Knowledge catalogue
arXiv:2605.21086v1 Announce Type: new Abstract: While Large Language Models (LLMs) are increasingly integrated into in-vehicle conversational systems, identifying the optimal model remains challenging
arXiv:2605.20410v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases.
arXiv:2605.20607v1 Announce Type: cross Abstract: EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural netwo
arXiv:2605.21207v1 Announce Type: new Abstract: The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained
arXiv:2605.20584v1 Announce Type: new Abstract: Mobile app marketplaces require developers to disclose standardized content rating descriptors (CRDs) to inform users about potentially sensitive or res
arXiv:2605.21195v1 Announce Type: new Abstract: Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the pol
arXiv:2605.20809v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable performance on zero-shot annotation tasks, they often struggle with the specialized convention
arXiv:2605.20189v1 Announce Type: cross Abstract: Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with prima
arXiv:2603.26603v2 Announce Type: replace-cross Abstract: The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced privacy and offline accessibility, but thi
arXiv:2605.20731v1 Announce Type: new Abstract: Text-to-image models produce graphic design at production scale, but their supervision comes from photo-style preference data with a single overall verd
arXiv:2605.20876v1 Announce Type: new Abstract: Terminal agents extend Large Language Models with the ability to execute tasks directly in command-line environments, but their progress is bottlenecked
arXiv:2605.20292v1 Announce Type: new Abstract: Numerical time-series models can effectively process irregular electronic health record (EHR) trajectories, but they do not naturally expose the measure
arXiv:2605.20795v1 Announce Type: new Abstract: Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-bas
arXiv:2605.19407v1 Announce Type: cross Abstract: We investigate data filtering for large model pretraining via new scaling studies that target the high compute, data-scarce regime. In spite of an app
arXiv:2605.18780v1 Announce Type: cross Abstract: Reasoning-based Large Language Models (LLMs) like PO4ISR have set new benchmarks in session-based recommendation. However, the reproducibility of thei
arXiv:2605.19728v1 Announce Type: new Abstract: Foundation video models produce visually impressive results, but their use in embodied AI remains limited because they are primarily trained on natural
arXiv:2605.19260v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced t
arXiv:2605.18807v1 Announce Type: cross Abstract: Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervis
brain dump of how/why we use Evals to measure agents before & after shipping to prod 1. Good Evals simulate what our real users will do and encounter. They’re not really random benchmark tasks, they r
arXiv:2605.19299v1 Announce Type: new Abstract: The exponential growth of big data has intensified the need for efficient and interpretable machine learning models that can handle diverse data charact
arXiv:2509.19707v2 Announce Type: replace-cross Abstract: Copulas are a fundamental tool for modelling multivariate dependencies in data, forming the method of choice in diverse fields and application
arXiv:2605.19130v1 Announce Type: cross Abstract: Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal
arXiv:2605.18918v1 Announce Type: cross Abstract: Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web s
arXiv:2605.18936v1 Announce Type: cross Abstract: Social media text data are often used to train Machine Learning (ML) models to identify users exhibiting high-risk mental health behaviors. However, s
arXiv:2605.19824v1 Announce Type: new Abstract: Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and
arXiv:2509.21698v2 Announce Type: replace Abstract: Risk categorization in 10-K risk disclosures matters for oversight and investment, yet no public benchmark evaluates unsupervised topic models for t
arXiv:2605.19192v1 Announce Type: new Abstract: Multimodal agents use screenshots, documents, and webpages to choose tool calls. When a false visual claim triggers a click, email, extraction, or trans
arXiv:2503.08633v2 Announce Type: replace Abstract: Machine unlearning is the task of updating a trained model to forget specific training data without retraining from scratch. In this paper, we inves
arXiv:2605.18849v1 Announce Type: cross Abstract: Explainability methods have progressed rapidly, but global explanations for time-series models remain underdeveloped, with most approaches focusing on
arXiv:2605.19008v1 Announce Type: new Abstract: Modern language-model training is increasingly exposed to instability, degraded runs, and wasted compute, especially under aggressive learning-rate, sca
arXiv:2605.19722v1 Announce Type: cross Abstract: Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents? Sin
arXiv:2605.20183v1 Announce Type: new Abstract: Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However,
arXiv:2605.18825v1 Announce Type: new Abstract: Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt p
arXiv:2604.01341v2 Announce Type: replace Abstract: Mathematical modeling of visual textures traces back to Julesz's intuition that texture perception in humans is based on local correlations between
✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for deve
arXiv:2605.18832v1 Announce Type: cross Abstract: The Transformer is the foundational building block of modern AI, yet offers no principled handling of uncertainty, which is prevalent in real applicat
arXiv:2605.19382v1 Announce Type: new Abstract: Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluat
Reporting from Google I/O 2026 with the four biggest themes from one of the biggest AI labs in the world. 🎤 Voice AI as an interface Google and Samsung announced new Gemini-powered glasses with Gentle
arXiv:2510.09174v3 Announce Type: replace Abstract: This paper takes a closer look at Git Re-Basin, an interesting new approach to merge trained models. We propose a hierarchical model merging scheme
arXiv:2605.19338v1 Announce Type: cross Abstract: Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, l
arXiv:2605.19895v1 Announce Type: new Abstract: Constraint programming practitioners accelerate hard problems through a layered set of techniques applied in order of risk. Standard hardening (symmetry
arXiv:2605.19866v1 Announce Type: new Abstract: Vision-Language Models (VLMs) parse documents end-to-end but frequently break down on layouts unlike those seen in training. We attribute this to a two-
arXiv:2605.20179v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive (AR) models, offering better hardware utilization an
arXiv:2605.20119v1 Announce Type: cross Abstract: We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters.
arXiv:2605.19528v1 Announce Type: new Abstract: 3D localization in Multimodal Large Language Models (MLLMs), including 3D object detection and 3D visual grounding, is fundamentally limited by camera i
arXiv:2605.20074v1 Announce Type: new Abstract: Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured pred
arXiv:2605.18792v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge confli
arXiv:2603.06740v2 Announce Type: replace-cross Abstract: Protein language models (pLMs) have shown strong potential for zero-shot prediction of missense variant effects, yet systematic benchmarking o
arXiv:2510.09872v2 Announce Type: replace-cross Abstract: Training web agents to navigate complex, real-world websites requires them to master extit{subtasks} - short-horizon interactions on multiple
arXiv:2605.19343v1 Announce Type: new Abstract: Single-cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approac
Worldlier is a Cohere language model that natively supports 48 world languages with improved efficiency, particularly for non-European languages. This represents an expansion of language coverage beyo
arXiv:2605.19969v1 Announce Type: new Abstract: Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train models without a central server. However, the col
arXiv:2212.02098v5 Announce Type: replace Abstract: Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memo
arXiv:2605.17954v1 Announce Type: cross Abstract: Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a seque
arXiv:2605.16386v1 Announce Type: new Abstract: Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal cl
arXiv:2605.17508v1 Announce Type: cross Abstract: Split Federated Learning (SFL) enables privacy-preserving collaborative training by partitioning models between clients and a server. However, under n
arXiv:2605.16949v1 Announce Type: new Abstract: Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Repre
arXiv:2605.16532v1 Announce Type: new Abstract: Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming:
arXiv:2605.16401v1 Announce Type: new Abstract: While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environm
arXiv:2605.17255v1 Announce Type: new Abstract: Formal theorem-proving benchmarks enable mechanically verifiable evaluation of mathematical reasoning in large language models. However, existing benchm