Search: “model-releases”

The new DeepSeek v4 Flash is now available in Hermes Agent through Nous Portal and OpenRouter 🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabili

The price wars that I have predicted going back to August 2023 are now in full swing. All this was inevitable – as long as everyone builds more or less the same kind of AI, there is no moat, and profi

They knew the charges were bullshit from the start. They knew they arrested an innocent man just to intimidate others and appease the fake narrative of an incompetent fucking toddler. This is the real

arXiv:2607.27303v1 Announce Type: cross Abstract: Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve

arXiv:2607.28186v1 Announce Type: new Abstract: Existing farmland remote sensing image (FRSI) segmentation follows a 'Think with Intra-Image' paradigm, assuming that the current image contains suffici

arXiv:2607.27830v1 Announce Type: new Abstract: High-resolution visual question answering (HR-VQA) is often treated as a problem of insufficient evidence acquisition, where failing multimodal large la

This is both a real incident (in that the AI really did get unauthorized access to real systems) and also something it was (sort of) prompted to do. In a review of our cybersecurity evaluations, we fo

This will happen frequently as AI becomes smarter and more agentic In a review of our cybersecurity evaluations, we found three incidents in which a Claude model reached the internet from within or wh

arXiv:2607.27680v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become the standard mechanism for fine-tuning large pretrained models, yet its statistical properties remain only parti

arXiv:2509.17041v2 Announce Type: replace Abstract: Behavioural differences across organisms, whether healthy or pathological, are closely tied to the structure of their neural circuits. Yet, the fine

arXiv:2405.04376v4 Announce Type: replace Abstract: Hyperparameter tuning, particularly the selection of an appropriate learning rate in adaptive gradient training methods, remains a challenge. To add

arXiv:2509.25991v3 Announce Type: replace-cross Abstract: Detecting deceptive multimodal content on social media has become an increasingly important problem. Two major types of deception dominate: hu

arXiv:2607.26307v1 Announce Type: new Abstract: Contemporary LLM-based coding agents produce code as black-box outputs: the rationale behind each line is hidden, the evolution of the code through benc

arXiv:2607.27940v1 Announce Type: cross Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint

Try Grok 4.5 http://X.ai/cli BREAKING: Grok 4.5 outperforms GPT-5.6 Terra across almost all shared benchmarks on AskClash, leading in ACB, GPQA, SWE-P, and Atlas while also achieving a higher overall

arXiv:2607.28287v1 Announce Type: cross Abstract: ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal w

First we have Jamba2-Mini Ultra Uncensored Heretic, it's a model which has never been uncensored before, it's a hybrid Mamba model with 52B parameters. Here is the model links: Safetensors: https://hu

Been working hard for the past month to bring to the community some interesting curios, so for starters we have LongCat-Flash-Lite Uncensored Heretic with MTPs which has never before been uncensored,

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