Knowledge catalogue
arXiv:2605.26365v1 Announce Type: new Abstract: Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping h
arXiv:2605.26119v1 Announce Type: cross Abstract: Industrial Edge AI programs often begin with the model and only later confront the platform. That sequencing is attractive because it allows early dem
arXiv:2602.04931v2 Announce Type: replace-cross Abstract: Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlation
Great to see @poolsideai (US lab) committing to open sourcing their foundation models going forward Laguna is an interesting release, check it out @Shaughnessy119 https://poolside.ai/blog/introducing-
If the Founder of Hugging Face asks, you gotta do it. Models and dataset now live: https://huggingface.co/papers/2605.22391 Also built an explorer: https://huggingface.co/spaces/Kaikaku/epicure-explor
arXiv:2605.26850v1 Announce Type: new Abstract: Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matc
arXiv:2601.03079v4 Announce Type: replace Abstract: Moral sensitivity is the most fundamental capability underlying human moral competence. Although many approaches aim to align large language models
arXiv:2601.12809v2 Announce Type: replace-cross Abstract: Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired,
arXiv:2605.27254v1 Announce Type: cross Abstract: Selecting which instances to label is a key challenge in low-label tabular learning. For recent Tabular Foundation Models such as TabPFN, context sele
arXiv:2605.26661v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected
arXiv:2605.26128v1 Announce Type: new Abstract: Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This
arXiv:2605.25889v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed on real robots, where each predicted action is executed and each failure carries a safet
Comfy will be at @aionthelot Our CEO @yoland_yan is joining a panel of AI video leaders for a progress report on the state of video models - where they excel, where they fall short, and what's coming
arXiv:2605.23909v1 Announce Type: new Abstract: We investigate the calibration of large language models' (LLMs') confidence across diverse tasks. The results of our preregistered study show that the c
arXiv:2505.18979v2 Announce Type: replace Abstract: Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters.
arXiv:2605.25477v1 Announce Type: cross Abstract: The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demons
arXiv:2605.24528v1 Announce Type: new Abstract: Real world decision-making requires constructing mental models under uncertainty over evidence, over the underlying causal rules, and over the state of
arXiv:2605.24550v1 Announce Type: new Abstract: Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning at
// Language Models Need Sleep // Let your agents 'sleep', folks. On a serious note, this is a fascinating paper on getting the most from long-horizon agents. Here is the problem with agents today: Att
arXiv:2605.26004v1 Announce Type: cross Abstract: Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with
arXiv:2605.24957v1 Announce Type: new Abstract: The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (L
Michael J. de la Merced / New York Times: OpenRouter raised 113M led by CapitalG, a source says at a 1.3B valuation, and now processes 25T tokens across 400+ models weekly, up from 5T six months ago —
arXiv:2605.24384v1 Announce Type: cross Abstract: Language models (LMs) can exhibit systematic biases against speakers based on variations in their dialects, even in the absence of a dialect label, a
Rebecca Torrence / Bloomberg: Sources: Fireworks AI, which helps companies run AI models, is in talks to raise funding at a 15B valuation after being valued at 4B in October 2025 — Fireworks AI, a sta
arXiv:2605.26111v1 Announce Type: cross Abstract: Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Ex
arXiv:2409.08379v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are reshaping knowledge work, yet their impact on voluntary, self-guided open innovation forums (contributors cho
arXiv:2605.25629v1 Announce Type: new Abstract: Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train--t
arXiv:2602.10538v3 Announce Type: replace-cross Abstract: Agentic theorem provers combine a reasoning model, retrieval, search, and a proof assistant verifier, yet it remains unclear which components
arXiv:2605.24806v1 Announce Type: cross Abstract: Large audio and language models have recently demonstrated zero-shot reasoning capabilities across various domains. However, it remains unclear how th
New York Times: A look at the UK's AI Safety Institute, whose researchers probe AI models for safety gaps, as its work becomes a blueprint for other governments' AI policies — The government's A.I. Se
arXiv:2605.23270v1 Announce Type: cross Abstract: Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consiste
arXiv:2605.23395v1 Announce Type: new Abstract: Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constra
arXiv:2605.23821v1 Announce Type: new Abstract: We propose a distributional theory of how hypernymy -- the ``is-a'' relation between general and specific concepts -- is encoded geometrically in langua
arXiv:2605.23556v1 Announce Type: new Abstract: Why does the low dimensionality of representations, typically dapprox 1000, not prevent modern embedding-based retrieval models from scaling to billions
arXiv:2605.23007v1 Announce Type: cross Abstract: We explore the application of LLM-driven algorithm optimization to several common tasks in quantitative finance. MadEvolve, a general-purpose algorith
arXiv:2511.05963v2 Announce Type: replace Abstract: Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Conse
A 6-person team is building task-specific AI models that are 4-8x faster than anything from OpenAI or Anthropic. 500K downloads on HuggingFace. No hype. Just better engineering winning on the merits.
arXiv:2605.22531v1 Announce Type: new Abstract: There is a gap between the theoretical foundations of disentanglement and the practice of modern representation learning. Existing theoretical framework
arXiv:2605.22795v1 Announce Type: cross Abstract: We propose and analyze a conservative drifting method for one-step generative modeling. The method replaces the original displacement-based drifting v
arXiv:2605.22331v1 Announce Type: new Abstract: Despite strong predictive results in the clinical machine learning literature, the translation of these models into bedside use remains limited by syste
arXiv:2605.22586v1 Announce Type: cross Abstract: This tutorial develops diffusion models from the viewpoint of differential equations. We begin with the conditional Gaussian forward process and show
arXiv:2605.22679v1 Announce Type: new Abstract: Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract in
arXiv:2605.22462v1 Announce Type: new Abstract: We propose a five-stage methodology for causal feature analysis in transformer language models (probe design, feature extraction, causal validation, rob
Jeremy Howard argues that AI model developers at OpenAI and Anthropic should prioritize breaking backwards compatibility during the prototyping phase rather than maintaining it, suggesting that backwa
arXiv:2605.20940v1 Announce Type: new Abstract: Accurate estimation of wheat spike volume is important for yield component analysis and stress resilience assessment, yet field-based measurement remain
arXiv:2605.20624v1 Announce Type: new Abstract: Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high in
arXiv:2605.21108v1 Announce Type: new Abstract: Latent state space systems are ubiquitous in statistical modelling, arising naturally when a time series is observed through a noisy measurement functio
arXiv:2605.20950v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existin
arXiv:2604.06750v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poo
arXiv:2603.22430v2 Announce Type: replace Abstract: Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without f
arXiv:2605.21123v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are co
arXiv:2605.21402v1 Announce Type: cross Abstract: Generative neural networks learn how to produce highly realistic images from a large, but finite number of examples - or do they simply memorise their
arXiv:2605.20235v1 Announce Type: new Abstract: Diffusion models generate high-dimensional data with remarkable quality, yet how their training efficiently learns the score function, bypassing the cur
arXiv:2605.19485v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning con
arXiv:2605.18927v1 Announce Type: cross Abstract: Bayesian latent space models offer a principled approach to network representation, but rely on correct specification of both geometry and link functi
arXiv:2605.20165v1 Announce Type: new Abstract: Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect gen
arXiv:2603.22161v2 Announce Type: replace Abstract: Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstra
arXiv:2605.19258v1 Announce Type: cross Abstract: Deep learning has enabled ECG diagnostic models with strong performance in tasks such as arrhythmia classification and abnormality detection. However,
arXiv:2605.19631v1 Announce Type: cross Abstract: End-to-end autonomous driving has emerged as a compelling alternative to traditional modular pipelines by directly mapping raw sensor data to driving
arXiv:2605.20170v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvemen