Knowledge catalogue
Open models are for everyone and how AI reaches everyone. 18M developers. 3M models. 200K companies building on @huggingface. @Dell has been partnered with Hugging Face for years. Now with @nvidia's b
arXiv:2609.00838v1 Announce Type: cross Abstract: Test-set accuracy is silent on two issues that matter when deploying autoregressive neural sequence models: how much probability mass the system under
arXiv:2608.30893v1 Announce Type: new Abstract: Electrocardiogram (ECG) interpretation requires knowledge of cardiology, electrophysiology, clinical diagnosis, ECG waveforms, signal acquisition, and i
arXiv:2608.28980v1 Announce Type: cross Abstract: Can the specialized architectures that machine learning has traditionally built for structured data be replaced by language-based models? This questio
arXiv:2608.26327v1 Announce Type: cross Abstract: Large language models increasingly produce and interpret verbal probability expressions, yet whether these expressions carry consistent meaning across
I built a benchmark called EchoNet. An agent gets a factual question, then searches a syntheic web I made before answering. Some of that web is seeded with misinformation: one fake page, a fake page r
arXiv:2608.22068v1 Announce Type: new Abstract: Geothermal well arrays, which organize multiple geothermal wells into carefully planned geometric configurations, provide opportunities to enhance energ
arXiv:2607.14975v2 Announce Type: replace Abstract: Channel foundation models (CFMs) are commonly evaluated in model-specific pipelines that differ in data, radio configurations, partitions, adaptatio
Thomas Claburn / The Register: Anthropic says new Claude models in the EU will add watermarks to text and C2PA metadata to files, to comply with the EU AI Act, and it will update older models — EU rul
arXiv:2608.04183v1 Announce Type: new Abstract: When a language model follows an in-context conditional rule such as 'if P(x) then A else B,' does it assemble a runtime circuit with one module that te
arXiv:2607.29389v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated a strong ability to generate syntactically correct code from natural-language specifications. In this stu
'Anthropic’s AI Claude escaped testing environment and hacked organizations' 'Company says it discovered unauthorized access during ‘proactive review’ after rival OpenAI revealed rogue agent… its AI C
arXiv:2607.23439v1 Announce Type: cross Abstract: Graphical models are ubiquitous in social and empirical science as they are intuitive and easy to use. These models belong to the broader class of Mar
arXiv:2607.21998v1 Announce Type: new Abstract: This paper introduces a new benchmark test, Medical-Checklist, for assessing medical multimodal models. The recent advancements in multimodal models hav
The GPT-5.x Pro series has remained the best models for hard technical problems since they launched. There is some parallel model magic going on that is not well-explained. Anthropic has never had an
arXiv:2607.14088v1 Announce Type: new Abstract: Video generative models commonly rely on latent spaces learned by 3D Variational Autoencoders (3D-VAEs). However, conventional 3D-VAEs are mainly optimi
Chinese models are now 41% of Hugging Face downloads. They passed the US. Clem Delangue @ClemDelangue, CEO of the main open model platform, cites Hugging Face's own Spring 2026 report: Chinese open we
Kurt Wagner / Bloomberg: Meta launches a Meta Model API, which Mark Zuckerberg says will have “aggressive and attractive” pricing at ~25% of the cost of OpenAI's and Anthropic's models — In a crowded
Nice stats on usage of open models across OpenCode. GLM-5.2 is still underrated, but one of the models that has really surprised me on agentic tasks is deepseek-v4-flash. Extremely cheap and effective
super interesting - and a reminder that language models model language and not ideas per se. also a stark example of how easily LLMs can (as a consequence) be influenced by propaganda. Asking ChatGPT
arXiv:2607.03198v1 Announce Type: new Abstract: World models -- compressed latent representations of an environment that support action-conditioned prediction and planning -- are typically presented a
arXiv:2607.02501v1 Announce Type: new Abstract: Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model
arXiv:2607.01774v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches,
Rampart, our PII removal model, has cracked the first screen of the top trending models across any category on Huggingface, on the same tier as GLM 5.2 / Deepseek! If building systems at fast pace at
The strongest models are gated and access is granted only to a select few. Hermes Agent now exposes MoA presets as virtual models, giving you capabilities beyond the publicly available frontier: 8% hi
Bring open models to where you're already working. FireConnect brings Fireworks' top models directly into Claude Code, Pi, OpenCode, and Codex. Watch our Head of AI Education @Prof_oz show you how: Ho
Introducing Claude code for 3D modeling You can now create a production-level 3D models from any agent you are using. Ready to plug into your own apps or games Made possible by @trysuzanne and @monid_
We’ve worked hard to make it secure at every level. 1/ At the model training stage, 2/ the classifiers on top of our models and things like auto mode, 3/ we protect what Claude has access to (websites
arXiv:2606.09749v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these
Kif Leswing / CNBC: Google and Nvidia are helping Apple with Apple Foundation Model Cloud Pro, which Apple says is comparable to Gemini frontier models and runs on Nvidia GPUs — - Apple showed off Sir
Interesting that the GPT-5 Pro series models have consistently been the best models for single-shot attempts at the hardest problems since last summer. There has been no real competition in all that t
arXiv:2605.21751v1 Announce Type: new Abstract: Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coeffi
arXiv:2505.17352v2 Announce Type: replace Abstract: Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignmen
Deepseek V4 Flash is one of the best 'worker' models out there IMHO so this is very cool! Yet ANOTHER free model available through the Nous Portal 😍😍😍 Can't believe people are still playing with toy l
arXiv:2605.12466v1 Announce Type: cross Abstract: Looped Transformers offer a promising alternative to purely feed-forward computation by iteratively refining latent representations, improving languag
gpt-realtime-2 is a great voice model (with a typically bad OpenAI name). Voice models are natively processing speech, not transcribing it, so the intelligence of the model matters. The old voice mode
AI Gateway lets you route to any model. On May 13 in SF, we're hosting a builder night powered by those models. Pick one, build, demo. Audience votes on best build. With @AnthropicAI, @MiniMax_AI, & @
arXiv:2605.01194v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities and generalization in embodied manipulation. However, their decision-makin
arXiv:2605.02038v1 Announce Type: new Abstract: Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-w
Some awesome open models trending on HF right now, including models from @deepseek_ai, @Xiaomi, @OpenAI, @MistralAI, and @aipoolside. And of course Nemotron 3 Nano Omni from @NVIDIAAI So great to see!
arXiv:2604.27124v1 Announce Type: new Abstract: Training stable biological foundation models requires rethinking attention mechanisms: we find that using sigmoid attention as a drop in replacement for
APEX-Agents now has a @huggingface leaderboard for open-source models. APEX-Agents is our frontier benchmark for whether models can do the real work of consultants, lawyers, and bankers. https://huggi
Both are great models and neither wins everywhere. I use both Opus and 5.5 depending on the task. LangSmith Fleet lets you choose the model for each agent, so you can match it to the work https://www.
arXiv:2604.24583v1 Announce Type: new Abstract: Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-languag
🚀Meet Carnice-V2-27b🚀 → Carnice is a 27 billion parameter model capable of beating models 10x the size in Hermes-agent, fully open-source and built on top of Qwen3.6-27B →Build to fit on Consumer GPU
GPT-5.5 is likely the best model in the world. But open models like Kimi and Minimax get almost identical coding benchmark scores at 10-25x lower cost. I broke down the benchmarks and pricing. Here's
arXiv:2604.19139v1 Announce Type: cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitu
arXiv:2604.16382v1 Announce Type: new Abstract: Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-conte
We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via @FireworksAI_HQ fast inference APIs. Kimi K2.6 has impressive a
arXiv:2506.13763v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable success in generative modeling. Despite more stable training, the loss of diffusion models is not in
Qwen: Alibaba unveils Qwen3.6-35B-A3B, an open-weight MoE model with 35B total and 3B active parameters, saying it rivals larger dense models in agentic coding tasks — · 4355 words · QwenTeam丨Translat
Sub-32B open weights models now offer GPT-5 level intelligence with Qwen3.5 27B (Reasoning) matching GPT-5 (medium) at 42 and Gemma 4 31B (Reasoning) matching GPT-5 (low) at 39 on the Artificial Analy
arXiv:2601.07220v3 Announce Type: replace Abstract: Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This sur
Relying on model providers' stateful APIs or harnesses creates lock-in: switching models means losing your agent's memory -- a cost that only grows as agents get better at learning a big part of agent
arXiv:2604.07430v1 Announce Type: new Abstract: We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Visi
arXiv:2604.06217v1 Announce Type: cross Abstract: The foundation model era -- roughly 2020 to 2025 -- is over. The forces that defined it have inverted. Open source models have reached frontier perfor
arXiv:2503.06717v3 Announce Type: replace Abstract: Interactive segmentation uses real-time user inputs, such as mouse clicks, to iteratively refine model predictions. Although not originally designed
We’re partnering with @MiniMax_AI across product and models to make their upcoming releases the best for Hermes Agent users. MiniMax models are already some of the most-used in Hermes Agent. If you ha
arXiv:2603.15046v2 Announce Type: replace Abstract: In this study, we address the problem of language-guided robotic manipulation, where a robot is required to manipulate a wide range of objects based
arXiv:2610.11069v1 Announce Type: new Abstract: Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their readiness rest largely on benchm