbing 27B model(Instead of opening duplicate repeated 27B posts here). I tried to grab summary(thought of including in this thread) of this video usin
Qwen Live now, an appetizer 👀 Ready for Qwen Live EP2？We will start at 10:00AM！ UTC+8 https://x.com/i/broadcasts/1mGPaZanWBqJN Qwen Cloud：https://www.qwencloud.com/?utm_content=g_20000002312 #QwenClou
Qwen3.8-2.4T-A95B is live on Together AI. The Qwen team’s new open-weight MoE packs 2.4T total parameters with 95B active, a 1M context window, and strong coding & agent capabilities. Start building:
Qwen3.8-27B is available on @ollama ！Any harness you run, the model always delivers. Let's code together, and show us what you build.😎 Qwen 3.8 27B is now available on Ollama. It's one of the best ope
mlx-dspark is an MLX port of DeepSeek's DSpark speculative-decoding drafters (the DeepSpec release), plus z-lab's DFlash, with one lossless verify loop. v0.10.0 adds Qwen3.8-27B via RadixArk's drafter
Qwen3.8-Max is coming to Nebius Token Factory on Day 0. Great to kick things off together with Nebius as our Day 0 launch partner, bringing dedicated inference to more users. Big model, right from the
Qwen3.8-Max is live on Fireworks, ready for agents, heavy coding, and long-context work. Fireworks is right there with us as a Day 0 launch partner. What a way to kick things off!It's Day 0, cue the F
Qwen3.8-Max is live on Together AI. Together AI is with us as a Day 0 launch partner, and we couldn’t ask for a better name to share Day 0 with. 2.4T parameters, 95B active, 1M context — all together
arXiv:2608.13239v1 Announce Type: new Abstract: Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought
arXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signa
arXiv:2608.13304v1 Announce Type: new Abstract: Safety tuning can improve harmful refusal, but models may learn surface-form shortcuts: wrapped harmful prompts bypass safety, while similarly wrapped b
Regular reminder -- the set of public ARC 3 games is called 'demonstration set', not 'eval set' nor 'training set'. It is not meant to be used as training data, and it is not meant to be used as an ev
arXiv:2608.12330v1 Announce Type: new Abstract: The detection of online sexism remains an open problem. Sexism detection is inherently subjective, yet most existing systems reduce multi-annotator labe
The demo video above was created with a single prompt using Qwen 3.8 27B Q8_K_XL. Prompt: create me a single page, html/js/css GeoCities, Laser Wave, 80's retro, minecraft clone named RetroCraft. Embe
Now we have it, a local Opus4.6 (Max) that runs on you local machine! The performance of Qwen3.8-27B blows Glimmer away, and a big leap from its own predecessor. Can't wait for GGUFs... Text: https://
arXiv:2401.11641v5 Announce Type: replace Abstract: In recent years, Large Language Models (LLMs) like ChatGPT have seen considerable advancements and have been applied in diverse fields. Built on the
arXiv:2608.12416v1 Announce Type: new Abstract: Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and lea
arXiv:2608.12879v1 Announce Type: new Abstract: Fractional partial differential equations describe nonlocal dynamics, but discovering them from noisy data is difficult because fractional differentiati
arXiv:2608.13108v1 Announce Type: new Abstract: Multi-source evidence fusion under Dempster-Shafer theory faces two persistent challenges: existing conflict measures assess inter-evidence inconsistenc
arXiv:2608.13345v1 Announce Type: new Abstract: Artificial Intelligence (AI) safety systems combine character shaping (e.g., Reinforcement Learning from Human Feedback [RLHF], Constitutional AI), whic
arXiv:2608.12748v1 Announce Type: new Abstract: Referring Expression Comprehension (REC) is commonly studied under dataset-specific fine-tuning, resulting in specialist models with limited cross-datas
arXiv:2608.13541v1 Announce Type: new Abstract: Part-aware 3D generation aims to create digital assets that are coherent as complete objects while exposing structural parts for editing, material assig
arXiv:2512.13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing contro
arXiv:2608.13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, b
arXiv:2506.15577v2 Announce Type: replace Abstract: Estimating above-ground biomass (AGB) from terrestrial laser scanning (TLS) via quantitative structural models (QSMs) is highly accurate under leaf-
arXiv:2608.13368v1 Announce Type: cross Abstract: This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Netwo