Knowledge catalogue
arXiv:2605.20337v1 Announce Type: new Abstract: How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into hi
arXiv:2605.19726v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) enable globally coherent, bidirectional, and controllable text generation, offering advantages over traditional autoreg
We ran 720 browser agent tasks with @nottecore across frontier models. One baseline model produced malformed outputs in ~1 out of every 5 calls, leading to retries inside multi-step workflows. Across
arXiv:2604.01674v2 Announce Type: replace Abstract: Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inferen
arXiv:2602.01970v2 Announce Type: replace Abstract: Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-inten
arXiv:2605.13030v1 Announce Type: cross Abstract: Model merging combines task experts into one model and avoids joint training, retraining, or deploying many expert models, but the merged model often
arXiv:2605.13587v1 Announce Type: cross Abstract: Near-infrared spectroscopy (NIRS) is rapid and non-destructive, but reliable calibration still depends heavily on spectral preprocessing. In routine p
Yann LeCun says you cannot build a reliable agentic system without a world model LLMs don't have world models. They can't predict the consequences of their actions before taking them 'they just act, a
arXiv:2605.10419v1 Announce Type: cross Abstract: This paper investigates the effectiveness of large language models (LLMs) in answering questions over datasets. We examine their performance in two sc
arXiv:2602.04093v2 Announce Type: replace Abstract: Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept ann
Introducing Flux Matching, a generative modeling paradigm that generalizes diffusion models to vector fields that need not be the score function. Enables structural priors in the dynamics, faster samp
arXiv:2605.07288v1 Announce Type: cross Abstract: The integration of Vision-Language-Action (VLA) models with World Models has gained increasing attention. One representative approach treats learned W
To train better open models, we need predictable scaling. Delphi is Marin’s first step: we pretrained many small models with one recipe, then extrapolated 300× to predict a 25B-param / 600B-token run
Today we're sharing our work on interaction models. A new class of model trained from scratch to handle real-time interaction natively, instead of gluing it onto a turn-based one. https://youtu.be/A12
.@BraceSproul changed our org's internal model in Fleet from Sonnet 4.6 to Kimi K2.6 and I didn't even notice. Open models are already good enough for most tasks, though not the hardest coding work ye
arXiv:2605.02202v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as their
arXiv:2605.02348v1 Announce Type: new Abstract: Large language models pick up social biases from the data they are trained on and carry those biases into downstream applications, often reinforcing ste
arXiv:2605.00334v1 Announce Type: cross Abstract: Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical
arXiv:2604.27911v1 Announce Type: new Abstract: Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks --
big theme of 2026 - cost of closed models is too high! really excited to make deepagents work exceptionally well with OSS models Switched out Sonnet 4.6 for GLM 5.1 through @FireworksAI_HQ while doing
Chris Welch / Bloomberg: Motorola unveils its 2026 foldables lineup, including its first book-style model, which costs 1,900; prices for clamshell models have gone up by up to 200 — The company's clam
arXiv:2604.24082v1 Announce Type: cross Abstract: Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to
@jon_barron 'World models' has a technical meaning - the transition model/dynamics model from Bellman/Kalman in the context of MDPs/ state space approach to control theory ~ 1960. I gave a talk on thi
arXiv:2603.29928v2 Announce Type: replace Abstract: Tabular foundation models such as TabPFN and TabICL already produce full predictive distributions, yet prevailing regression benchmarks evaluate the
arXiv:2604.19809v1 Announce Type: new Abstract: We introduce MIRROR, a benchmark comprising eight experiments across four metacognitive levels that evaluates whether large language models can use self
arXiv:2604.20551v1 Announce Type: cross Abstract: Mixture-of-experts models provide a flexible framework for learning complex probabilistic input-output relationships by combining multiple expert mode
arXiv:2604.18957v1 Announce Type: new Abstract: Extracting standardized metallurgical metrics from microscopy images remains challenging due to complex grain morphology and the data demands of supervi
Here's how anyone can find models that work for your hardware easily. 1. Go to http://huggingface.co and make an account 2. Models tab to find weights and all compressions 3. Click on your profile on
arXiv:2604.17282v1 Announce Type: new Abstract: Process-Level Reward Models (PRMs) are essential for guiding complex reasoning in large language models, yet existing PRM benchmarks cover only general
arXiv:2604.16443v1 Announce Type: cross Abstract: Data-driven models for building thermal dynamics are a scalable approach for enabling energy-efficient operation through fault detection & diagnosis o
arXiv:2604.18463v1 Announce Type: cross Abstract: Large language models are increasingly used as planners for robotic systems, yet how safely they plan remains an open question. To evaluate safe plann
arXiv:2604.15490v1 Announce Type: new Abstract: Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical tasks
> grok4.20-beta1 is a much smaller model than opus but is #1 ranked in medicine and healthcare > 4.3 and 4.4 will be much larger models, and likely will have a significant boost in performance on comp
arXiv:2505.02979v3 Announce Type: replace-cross Abstract: We propose a novel inverse-modelling approach which estimates the parameters of a simple land-surface model (LSM) by assimilating data into a
arXiv:2511.17792v2 Announce Type: replace Abstract: While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and u
arXiv:2604.12033v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook c
arXiv:2604.09866v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have shown the promise to significantly accelerate the workflow by automating structural modeling and
arXiv:2604.10701v1 Announce Type: cross Abstract: Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained ad
arXiv:2604.10556v1 Announce Type: new Abstract: While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their fa
arXiv:2604.11061v1 Announce Type: cross Abstract: Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading.
arXiv:2604.08685v1 Announce Type: new Abstract: Automated planning algorithms require an action model specifying the preconditions and effects of each action, but obtaining such a model is often hard.
arXiv:2601.05529v5 Announce Type: replace Abstract: High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap,
arXiv:2604.06197v1 Announce Type: cross Abstract: Type 2 diabetes case reports describe complex clinical courses, but their timelines are often expressed in language that is difficult to reuse in long
arXiv:2510.26241v5 Announce Type: replace-cross Abstract: Modern vision-language models (VLMs) excel at many multimodal tasks, yet their grasp of temporal information in video remains weak and has not
Google's Gemma 4, launched on April 2, 2026, surpassed 10 million downloads within its first week, according to Google CEO Sundar Pichai, pushing the cumulative total for all Gemma models past 500 ...
arXiv:2610.19157v1 Announce Type: cross Abstract: Code generation models are actively being used in professional and educational settings. However, the competence of large language models (LLMs) to ge
arXiv:2610.17738v1 Announce Type: new Abstract: End-to-end (E2E) full-duplex spoken language models (FD-SLMs) enable simutanous listening and speaking continously, requiring models to take appropriate
arXiv:2610.19042v1 Announce Type: new Abstract: Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we
arXiv:2610.19375v1 Announce Type: new Abstract: Latent world models are routinely selected, checkpointed and ablated on one-step prediction loss, on the assumption that a model which predicts the next
arXiv:2603.23678v2 Announce Type: replace Abstract: Large Language Models (LLMs) offer transformative solutions across many domains, but healthcare integration is hindered by strict data privacy const
arXiv:2610.17630v1 Announce Type: cross Abstract: In outdoor environments, varying terrain and contact conditions can cause identical action commands to produce different motion outcomes for quadruped
arXiv:2610.18694v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models rec
arXiv:2610.14409v1 Announce Type: new Abstract: Generating an image with a diffusion or flow-matching model typically involves integrating a velocity field for hundreds of sequential steps. That compu
arXiv:2610.15322v1 Announce Type: cross Abstract: Enabling the reuse and composition of knowledge and capabilities distributed across foundation models is an important step toward building scalable ar
arXiv:2610.15724v1 Announce Type: new Abstract: Denoising Diffusion Probabilistic Models have emerged as powerful generative priors across domains ranging from molecular design to high-resolution imag
arXiv:2610.18826v1 Announce Type: cross Abstract: We introduce WorldOracle, a benchmark specifically designed to evaluate action-conditioned world models (ACWMs) against paired real-world executions.
i'm the maintainer of dodaios (formerly personal jarvis), an open-source ai agent app for the desktop. apache 2.0, runs on windows, macos and linux, no account and no cloud of ours between you and you
arXiv:2610.13276v1 Announce Type: new Abstract: Set-based language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the num
arXiv:2610.12758v1 Announce Type: new Abstract: Language models have been adopted faster than evaluation practices that reliably assess their risks, and a growing share of use is affective rather than
arXiv:2505.17244v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) leverage explicit reasoning traces, known as Chain-of-Thought (CoT) reasoning, to decompose complex problems int