Knowledge catalogue
arXiv:2608.18736v1 Announce Type: new Abstract: Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimi
arXiv:2608.17250v1 Announce Type: cross Abstract: This paper develops an adaptive surrogate modeling method for problems with very high-dimensional spatio-temporal outputs. The analysis of spatio-temp
Regarding Sentence Transformers v6.0 update: A dense model compresses a whole text into one vector, then compares two vectors. A multi-vector model keeps one vector per token, scores every query token
arXiv:2608.16885v1 Announce Type: new Abstract: Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hiera
arXiv:2608.16834v1 Announce Type: cross Abstract: We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues
arXiv:2608.12398v1 Announce Type: cross Abstract: We propose IM-LEPP (Integrated Multimodal Latent Energy-based Predictive Processing), a hierarchical, energy-based model of multimodal cognition that
arXiv:2608.11495v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS). Still, their black-box deploym
arXiv:2608.11444v1 Announce Type: cross Abstract: Drug response prediction (DRP) models are an active area of research in pharmacogenomics, with growing potential to accelerate the identification of e
SpaceXAI today released Grok 4.6, a large language model that it says can outperform Anthropic PBC’s Claude Fable 5 in some areas. SpaceXAI was known as xAI until last month. The Elon Musk-founded art
arXiv:2608.10860v1 Announce Type: cross Abstract: World-action models (WAMs) predict the future to act better, but nearly all of them predict only RGB latents, trained purely for pixel reconstruction,
Not even sure if I'm allowed to post this, what with the 'completely/primarily LLM generated copy' rule (the post itself is fine, but the repo/model I'm sharing definitely is, whoops) and the whole li
arXiv:2608.07157v1 Announce Type: new Abstract: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by
arXiv:2608.06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution is inherently iterative: each action reshapes
The successor to Llama is here, and Meta is revitalizing focus on open weights with their new Muse Glimmer - a leading 30B param model designed for always-on local agent use, small enough to run on a
arXiv:2608.05104v1 Announce Type: new Abstract: Deep neural networks have shown impressive success in NLP tasks owing to their complex structure and huge number of edges. Achieving state-of-the-art pe
Taalas buried the lede for the amazing demo of their first tape out. 15k tokens per second with a llama 8b model, ability to scale that up etched onto silicon As models satisfice etching makes sense,
Hey everyone! I just released a sub-6B sparse activation AI model which was built with a brand new architecture : fusion. I fused weights from @liquidai's LFM2.5-2.6B & @Alibaba_Qwen's Qwen3.6-35B-A3B
tests: add model resolution test on synthetic repo listings (#26172) tests: add model resolution test on synthetic repo listings Include download.cpp and arg.cpp inside a namespace with hf_cache monke
arXiv:2608.02050v1 Announce Type: new Abstract: Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the
arXiv:2608.00105v1 Announce Type: new Abstract: Pathology foundation models are reported to encode molecular programmes in tissue morphology, but the evidence is usually a cohort-wide ranked gene list
arXiv:2607.28982v1 Announce Type: cross Abstract: Recent language models achieve strong performance across a variety of tasks, but conventional adaptation applies updates uniformly across training sam
Has anyone figured out how to enable speculative decoding with deepseek v4 flash 0731 on llamacpp? I’m on the right release for llamacpp (b10228 or earlier) and running am17an’s draft model with unslo
arXiv:2607.27433v1 Announce Type: cross Abstract: We develop two parametric data-driven reduced models: a physics-informed neural network (PINN) and a non-intrusive tensorial reduced-order model (TROM
arXiv:2607.28624v1 Announce Type: new Abstract: We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing phys
arXiv:2607.27023v1 Announce Type: new Abstract: Evaluating large generative models across benchmarks is time-consuming and computationally expensive. This drives the need for methods that can estimate
Google DeepMind says the latest version of its Gemini Robotics AI model can 'control entire humanoid robots.' While the previous model focused on controlling a humanoid robot's upper body, Gemini Robo
Model + harness. We have barely begun to understand the best ways to do harness engineering. A huge amount of untapped potential even without models getting better (but models are getting better) Turn
arXiv:2607.23183v1 Announce Type: cross Abstract: Neurological disorders are a leading cause of global disability and are increasingly linked to environmental chemical exposures. Yet neurotoxicity ass
Mage-VL is a codec-native, proactive-streaming multimodal foundation model for image and video understanding, whose visual encoder is trained entirely from scratch at a compact 4B scale. It targets a
arXiv:2607.22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities. However, deploying the
arXiv:2607.22708v1 Announce Type: new Abstract: Deploying a vision-language model with full UI understanding on end devices has long been trapped between accuracy and efficiency: on one side is the ac
arXiv:2607.24032v1 Announce Type: new Abstract: Generative-AI evaluations can become historical before publication, yet calendar age does not affect every conclusion equally. This paper has two linked
Learning causality from internet videos in latent space first, and then using RL to teach the foundation model how to act. This approach is 30× cheaper than Gemini 3.1 Flash on pretraining and achieve
arXiv:2607.06216v1 Announce Type: new Abstract: The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate infe
arXiv:2607.04755v1 Announce Type: new Abstract: Model merging offers a practical alternative to conventional continual learning by integrating independently fine-tuned models without retaining previou
Sakana AI (@SakanaAILabs) is now a model vendor on Merge Gateway, and Fugu Ultra is live through them. It's a multi-agent orchestration model that routes across frontier models behind one API. You get
arXiv:2607.01986v1 Announce Type: new Abstract: Multivariate time-series models for prognostics are often evaluated by point prediction accuracy, yet their internal states rarely expose a coherent deg
arXiv:2607.00083v1 Announce Type: cross Abstract: Language models have changed from unreliable text generators to highly-capable large models with trillions of parameters. Capability increases come ha
arXiv:2606.29059v1 Announce Type: cross Abstract: World modeling requires forecasting uncertain futures while preserving information useful for downstream perception. Existing visual world models ofte
arXiv:2606.26578v1 Announce Type: new Abstract: Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structur
arXiv:2606.27325v1 Announce Type: new Abstract: Recent advances in action-conditioned world models show promising progress in modeling complex interactions and forecasting future states under diverse
arXiv:2606.24256v1 Announce Type: new Abstract: Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a br
arXiv:2606.22317v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward continuously improving large language models. Recent w
arXiv:2509.21489v3 Announce Type: replace Abstract: Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into que
arXiv:2606.20726v1 Announce Type: new Abstract: We introduce a compact empirical model that quantifies how answer accuracy degrades as a function of frame budget B and temporal distance D in long vide
arXiv:2606.18627v2 Announce Type: replace Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a s
arXiv:2511.22699v4 Announce Type: replace Abstract: The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. L
arXiv:2606.11270v1 Announce Type: cross Abstract: Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are pr
arXiv:2606.09936v1 Announce Type: cross Abstract: World models are now built on substantially different computational substrates. Latent recurrent state-space models such as PlaNet and the Dreamer fam
arXiv:2606.09932v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT
arXiv:2606.08525v1 Announce Type: new Abstract: Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such re
arXiv:2603.24963v3 Announce Type: replace Abstract: Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversi
arXiv:2511.04567v2 Announce Type: replace-cross Abstract: Constructing reduced models for turbulent transport is essential for accelerating profile predictions and enabling many-query tasks such as pa
arXiv:2509.25522v3 Announce Type: replace Abstract: Recent advancements in generative models have allowed the emergence of a promising paradigm for recommender systems (RS), known as Generative Recomm
VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relev
arXiv:2512.21917v3 Announce Type: replace-cross Abstract: Policy alignment to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., Bradley-Ter
arXiv:2606.04459v1 Announce Type: cross Abstract: Language model parameters are known to impose unique (to each model) geometric constraints on their logit outputs, which serves as a signature that id
arXiv:2606.04264v1 Announce Type: new Abstract: Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single archi
arXiv:2606.02969v1 Announce Type: new Abstract: This paper examines three approaches for modeling the dynamics of a flexible-link 2-DoF robotic arm to address unmodeled dynamics not captured by rigid-
arXiv:2606.01057v1 Announce Type: cross Abstract: Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neur