Knowledge catalogue
arXiv:2610.06992v1 Announce Type: new Abstract: Improved traffic forecasts do not necessarily yield better signal-control decisions. We investigate this gap through a layered diagnostic study using 29
arXiv:2610.07009v1 Announce Type: cross Abstract: Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four publ
arXiv:2610.07115v1 Announce Type: cross Abstract: The order in which candidate responses are presented can change an LLM judge's verdict. Detecting such a position flip ordinarily requires judging eac
@WSJ @nvidia @M12vc @SamsungNext @robotventures @usv @ycombinator @MenloVentures Join us at NousCon to celebrate and perhaps catch some sneak peeks https://x.com/NousResearch/status/210504377770675421
Row-Bot 5.0 with qwen3.8:27b in Ollama, on my own GPU. No API keys, no cloud. Gave it a year of bills, a tenancy agreement, an insurance policy and a rent increase letter (all made up). It spotted a l
arXiv:2610.06019v1 Announce Type: new Abstract: With massively parallel simulation, on-policy Reinforcement Learning methods such as PPO have become standard in many domains. However, learning from sc
arXiv:2610.06643v1 Announce Type: cross Abstract: Robot learning in simulation depends on the objects the simulator offers. Many tasks need objects with separate parts, joints that allow the required
arXiv:2610.05600v1 Announce Type: new Abstract: High-dimensional bioinformatics data, characterized by a large number of features relative to the number of samples, pose major challenges such as the `
We released Aplomb 1 today, a 5.3B decision model with open weights. It reads up to 1M tokens of text, JSON, images, video and audio in a single request, and on our API it makes a decision on a 1M-tok
The secondary button gets its own look back and the chat add button its own light surface. Pressable elements get a pointer cursor again, the font rendering smooths on the app shell, the root layout r
arXiv:2610.04851v1 Announce Type: new Abstract: Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a froz
arXiv:2610.03945v1 Announce Type: new Abstract: A constrained optimization problem may involve a parameter in its objective and active constraints, yet the final decision may remain insensitive to sma
arXiv:2610.05418v1 Announce Type: cross Abstract: Most vision-language-action (VLA) models rely on current observations and lose task-relevant evidence once it leaves view, limiting performance on lon
arXiv:2610.06105v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but generating and evaluating long rollouts incurs su
arXiv:2610.05993v1 Announce Type: new Abstract: Composed image retrieval (CIR) aims to retrieve a desired target image from a query consisting of a reference image and a modification text. This task e
Grok 4.7 is excellent at dealing with large code repositories Grok 4.7 takes the TOP 3 spots on VulcanBench Frontier v4, outperforming Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol and other leading f
arXiv:2610.05922v1 Announce Type: cross Abstract: Evaluating the causal effect of new features is a central goal for online platforms. While recent literature addresses limited testing traffic via cen
arXiv:2610.06306v1 Announce Type: new Abstract: General purpose language models are increasingly able to control robotic hardware. Understanding the capabilities and safety of these models when embodi
arXiv:2610.05775v1 Announce Type: new Abstract: A video assistant must speak when its instruction warrants a response and stay silent otherwise. We introduce a benchmark that evaluates this decision f
Introducing Mistral Large 4: Le chonk Mistral are back in the game. Today they're releasing a preview of Mistral Large 4, a 1 trillion parameter, 49 billion active parameter model trained on their own
arXiv:2610.05428v1 Announce Type: cross Abstract: We study learning in continuous games when players receive only pairwise preference feedback, revealing which of two actions is preferred but neither
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I
I’ve been building this for a long fucking time, and tonight I finally released Memoria 1.0.0. I built it because I actually wanted to use it. I wanted a real memory layer for local LLM applications t
arXiv:2610.03830v1 Announce Type: new Abstract: In partially observable Markov decision processes, the optimal policy generally depends on the history of observations and past actions. Asymmetric acto
Carl Franzen / VentureBeat: Mistral launches a preview of Mistral Large 4, or Le Chonk, a 1T model it claims tops any open model developed in the US or Europe; weights are due October 27 — Mistral is
Mistral Blog: Mistral says it trained ML4 “from scratch” using 3,800 Nvidia Grace Blackwell GPUs in its data centers in Europe and much of its training data was multilingual — Le Chonk — Today, we're
arXiv:2610.06210v1 Announce Type: new Abstract: Autoregressive generation is natural for language, where predicted tokens can be directly reused as the next prediction state, but trajectory forecastin
arXiv:2503.09950v2 Announce Type: replace Abstract: In this paper, we address the problem of human trajectory forecasting, which aims to predict the inherently multi-modal future movements of humans b
arXiv:2610.06378v1 Announce Type: new Abstract: The rapid evolution of video generation has narrowed the perceptual gap between authentic and synthetic videos, making generalizable AI-generated video
OpenAI: OpenAI releases a range of new mathematical results produced by an internal model, with details like estimations of compute spent in terms of ChatGPT Pro usage — We're releasing a broad range
arXiv:2610.05070v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiab
With llama.cpp using a customized SYCL backend on Intel B70 (32GB), overclocking my DDR5 memory gave modest gains for MoE models which do not fit in VRAM. Both PP and TG increased after overclocking D
arXiv:2610.06825v1 Announce Type: cross Abstract: Scientific figures often encode quantitative results that are not readily available in machine-readable form, making accurate plot digitization import
arXiv:2610.05151v1 Announce Type: new Abstract: Visuomotor policies can execute familiar tasks yet lack the corrective behavior needed after their own mistakes. We present a framework for recursive se
arXiv:2610.06148v1 Announce Type: cross Abstract: Power Delivery Networks (PDNs) are critical components of modern VLSI chips, providing stable voltage levels while satisfying electromigration (EM) an
Hey everyone! I am trying to go really deep into Machine Learning and Artificial Intelligence. Not just learning how to use the latest models and frameworks, but understanding how we reached here from
arXiv:2610.06691v1 Announce Type: cross Abstract: Embedding enhancement improves speaker verification under acoustic mismatch without modifying a frozen backbone. Recent work has established a practic
arXiv:2610.06021v1 Announce Type: new Abstract: Image editing should change only the attributes specified by an instruction while preserving everything else, yet current methods often make unintended
arXiv:2610.06658v1 Announce Type: new Abstract: In daily life, each person exhibits unique speaking habits, leading to subtle yet consistent lip-shape variations even when pronouncing the same word. A
That one took some groundwork. Trained and served on our own compute, and RL shows no sign of saturation Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the
Today, we are launching a preview of our new model, Mistral Large 4 (ML4), aka le Chonk 🐈. ML4 is a 1T-parameter model with 49B active parameters, trained natively with multimodal capabilities. It is
arXiv:2610.05684v1 Announce Type: cross Abstract: Modern deep generative models are primarily studied for their ability to generate realistic samples, yet the generative dynamics they learn can also s
arXiv:2610.06400v1 Announce Type: new Abstract: Swarm robotics presents a robust and cost-effective paradigm for advanced automation in complex, dynamic environments, such as those encountered in sear
We’re so back. Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on
arXiv:2610.05577v1 Announce Type: new Abstract: A linear probe can show that a label is recoverable from a model's hidden states, but not whether that goes beyond what the input already reveals, or wh
arXiv:2610.03563v1 Announce Type: new Abstract: Sampling-based model predictive control (MPC) is a powerful approach to trajectory optimization, but its performance depends on an informative cost func
arXiv:2610.03395v1 Announce Type: new Abstract: Long-horizon tasks with sparse rewards pose an exploration bottleneck for goal-conditioned reinforcement learning: a policy started from the initial sta
arXiv:2506.05766v2 Announce Type: replace Abstract: Retrieval augmented generation (RAG) has shown great power in improving Large Language Models (LLMs). However, most existing RAG-based LLMs are dedi
arXiv:2610.02750v1 Announce Type: new Abstract: We address the Person Goal Navigation (PersonNav) problem, enabling robots to search for people under realistic constraints on information accessibility
Disclosure: I made this. Sharing it here because it is fully local and small, and I want feedback from people who run models on their own machines. What it is: a 395M decision model (ModernBERT-large
arXiv:2610.02762v1 Announce Type: new Abstract: Dynamic LLM routers promise to cut inference costs by sending each query to the cheapest model that can answer it correctly. We analyze six commercial r
arXiv:2610.02432v1 Announce Type: cross Abstract: Large language models (LLMs) in production systems face prompt injections, trojans (backdoors), and manipulation of automatic quality metrics. This th
arXiv:2610.03273v1 Announce Type: new Abstract: Reinforcement learning (RL) for learning path recommendation (LPR) faces two coupled obstacles. First, the policy must commit to a sequence of L concept
arXiv:2610.03675v1 Announce Type: cross Abstract: LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as
arXiv:2603.29112v2 Announce Type: replace Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in rec
After some recommendations for hardware (I'm starting from nothing), in the region of £6-7k. I will be mainly looking to use it for coding and have found Deepseek V4.1 Flash or Qwen3.8 27b good and so
arXiv:2610.03136v1 Announce Type: new Abstract: Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It has been shown that forcing a mode
arXiv:2610.02781v1 Announce Type: cross Abstract: Many useful language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learning (RL) addresses this issue by s
So PewDiePie decides to fine-tune a local AI model called Ajax on his own computer. Pretty normal stuff for local model fans. To make his dataset, he uses OpenAI's API. OpenAI catches him using their
Vanity Fair: Q&A with Sam Altman on his kids, his rivalries, pronatalism, “prepping” for the apocalypse, new products, the IPO delay, Luca Guadagnino's Artificial, and more — In an exclusive video int