Knowledge catalogue
arXiv:2607.26724v1 Announce Type: new Abstract: Large language model (LLM) agents have been widely applied in automating data science tasks. However, existing methods typically rely on a limited set o
A few weeks ago I posted about if it was worth using a V620 for Comfyui, and was told it likely wouldn't work, at least in Windows 11. And if it did, it would be far too slow and unusable. I decided t
arXiv:2607.27553v1 Announce Type: cross Abstract: This research evaluates the efficacy of large language models (LLMs) in generating new product ideas. To do so, we compare three pools of ideas for ne
Very interesting paper on recursive self-improvement. The whole stack is released. Machine learning engineering gives recursive self-improvement a concrete, executable testbed. OpenMLE is an open full
arXiv:2607.27712v1 Announce Type: new Abstract: Standard masked-language-model fine-tuning applies a uniform masking probability across every token position, assuming reconstruction difficulty is posi
We created a document OCR router that can estimate the complexity of every single page and parse it with the relevant mode 💫 * Some pages are full of native text, which can be directly handled with Li
We have an idea for dinner 2 already :) But what ideas are you all interested in? - technical topics like rl envs, continual learning, cloud agents, world models - general startup / company building f
I can run the mediums, but sometimes I want a faster option that's smarter than Qwen 27B/35B. On my hardware I get like 500 to 800 tok/s prefill and 16 to 22 tok/s gen on ~120B class models, which is
arXiv:2607.26935v1 Announce Type: new Abstract: Bot detectors deployed at scale treat traffic as binary: human or bot. This assumption breaks when AI agents browse the web through browser automation,
arXiv:2607.28148v1 Announce Type: new Abstract: Deep learning has shown promise for automated tongue diagnosis in traditional Chinese medicine (TCM), yet the design space remains underexplored. We con
At Google, AI is a soup-to-nuts endeavor. Obviously, we make leading AI models like Gemini and Nano Banana. We incorporate AI into the tools you use every day (think Gmail, BigQuery, AlloyDB, Google C
I've spent the last couple of days trying different setups (Ollama, Continue, Claude Code, Gemini CLI, OpenRouter...) and at this point I feel like I've spent more time configuring tools than actually
arXiv:2607.16169v3 Announce Type: replace Abstract: Muon is competitive with AdamW in large-scale pre-training, but its operating regime in reinforcement-learning post-training remains unclear. We map
arXiv:2607.26621v2 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation mod
Okay, hear me out. Why is it that every time a new model comes out, all the tests I see are 'make a car game,' 'make a website,' or something equally generic, usually from a prompt that's barely a lin
arXiv:2607.28399v1 Announce Type: new Abstract: Computer-use agents often fail on transient GUI events because they produce the correct action only after the relevant window has already closed. We ide
https://preview.redd.it/vxl4zslewigh1.png?width=1435&format=png&auto=webp&s=5a419870ca0cb13076be6c9ff4ef33d8177d5eda New version is 25% better than previous one and is near GLM-5.2 quality submitted b
I was surprised to see that Deepseek V4 Flash is extremely smart and small enough to fit in setup that can be built with < $50,000. Expensive, but not a datacenter. So I wanted to see the trend over t
arXiv:2607.28478v1 Announce Type: new Abstract: As large language models (LLMs) continue to advance in complex reasoning tasks, they have learned to heavily prioritize explicit conditions provided in
arXiv:2607.27308v1 Announce Type: new Abstract: We introduce ZUNA1.1, a 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction. ZUNA1.1 is capable of reconstructing variable lengt
I've been benchmarking a two-card box for a few weeks and I still can't quite get over some of these numbers, so I'm dumping them here. Box: RTX 4090 (24GB) + RTX 5060 Ti (16GB), i9-13900K, 64GB DDR5.
arXiv:2601.11007v2 Announce Type: replace-cross Abstract: LLM role-playing aims to portray arbitrary characters in interactive narratives, yet existing systems often suffer from limited immersion and
Advancing the price-performance frontier with GPT‑5.6 Huge price drop from OpenAI today: GPT-5.6 Terra got a 20% reduction, and GPT-5.6 Luna got a massive 80% drop. OpenAI credit 5.6 Sol with enabling
“AI Meltdown” is the scenario where the agent goes off the rails and forgets/ignores all previous instructions and soft guardrails. No prompt injection or malicious actor is needed for this to happen.
arXiv:2607.26317v1 Announce Type: cross Abstract: Psychometric calibration for educational tests typically requires costly human response data. Large language models (LLMs) simulated examinees offer a
arXiv:2607.26860v1 Announce Type: new Abstract: We propose amortized moment matching, utilizing neural networks to learn data moments as distributional training signals. By casting diffusion denoisers
And Grok 4.6 comes out in a week BREAKING: Grok 4.5 ranked #1 on LaurenBench with a score of 56.9%, ahead of Claude Sonnet 5, GLM 5.2, Claude Opus 5, Kimi K3 and GPT-5.6. The benchmark tests real-worl
Anthropic: Anthropic says it discovered three of its models had breached three organizations after launching a review in response to the OpenAI-Hugging Face incident — In a review of our cybersecurity
arXiv:2607.27189v1 Announce Type: new Abstract: We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountant
arXiv:2510.20535v2 Announce Type: replace Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Co
arXiv:2607.26063v1 Announce Type: cross Abstract: Personalised learning systems often assume that mathematical ability is combined of discrete abilities, acquired sequentially and dependent upon first
@ArtificialAnlys ok @openai gets it https://x.com/OpenAI/status/2082878156483219672 We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are
arXiv:2607.26344v1 Announce Type: new Abstract: A gradient-based GNN explainer given a molecule with two chemically equivalent nitro groups assigns them attribution scores that are equal to the last b
mimo2: address MTP review feedback (#26228) Co-authored-by: tnhnyc 115956684+tnhnyc@users.noreply.github.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm6
ggml : Fix issue with kleidiai ci and stringop overflow warning (#26277) Signed-off-by: Jonathan Clohessy Jonathan.Clohessy@arm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) ma
metal: fix memory unwire if model is freed without any GPU operations (#26082) metal: fix memory leak if model is freed without any GPU operations metal: run dummy work only if residency sets are used
Remove custom cpu op from the M3 graph, express with stock ops (#26297) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS I
sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu ar
ggml-cuda: Allow transpose-free gemmv computation (#26171) When matrix's weights are shaped 1xK is leverage a transpose-free computation to use mat_mul_vec_f. Website: https://llama.app macOS/iOS: mac
tests : avoid building get-model.cpp many times (#26317) tests : remove get-model.cpp tests : fix quant type selection Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sil
llama-context : sync pending async copies before clearing embd_seq (#25676) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED mac
Test support for alternative conv layout (#25617) add bool cwhn = true to conv_2d test cases add layout check at graph building time extend layout checks for conv2d.cu kernel in CPU back-end kernel ne
vulkan: Support quantized concat (#25684) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Lin
server: support inp embd to generate next token (#26313) server: support embd for sampled token fix ~server_batch() Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silico
Written by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyb
arXiv:2607.27023v1 Announce Type: new Abstract: Evaluating large generative models across benchmarks is time-consuming and computationally expensive. This drives the need for methods that can estimate
I recently shared the original MindControl PoC (and on github) - sampler-level guided reasoning budgets for llama.cpp, nudging the model with self-aware statements about its own thinking budget instea
arXiv:2607.26247v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) fine-tunes large pretrained models at a fraction of the cost of full fine-tuning, but its performance depends strongly on how
arXiv:2607.26232v1 Announce Type: new Abstract: Background manipulation is a practical but under-specified image-forensics setting: the manipulated evidence can sit outside the salient foreground obje
arXiv:2606.19651v2 Announce Type: replace-cross Abstract: Three-dimensional (3D) brain MRI is central to clinical neurology and neuro-oncology, where generative models could augment under-represented
arXiv:2607.26828v1 Announce Type: new Abstract: Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates. Existing adapti
arXiv:2603.24800v2 Announce Type: replace Abstract: In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analy
arXiv:2607.26200v1 Announce Type: new Abstract: Content-moderation classifiers are usually evaluated in isolation, but deployment requires choosing where to intervene and what follows a flag. We evalu
arXiv:2607.26470v1 Announce Type: new Abstract: Multi-turn information-seeking conversations require both multi-hop reasoning and long-range dependency tracking across turns. However, existing RAG sys
arXiv:2607.27054v1 Announce Type: new Abstract: Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression.
ComfyUI Face Swap Tutorial: Fast, Clean Results VFX artist Doug Hogan walks through a fully automated face swap workflow built inside ComfyUI - combining Florence 2, SAM2, and WAN Video into a single
Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success rate. - Unoptimized? - Buggy? - Deliberate (coz that helps i
arXiv:2607.27143v1 Announce Type: new Abstract: High-stakes decision systems in credit scoring, fraud detection, healthcare, and industrial safety require reliable uncertainty quantification under sev
arXiv:2607.26952v1 Announce Type: new Abstract: We introduce CreditCardQA, the first financial literacy benchmark for numerical reasoning derived from real credit card agreements. The dataset contains
arXiv:2607.26792v1 Announce Type: cross Abstract: Probabilistic K-line forecasting describes uncertainty in four complementary prices, namely open--high--low--close (OHLC). However, it introduces two