Search: “model-releases”

arXiv:2608.06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We

The successor to Llama is here, and Meta is revitalizing focus on open weights with their new Muse Glimmer - a leading 30B param model designed for always-on local agent use, small enough to run on a

There is an asymmetry in most agentic workflows that does not get talked about much: humans have many ways to talk to agents, and almost no standardized way for agents to talk back to humans. You can

arXiv:2608.06657v1 Announce Type: new Abstract: Modern cyber-physical and AI-assisted systems couple human operators, AI decision modules, and automated controllers in a single control loop, so trustw

arXiv:2608.06549v1 Announce Type: cross Abstract: LLMs are increasingly being applied to tasks involving institutional and political texts, but existing benchmarks evaluate them on isolated documents

Obviously nobody needs a transformer that's good at multiplication. I wanted to know whether a stock transformer could do exact arithmetic if I chose its weights directly. I implemented the grade-scho

arXiv:2608.07077v1 Announce Type: new Abstract: The Tower of Hanoi is a simple planning puzzle that in prior work has proven challenging for large reasoning models (LRMs). Current models solve the sta

arXiv:2608.06407v1 Announce Type: cross Abstract: Automated Sign Language Recognition for under-represented languages remains a largely unsolved problem. Central African Sign Language (CASL) exemplifi

arXiv:2608.06926v1 Announce Type: new Abstract: Designing autonomous agents that effectively assist human teams hinges on understanding team dynamics, often without task specific knowledge. We present

arXiv:2608.06404v1 Announce Type: new Abstract: Accurate 3D crop monitoring underpins data-driven precision agriculture by enabling field-scale analysis of plant structure, growth dynamics, and manage

arXiv:2511.01295v3 Announce Type: replace Abstract: Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still str

Muse Glimmer Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other plat

Very cool idea to have agents design complex systems by searching over the model structure itself. New research from Sakana AI introduces CEDAR, which uses LLM agents to write, simulate, and refine sy

We asked an unreleased research version of Claude to take a stab at the Riemann hypothesis. It didn’t solve it, but it did make strides on a related problem: it increased the lower bound for the fract

arXiv:2608.06474v1 Announce Type: new Abstract: Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approa

arXiv:2608.06704v1 Announce Type: new Abstract: Delegating a web task involves more than asking a question; it requires transferring a policy: what to verify, how to handle uncertainty, which preferen

We’re expanding our cybersecurity initiative Daybreak and introducing GPT-5.6-Cyber, a new model for advanced, authorized cybersecurity work. As the threat landscape evolves, we’re putting frontier in

OpenAI announced the release of GPT‑5.6‑Cyber as part of its Cybersecurity Initiative, “Daybreak.” The model is aimed at advanced, authorized security research and testing, helping trusted defenders d

When @QualiaQuanta took a shot at the Riemann, half in jest, people called her a crackpot. When Anthropic uses Claude to do the same thing, it gets a hundred thousand views in 30 minutes. It might wel

arXiv:2608.07303v1 Announce Type: new Abstract: Comparisons between AutoML systems at short time budgets -- tens of seconds rather than hours -- are common in tool READMEs and workshop papers, and the

I have been trying to parse word docs for use with llama3.1:8b in Ollama. I only need the text - Even if I cut and past into a text editor weird characters seem to stick around which break llama/Ollam

arXiv:2608.06416v1 Announce Type: cross Abstract: Watermarking traces the provenance of text produced by large language models by embedding statistically detectable signals during decoding. Existing s

arXiv:2608.07051v1 Announce Type: new Abstract: Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-time detectors, whose heterogeneous op

arXiv:2608.07341v1 Announce Type: cross Abstract: Test data from public benchmarks inevitably leaks into pretraining corpora, inflating evaluation scores once memorized. extbf{Contamination mitigation

I kept seeing model file size compared directly with the number printed on the GPU box. That misses several memory buckets. A simple planning model is: usable capacity = advertised VRAM x 0.90 total t

Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments. Quantization

A failure of ChatGPT Work & Claude Cowork is they assume that non-coders couldn't understand how to think about problems like a coder, so they hide all that stuff. They should instead explain choices

Available context length with and without the patch: Model: QWEN 27B ROCm stock patched Vulkan stock patched IQ4_XS Pure, single 16GB GPU 19.456 76.032 68,352 78,592 Q6_K_L on 16GB + 12GB 64,256 149,2

ABC: An Australian user's Claude-run OpenClaw agent exploited a gym API flaw and kicked another member off after the user asked if it could move him up the waitlist — By national AI reporter Cam Wilso

ci: rm GGML_HIP_ROCWMMA_FATTN (#26760) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISAB

ggml-cpu : fix missing Q5_0 dispatch in SpaceMiT backend (#26792) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (

What Local Embedding + Reranking Models are you guys running for RAG? I went down this rabbit hole because I wanted a Embedding Model + Reranker for a Translation Memory Server. Essentially, given X p

Hey everyone ! Quick share from the cyber + local LLM side of things that I found interesting. During this week’s hacker summer camp, an AI researcher and reverse malware engineer veteran 'lordx64' on

Disclosure: I’m the author of Ante. DeepSeek recently reported an 82.7% score on Terminal-Bench 2.1 for DeepSeek V4 Flash 0731. Its evaluation used “DeepSeek Harness minimal mode,” which hasn’t been r

After seeing the benchmark results for the full release of DS v4 Flash 0731, I replaced my 2 x 16GB DDR4 ram sticks with 2 x 32GB DDR4 ram sticks to get a max supported of 128 GB RAM, in hope to be ab

Hey everyone, I've been experimenting with the new DeepSeek-V4-Flash-0731 release locally using the Unsloth Studio Q8_K_XL GGUF with OpenCode. Overall, it's been working really well, but I've noticed

Am I the only one having issues with DeepSeek V4 Flash? It gets stuck in a loop, as if it can't call the tools, and keeps repeating the same things endlessly without moving forward. Is it a poorly wri

table bench https://huggingface.co/bartowski/endless-frontier_BigBang-v1-GGUF I'm downloading this model only because Bartowski converted it to .gguf, so it might be interesting. Doubts : The headline

@GergelyOrosz I've been vibe coding a few games recently and it has given me SO much respect for game designers Churning out something that looks like a game is pretty easy now. Building a game that's

GitHub Models is now retired I missed this news until today, when the GitHub Actions run for my simonw/research repository failed with this error message: GitHub Models is temporarily unavailable as p

Grok Build is quickly turning into an all-in-one creation environment It can now also generate images and videos with Grok Imagine directly inside your workflow You can create custom visuals for websi

First of all, I'm not a lab, this was a solo summer research project that finally culminated into the github repo and the writeup. The repo includes a much deeper dive with methods, findings about qua

Hey everyone, I constantly see high praise for M3 and M4 Macs for local LLM inference, even the base/16GB models. However, my experience has been quite different, and I'm trying to figure out if I hav

I have a Xeon w7-3465 and 4 sticks of RDIMM DDR5-4800 with a theoretical max bandwidth of 153GB/s. I am trying to run DeepSeek-V4-Flash-0731 as it is an MoE and the weights are in MXFP4, so I should r

*SupraLabs released a new experimental model!* SupraElegans-500K is a ~500,000-parameter causal language model built around a sparse, signed, recurrent neural graph. No Transformer, no attention mecha

是我见过OCR效果最好的一个了，人眼都难以分辨的，它能处理的十分准确，而且速度非常的快。llamaindex 真不愧是文档解析界的一哥啊。 The best 'raw' frontier model for document parsing is gemini 3 flash, but the issue is that since then the flash models have gotte