Knowledge catalogue
arXiv:2610.14476v1 Announce Type: cross Abstract: Comparing large language models can reveal shared representational structure and systematic differences between them. However, aggregate similarity me
arXiv:2610.19696v1 Announce Type: new Abstract: Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate throu
arXiv:2610.19725v1 Announce Type: new Abstract: Time-series foundation models provide strong zero-shot forecast, but deployment for real- world applications still requires task-specific designs for mo
We now have state-of-the-art pre-trained base models in the 3T-parameter weight class, built entirely in-house at MAI. Post-training results coming soon -- stay tuned! Lots of details in our technical
arXiv:2610.14863v1 Announce Type: new Abstract: Data-driven weather forecasting models are commonly trained on ERA5, yet operational deployment must use timely initial states from physics-based numeri
arXiv:2610.20104v1 Announce Type: new Abstract: Autoregressive transformers trained on limit order book (LOB) message streams are increasingly proposed as foundation models for market microstructure.
arXiv:2610.15097v1 Announce Type: new Abstract: Diffusion language models (DLMs) offer new opportunities for controllable text generation. However, their controllability, defined as the ability to sat
arXiv:2610.15818v1 Announce Type: new Abstract: Modern cloud platforms generate high-dimensional, noisy telemetry from thousands of microservices. Unlike classical anomaly detection benchmarks, cloud
arXiv:2610.18543v1 Announce Type: new Abstract: Foundation models are increasingly used as feature extractors for downstream tasks with limited data, typically through representations obtained from th
arXiv:2610.17526v1 Announce Type: new Abstract: World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states. They have been shown to outpe
arXiv:2610.15794v1 Announce Type: new Abstract: Flow matching is a common generative recipe for robot foundation models. Vision-language-action models (VLAs) generate action chunks, while world-action
arXiv:2610.16139v1 Announce Type: new Abstract: Learned world models for autonomous driving operate in unconstrained latent spaces, yet the physical systems they represent are governed by strict non-h
arXiv:2601.22371v2 Announce Type: replace Abstract: Multi-fidelity (MF) regression often operates in regimes of extreme data imbalance, where the commonly-used Gaussian-process (GP) surrogates struggl
arXiv:2506.10946v3 Announce Type: replace Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing
arXiv:2610.17440v1 Announce Type: new Abstract: Dual-encoder vision-language models systematically fail at negation, scoring ''a cat without a dog'' nearly identically to ''a cat with a dog.'' We show
arXiv:2610.17080v1 Announce Type: new Abstract: Unified multimodal models (UMMs) provide an interface for interleaved text-image generation, where generated visual states can directly inform subsequen
arXiv:2610.18729v1 Announce Type: new Abstract: Vision-language models (VLMs) that segment from language must pass the location of the referent to a pixel decoder. The dominant interface compresses it
arXiv:2601.04824v3 Announce Type: replace Abstract: Automatic identification of events and recurrent behavior analysis are critical for video surveillance. However, most existing content-based video r
arXiv:2610.17065v1 Announce Type: new Abstract: Real-world tables are often heterogeneous, combining numerical features with free-form string columns. Table foundation models (TFMs) excel on numerical
arXiv:2610.17530v1 Announce Type: new Abstract: We propose a unified spatial-density signal to score token importance for both inference phases: bipartite merge for prefill and KV eviction for decode,
arXiv:2610.16945v1 Announce Type: new Abstract: Recent advances in multimodal foundation models, exemplified by GPT-6 Astra, raise the prospect of general-purpose embodied reasoning and planning. Usin
arXiv:2610.16641v1 Announce Type: new Abstract: Cross-task generalization remains difficult for world action models (WAMs), even when their predicted futures depict plausible manipulation. This gap ca
arXiv:2601.16333v3 Announce Type: replace Abstract: Foundation models are used for many real-world applications involving language understanding and generation from temporally-ordered multimodal event
Quick note, not my character, original came from schmede_AI on youtube. But yes my question is do any local models currently have the ability to match and generate additional images of a character fro
Look up! Mistral models are in orbit 🌍. Proud to join @orbitworksspace and @LoftOrbital's first-of-its-kind AI satellite constellation with @NVIDIAAIInfra. Just a few weeks ago, @orbitworksspace launc
arXiv:2610.13504v1 Announce Type: cross Abstract: Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after
arXiv:2610.12907v1 Announce Type: cross Abstract: Federated vision-language models (FedVLMs) represent one of the emerging frontiers of machine learning, aiming to integrate federated learning within
arXiv:2610.12789v1 Announce Type: new Abstract: Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can
arXiv:2610.12669v1 Announce Type: cross Abstract: Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. Th
arXiv:2610.12537v1 Announce Type: new Abstract: When a trader executes a large order, the relevant question is not what will the price be? but what would the price have been had I not traded? Market i
arXiv:2610.13456v1 Announce Type: new Abstract: Cyber-Physical Systems are developed through multiple model based activities, comprising several stages of development. As the development progresses th
arXiv:2610.13404v1 Announce Type: new Abstract: Linear models can predict well in complex domains even when underlying mechanisms are nonlinear. We argue that this can occur because the complexity of
arXiv:2610.10946v1 Announce Type: new Abstract: Large language models (LLMs) are entering wildfire management, where overstated evaluations can cost property and lives. How do they perform on wildfire
arXiv:2610.12386v1 Announce Type: cross Abstract: The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale.
arXiv:2610.11163v1 Announce Type: cross Abstract: Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claimant possesses a model identica
arXiv:2512.22454v2 Announce Type: replace Abstract: Electrical substations are a significant component of an electrical grid. Indeed, the assets at these substations (e.g., transformers) are vulnerabl
arXiv:2610.11113v1 Announce Type: new Abstract: Pre-trained vision-language models excel across varied perception tasks, but adapting them to novel downstream settings without sacrificing generalizati
arXiv:2610.11826v1 Announce Type: cross Abstract: Object hallucination remains a major obstacle for large vision-language models (LVLMs) to generate reliable content. An intuitive mitigation strategy
OpenAI released 719 mathematics manuscripts on October 6, 2026 that were generated by an internal frontier model (not publicly available), covering 372 topic families—including a solution to the Navie
arXiv:2610.12168v1 Announce Type: new Abstract: We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's
arXiv:2603.06578v3 Announce Type: replace Abstract: Multimodal Large Language Model (MLLM) classification performance depends critically on evaluation protocol and ground truth quality. Studies compar
arXiv:2610.11329v1 Announce Type: new Abstract: Pathology vision-language models (VLMs) have shown strong visual perception ability, but their robustness in the language domain remains poorly characte
arXiv:2610.12402v1 Announce Type: cross Abstract: Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input. Yet real-world spatial intel
arXiv:2610.11978v1 Announce Type: new Abstract: Jev is a 'System One' model that returns a choice among given options instead of generating text. We study how such a specialized decision model compare
arXiv:2604.00050v3 Announce Type: replace-cross Abstract: Federated Learning (FL) has emerged as a promising technique for training language models on distributed and private datasets of diverse tasks
arXiv:2610.12005v1 Announce Type: new Abstract: Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)? We systematically study this along three
arXiv:2610.09096v1 Announce Type: new Abstract: While established literature underscores the pivotal role of preprocessing in forecasting accuracy, this stage remains largely overlooked in current res
Opus5.5, Sol6.1, Fable, and Astra have all proven they can and the scene has exploded this past week. Part of that is from the tools and feedback loops maturing though. Are any open weight models (at
arXiv:2610.09519v1 Announce Type: new Abstract: Production machine-learning models are derived artifacts of time-bounded training snapshots: a deployed model is a materialized view over a training cut
arXiv:2610.09802v1 Announce Type: new Abstract: Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to tho
In my attempt to combat powerty; as electricity cost a ton these days and it is hot as hell, I consolidated 2 machines into one, so my 2 crappy machines now are one, and that means a bit less power an
arXiv:2610.10526v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-languag
arXiv:2610.09710v1 Announce Type: new Abstract: ANN-to-SNN conversion offers a practical route toward energy-efficient spiking Vision-Language-Action (VLA) models by bypassing the substantial cost of
arXiv:2610.09550v1 Announce Type: new Abstract: Vision-language models increasingly reason through crops, regions, and tool-produced observations. Yet an observation can influence the answer without b
arXiv:2610.10508v1 Announce Type: new Abstract: Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as
arXiv:2610.07391v1 Announce Type: cross Abstract: We present a new perspective on the problem of likelihood approximation within the framework of simulation-based inference that promotes scalable and
Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu
Both embeddings models from Perplexity.ai—referred to as *pplx‑embed‑v2*—are publicly available on Hugging Face under the “perplexity‑ai” collection. The models can be accessed via the Hugging Face pa
arXiv:2610.06881v1 Announce Type: cross Abstract: In this paper, a comparative review of different hybrid models for short-term forecasting of building thermal demand is carried out. Particularly, the
arXiv:2610.07940v1 Announce Type: cross Abstract: Looped language models apply the same stack of layers T times to each token, which deepens the model without adding parameters but multiplies its key-