Search: “models”

arXiv:2607.23507v1 Announce Type: cross Abstract: Choosing the right text embedding model is one of the most consequential -- and most frequently under-examined -- decisions in building a retrieval or

arXiv:2607.24585v1 Announce Type: new Abstract: We present ELMOD - Efficient Language Model for On-Device Deployment - a compact (2.7B) German language model designed for efficient inference on resour

Qwen3.6-27b is fantastic! It makes me wonder if there's a hard ceiling to smaller sized models. Do you guys think the ceiling of intelligence for smaller models will be constrained by factors like par

mii-llm, an open source AI lab, released Zagreus-0.4B-por, a compact bilingual Portuguese–English language model pretrained entirely from scratch. The model has approximately 400 million parameters an

The news about Anthropic settling a class action lawsuit for 1.5B over training data isn't just a legal headache for them, it's a massive warning sign for engineering teams relying entirely on closed

Hugging Face says it resorted to a Chinese AI model to battle a fully autonomous cyberattack because U.S. model guardrails stymied its defense https://fortune.com/2026/07/20/hugging-face-turns-to-chin

arXiv:2603.08862v2 Announce Type: replace-cross Abstract: Autonomous navigation in highly constrained environments remains challenging for mobile robots. Classical navigation approaches offer safety a

The best base model for training isn't about someone else's benchmarks. Excited to offer @thinkymachines' first open-weights model: Inkling. 975B MoE, multimodal, with Apache 2.0. A great foundation f

arXiv:2607.08170v1 Announce Type: new Abstract: Zero-shot model size interpolation aims to create new models of intermediate target sizes by combining existing models without additional training. Rece

You can no longer just drop in the smartest model into a harness and expect it to behave similarly to any other model of similar ability levels. This is starting to look a lot more like hiring for a r

arXiv:2607.07690v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reasoning models, yet it grades only the final answer. On hard

We're releasing a research preview of a new orchestrator model in Perplexity Computer. The model is an adapted version of GLM 5.2, post-trained for the Computer harness. It delivers near-frontier perf

arXiv:2512.08029v3 Announce Type: replace-cross Abstract: Clinical decision-making in oncology requires predicting dynamic disease evolution, a task current static AI predictors cannot perform. While

With full autonomy and maximized ride-hailing, Cybercab is projected to nearly halve emissions per mile compared to Model 3 + Model Y Also, a personal car sits parked ~95% of the time. Cybercab keeps

If you want frontier-level coding and agent performance but you don't want to pay closed-model prices, GLM 5.2 is the open model you've probably been hearing about. Here's why you should run it on Fir

LeWorld model becomes ADAPTIVE and meets MODEL-PREDICTIVE CONTROL AdaJEPA by Yann LeCun and colleagues performs actions, then checks the predicted latent state versus the observed and adapts at TEST T

The Sensorimotor World Model (https://arxiv.org/abs/2606.20104): a deep dive into the role of inverse dynamics modeling as an anti-collapse regularization for JEPAs. IDM is weaker than SIGReg as it do

arXiv:2603.22050v2 Announce Type: replace-cross Abstract: Supervised machine learning describes the practice of fitting a parameterized model to labeled input-output data. Supervised machine learning

Kog open-sourced on @huggingface the 2B model that they used to show a model running at 3,000+ tokens per second. Very cool work! https://huggingface.co/blog/kogai/kog-laneformer-2b-the-latency-first-

Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API. Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability w

arXiv:2606.11210v1 Announce Type: cross Abstract: Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly

🚨 Fable 5 is something to pay attention to. This is another 'I had early access to the new Mythos-class Anthropic model and I want to tell you what I thought of it' post. I know, I know, it's annoying

arXiv:2606.08945v1 Announce Type: new Abstract: We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large lan

A researcher distilled their flow matching model into a rectified flow model, enabling high-quality generation in few steps without requiring classifier-free guidance (CFG). Rectified flow straightens

arXiv:2602.18008v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise in constructing mechanistic models from data. However, existing evaluations largely focus on s

arXiv:2606.01189v1 Announce Type: new Abstract: We argue that the AI community is now ready to move beyond benchmarking and consolidate scattered efforts in model analysis into a systematic discipline

arXiv:2605.28418v1 Announce Type: new Abstract: With the rise of tabular foundation models alongside traditional models still performing well on many tasks, choosing the right model for a tabular data

arXiv:2605.25254v1 Announce Type: cross Abstract: With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into

arXiv:2602.13249v2 Announce Type: replace-cross Abstract: Small-molecule foundation models are typically pretrained on standalone molecular data, unlike vision and language models that often benefit f

The Top AI Papers of the Week (May 18 - 24): - AIRA - MetaCogAgent - Memory as a Model - Code as Agent Harness - Weak-Model Critic-Comparator - OpenAI Disproves the Unit Distance Conjecture - Producti

arXiv:2605.20803v1 Announce Type: new Abstract: Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Re

Introducing Starchild-1 from @odysseyml, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear.

arXiv:2605.11367v1 Announce Type: new Abstract: Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame wo

The UK AISI found Mythos Preview is the first model to solve both their cyber ranges end-to-end. No model had ever solved the AISI’s “Cooling Tower” cyber range before. We're getting it to defenders a

arXiv:2605.09131v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has unified the interface between Large Language Models (LLMs) and external tools, yet a fundamental gap remains in how

Jensen Huang describes his early collaboration with Elon Musk, noting that he provided computational support for Tesla's Model S and Model 3 vehicles through NVIDIA technology. Huang credits this prof

arXiv:2605.02087v1 Announce Type: new Abstract: Some frontier AI developers aim to align language models to a Model Spec or Constitution that describes the intended model behavior. However, standard a

switching model providers is easy switching harnesses is less so model providers want to lock you in via harness we need open harnesses! TBH I don't agree with your take. I don't think Athropic's desi

arXiv:2604.25119v1 Announce Type: new Abstract: Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. T

arXiv:2604.24302v1 Announce Type: new Abstract: Mechanistic interpretability has made it possible to localize circuits underlying specific behaviors in language models, but existing methods are expens

arXiv:2509.04802v3 Announce Type: replace Abstract: As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating dep

This is an incredibly cool experiment It is also fascinating that the model knows information up to 1931, but, at least in some science topics, seems very stuck in the early 1900s. For example, it def

arXiv:2604.22700v1 Announce Type: new Abstract: Understanding and predicting the progression of neurodegenerative diseases remains a major challenge in medical AI, with significant implications for ea

On Friday, Chinese AI firm DeepSeek released a preview of V4, its long-awaited new flagship model. Notably, the model can process much longer prompts than its last generation, thanks to a new design t

arXiv:2503.03480v4 Announce Type: replace Abstract: Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-w

⚡ Meet Qwen3.6-35B-A3B：Now Open-Source！🚀🚀 A sparse MoE model, 35B total params, 3B active. Apache 2.0 license. 🔥 Agentic coding on par with models 10x its active size 📷 Strong multimodal perception an