Knowledge catalogue
arXiv:2607.06482v1 Announce Type: cross Abstract: Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fac
arXiv:2607.05533v1 Announce Type: new Abstract: Computational pathology foundation models (PFMs) have advanced whole-slide image analysis. However, their size and inference cost hinder local deploymen
arXiv:2502.09696v3 Announce Type: replace Abstract: Large Multimodal Models (LMMs) exhibit shortfalls when interpreting images and, by some measures, have poorer spatial cognition than young children
arXiv:2607.03659v1 Announce Type: cross Abstract: Relational databases (RDBs) are the primary data infrastructure in many enterprises, yet recent deep learning methods designed for RDBs have been eval
arXiv:2507.04136v2 Announce Type: replace Abstract: This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Poli
arXiv:2607.04081v1 Announce Type: new Abstract: In-context learning (ICL) has emerged as a central capability of pretrained language models, yet its theoretical analysis has focused primarily on causa
arXiv:2607.02563v1 Announce Type: cross Abstract: Diffusion-based text-to-image models can synthesize complex and highly structured visual content, yet the emergence and evolution of semantic structur
Banger compression paper from NVIDIA. (bookmark it) Bigger MoE models keep winning on quality, but serving them at interactive latency is still hard. NVIDIA compresses the hybrid MoE Nemotron-3-Super
arXiv:2607.03647v1 Announce Type: new Abstract: Large vision language models (VLMs) report strong accuracy on medical question-answering, yet it remains unclear whether they reason from visual evidenc
arXiv:2607.02865v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies show promising zero-shot generalization, but often fail under deployment-time distribution shift, leadi
arXiv:2607.05274v1 Announce Type: new Abstract: Training-free concept erasure is an attractive mechanism for controlling text-to-image diffusion models, but precise erasure often comes at the cost of
Excellent investigation of the mechanics of language models. 🫢A notable blindspot, however: several teams have actually been **directly** comparing the working of LLMs to those of the human brain 🧠 fo
arXiv:2511.19636v2 Announce Type: replace-cross Abstract: In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on funda
arXiv:2607.04856v1 Announce Type: new Abstract: Local Process Models (LPMs) are an underexplored concept in process mining. LPMs describe patterns in event data considering sequence, choice, concurren
arXiv:2607.04500v1 Announce Type: new Abstract: Self-supervised latent world models can assign a surprise score to driving scenarios without any human labels. A natural follow-up question is whether s
arXiv:2607.04167v1 Announce Type: new Abstract: Recent work showed that language models represent character counts on curved 1D manifolds, with attention heads performing geometric transformations to
arXiv:2603.22730v2 Announce Type: replace Abstract: Pfeffer, Krugel, and Uhl (2025) report that OpenAI's reasoning model o1-mini produces more utilitarian responses to the trolley problem and footbrid
arXiv:2607.04647v1 Announce Type: cross Abstract: Scalable Bayesian inference for generalized linear mixed models (GLMMs) provides uncertainty-aware analysis of correlated longitudinal data, but exist
arXiv:2607.03585v1 Announce Type: new Abstract: Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perception modules to extract actionable information from h
arXiv:2607.03050v1 Announce Type: cross Abstract: Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate larg
arXiv:2607.04245v1 Announce Type: cross Abstract: Generative models have changed how machine learning represents complex data distributions, especially in language and vision, yet many real-world syst
arXiv:2607.03094v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding for brain-computer interfaces (BCIs) faces a major challenge: substantial inter-subject variability limits effecti
arXiv:2607.02805v1 Announce Type: cross Abstract: High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rat
arXiv:2607.05133v1 Announce Type: new Abstract: World Action Models (WAMs) have shown strong potential for improving action generalization in autonomous driving by using future video prediction as den
arXiv:2607.02995v1 Announce Type: cross Abstract: Vision-language models can exhibit visual concept-conditioned divergence: given images containing demographic features, corporate logos, or ideologica
arXiv:2607.03158v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to implement algorithms from research manuscripts, but papers often leave implementation choices im
arXiv:2607.04640v1 Announce Type: new Abstract: We study how correctness is assembled inside aligned language models, not only whether the final answer is right. Using layer-wise difference-in-differe
Armin Ronacher / Armin Ronacher's Thoughts and Writings: Claude Opus 4.8 and Sonnet 5 seem worse at tool calls than older models, likely due to post-training that assumes Claude Code-like harnesses as
GLM-5.2, an open-source model available through Hugging Face, can now be selected and used within Claude Code through Hugging Face Inference Providers and the hf-claude integration. This development d
arXiv:2408.01139v4 Announce Type: replace Abstract: Perturbation robustness evaluates the vulnerabilities of models, arising from a variety of perturbations, such as data corruptions and adversarial a
arXiv:2607.01813v1 Announce Type: cross Abstract: Evaluation benchmarks are essential for assessing vision-language models (VLMs), but most multimodal benchmarks are static, making them vulnerable to
arXiv:2607.01977v1 Announce Type: new Abstract: Ontology learning (OL) aims to automatically construct structured knowledge models from text, yet progress remains fragmented across methods, domains, a
Prompt engineering is costing you money. Learn how to fine-tune your models. Stuffing a lot of text into every single API call slows down your app because the model has to process all those tokens bef
arXiv:2510.04391v5 Announce Type: replace Abstract: Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relational structure across human and synthetic large la
The Information: Sources: Alibaba has banned employees from using Claude Code and asked them to remove all Claude models from their work computers, citing security concerns — Alibaba Group has banned
arXiv:2607.01394v1 Announce Type: new Abstract: We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing
This is true… but maybe less important than the fact that people don’t try ambitious things with these systems. Many models are excellent as a Google replacement, for homework “help,” etc. It is someo
Unpopular opinion: While everyone is so hyped about Fable, GPT5.6 and other huge and expensive models, I think the real hero of the last few months is *Qwen 27b*. Our ML/AI engineering teams are have
arXiv:2607.00148v1 Announce Type: cross Abstract: Learning predictive models of the world enables robotic control through planning, potentially allowing robots to improvise solutions on new tasks. How
arXiv:2607.00249v1 Announce Type: new Abstract: New device layouts pose a challenging modeling problem due to the lack of large datasets for each specific layout. Biosignal foundation models offer a p
arXiv:2604.04198v2 Announce Type: replace Abstract: Generalization is a central challenge in autonomous driving, as real-world deployment requires robust performance under unseen scenarios, sensor dom
arXiv:2607.00020v1 Announce Type: new Abstract: Spatial grounding remains a key limitation of vision-language-action (VLA) systems for robotic manipulation. While current models can recognize objects
arXiv:2607.01001v1 Announce Type: new Abstract: Radiomics is the established approach for CT-based lung cancer phenotyping, yet comparisons with foundation models rarely isolate contributions of featu
arXiv:2607.01222v1 Announce Type: new Abstract: Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due t
arXiv:2602.23164v2 Announce Type: replace Abstract: Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains
arXiv:2607.00510v1 Announce Type: new Abstract: Knowing which training examples drive outputs is fundamental to auditing, correcting, and understanding language models, yet for modern LLMs this remain
arXiv:2607.00351v1 Announce Type: new Abstract: Vision-Language-Action models excel at robotic manipulation, driven by the scale and diversity of demonstration data. However, standard training paradig
arXiv:2512.18934v2 Announce Type: replace-cross Abstract: Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency.
arXiv:2606.31308v1 Announce Type: new Abstract: This paper investigates the capability of Large Language Models (LLMs) to detect and classify floating-point errors statically in software code. We intr
arXiv:2510.09340v2 Announce Type: replace Abstract: Recent language models exhibit significant logical reasoning abilities, yet the mechanisms supporting deductive inference remain poorly understood.
arXiv:2606.31293v1 Announce Type: new Abstract: Accurate modeling of dental crown morphology is fundamental for diagnosis, orthodontic planning, and computer-aided restoration design. However, dataset
Neurologyca, a company working on human-centric artificial intelligence, announced the launch of a research division on Tuesday dedicated to advancing AI models’ ability to understand and adapt to peo
arXiv:2606.31334v1 Announce Type: new Abstract: Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min f
arXiv:2606.30686v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) systems, built on pretrained vision-language models (VLMs), have shown rapidly improving performance on robot manipulatio
arXiv:2501.14940v4 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety ben
arXiv:2606.29094v1 Announce Type: new Abstract: Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple
arXiv:2606.28538v1 Announce Type: new Abstract: We investigate domain adaptation of modern BERT models in the legal domain. We further pre-train ModernBERT on all US court opinions using the masked la
arXiv:2601.05366v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as agents that invoke external tools through structured function calls. While recent wo
Love how Google continues to drive down the cost of building with their models. <4s image and 0.034 / 1K image. Wow! We have a bunch of stuff (education & research) we're building @dair_ai using Nano
arXiv:2606.29600v1 Announce Type: cross Abstract: A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid