Knowledge catalogue
arXiv:2605.27616v1 Announce Type: cross Abstract: Real-time anomaly segmentation demands both high recall and efficient low-precision inference. We study the three-way interaction of model architectur
arXiv:2605.28158v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used to assist with operations research (OR) modeling, yet existing OR-oriented benchmarks often redu
arXiv:2205.14090v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) has well-documented merits for optimizing black-box functions with an expensive evaluation cost. Such functions eme
arXiv:2503.22655v2 Announce Type: replace Abstract: Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is co
Today, we're releasing LFM2.5-8B-A1B, a device-optimized model designed to power real-life applications on phones, laptops, PCs, robots, and fast & lightweight server-side use-cases. > 8B MoE, 1.5B ac
arXiv:2605.28346v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly evaluated for whether they identify the right visual content, but little is known about whether they expr
arXiv:2605.26967v1 Announce Type: new Abstract: Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, wher
arXiv:2501.06708v5 Announce Type: replace-cross Abstract: Large-scale web-crawled datasets contain noise, bias, and irrelevant information, necessitating data selection techniques. Existing methods de
Google has the only true Omni model, but the elements aren't hooked up. It appears it can take in & output audio, images. video, songs, text, code, etc. But right now each type of output is separate.
arXiv:2605.26454v1 Announce Type: new Abstract: Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-trai
arXiv:2602.10104v2 Announce Type: replace-cross Abstract: Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control
arXiv:2605.26788v1 Announce Type: cross Abstract: Large language models (LLMs) achieve impressive performance when a task is fully specified in a single turn, yet the same models lose up to 39% of tha
arXiv:2603.28730v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervis
arXiv:2510.05141v2 Announce Type: replace Abstract: When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs
Jeremy Howard comments on the Xiaomi MiMo v2.5 model, highlighting its exceptional value proposition and cost-effectiveness for prompt processing. The post appears to include comparative pricing data
arXiv:2605.26026v1 Announce Type: cross Abstract: Light sheet fluorescence microscopy (LSM) enables high-resolution, three-dimensional (3D) imaging of biological specimens, providing rich volumetric d
arXiv:2604.05550v2 Announce Type: replace Abstract: Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-T
arXiv:2512.04733v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's e
arXiv:2605.25347v1 Announce Type: cross Abstract: We introduce ERNIE-Image, an open-source text-to-image generation model built upon an 8B single-stream DiT architecture. ERNIE-Image aims to bridge th
arXiv:2406.09079v5 Announce Type: replace Abstract: Deep reinforcement learning agents progressively lose representational capacity during training: neurons become dormant, removing active capacity fr
arXiv:2605.24597v1 Announce Type: new Abstract: Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We
arXiv:2602.02009v2 Announce Type: replace Abstract: Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models typ
arXiv:2508.12538v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) has emerged as a universal standard that enables AI agents to seamlessly connect with external tools, signifi
Anima is a 2 billion parameter text-to-image model focused mainly on anime concepts and styles, but also capable of generating other non-photorealistic content. A Regional Condition Custom Node for An
arXiv:2605.24396v1 Announce Type: new Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test
arXiv:2605.25903v1 Announce Type: new Abstract: Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each mo
arXiv:2602.06508v2 Announce Type: replace Abstract: Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to ext
arXiv:2605.23055v1 Announce Type: cross Abstract: Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet t
arXiv:2605.23899v1 Announce Type: new Abstract: Language agents increasingly improve by reusing skills -- structured procedural artifacts distilled from past experience. In particular, domain-level an
arXiv:2605.23825v1 Announce Type: cross Abstract: It has generally been assumed that geopolitical bias in language models originates from the training data used during the pre-training phase. We teste
arXiv:2605.22864v1 Announce Type: new Abstract: The maximum softmax probability (MSP) represents a default approach when evaluating uncertainty quantification for language model generation with struct
arXiv:2605.23220v1 Announce Type: new Abstract: Despite the growing use of world models as decision-making agents, their adversarial robustness remains underexplored due to the lack of dedicated autom
arXiv:2605.23025v1 Announce Type: new Abstract: World models represent a paradigm shift in generative AI, pursuing predictive understanding and controllable simulation of environments in a structured
Clem Delangue reports consuming approximately 17 million tokens daily when running local language models, indicating substantial usage of on-device AI inference. He expresses satisfaction with the uti
Thinking Machines is impressive. In a couple hours I just fine tuned my own Qwen3.5-397B model this afternoon. Fast usable multimodal is also going to enable very mind-blowing personal AI. People talk
Latent Space reports on a rebranding or reorganization where Model Labs have been renamed or converted into Agent Labs, reflecting a shift in focus toward AI agent development and capabilities. This c
arXiv:2605.22506v1 Announce Type: cross Abstract: Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typ
arXiv:2605.22507v1 Announce Type: new Abstract: We propose a new framework for generative modeling based on a discrete-time stochastic control formulation of measure transport. Adapting classic result
Last year I deepfaked my kid's stuffed animal to make it look like his plush deer was on vacation. It was an experiment to see if I could re-create the events depicted in a Gemini ad Google was runnin
it’s truly astonishing to see the entire field move in the neurosymbolic and world model directions I advocated in 2019 and 2020 and then simultaneously see people claim (invariably without specific e
arXiv:2605.21835v1 Announce Type: cross Abstract: The synergistic interpretation of anatomical information from computed tomography (CT) and metabolic information from positron emission tomography (PE
Cohere Command A+ is now available in Microsoft Foundry as a Managed Compute offer. Cohere’s latest open-source model is built for enterprise-grade agentic AI workloads, bringing together reasoning, m
arXiv:2605.22465v1 Announce Type: new Abstract: The fundamental challenge of listening in multi-talker environments is a cognitive bottleneck, defined by the Ease of Language Understanding (ELU) model
NEW paper worth reading. A full agentic workflow can be distilled into model weights and run at roughly 100x lower inference cost while preserving near-frontier task quality. The workflow includes mul
arXiv:2605.20303v1 Announce Type: new Abstract: Airfoil shape design is a fundamental task in aerospace engineering, with a direct impact on flight stability and fuel consumption. Deep learning has re
arXiv:2605.21143v1 Announce Type: cross Abstract: A soundscape is composed of three types of sound: biophony (sounds made by animals), geophony (natural abiotic sounds) and anthropophony (sounds made
arXiv:2605.20267v1 Announce Type: new Abstract: Synthetic PET images are valuable for quantitative imaging workflow development, scalable virtual imaging trials, and deep learning model training, but
arXiv:2605.21292v1 Announce Type: cross Abstract: Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the fini
Managed Deep Agents is a new LangChain feature in private beta that provides managed infrastructure for deep agents, designed to be model-agnostic and deployable with minimal code. The service aims to
arXiv:2605.20479v1 Announce Type: new Abstract: Hyperparameter prediction is a critical practical bottleneck for model-based image denoisers, ranging from classical TV/TGV variational solvers to moder
Many of the world’s fastest-growing AI startups are choosing to build their future — and the world’s — on Google Cloud because of our complete and open AI stack. We embed AI into every layer of our ar
arXiv:2605.21487v1 Announce Type: new Abstract: Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task t
arXiv:2602.14778v3 Announce Type: replace-cross Abstract: Hallucinations -- plausible but factually incorrect responses -- pose a major challenge to the reliability of Large Language Models (LLMs), es
arXiv:2605.19311v1 Announce Type: new Abstract: The rapid adoption of deep learning has increasingly led to data-driven models replacing classical model-based algorithms, even in domains governed by w
Cohere is on such a great open-source trajectory lately. Beautiful Apache 2.0 model! https://huggingface.co/CohereLabs/command-a-plus-05-2026-bf16 Command A+ from @cohere is out now :) its our best mo
arXiv:2605.18993v1 Announce Type: cross Abstract: Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging through addition and unlearning thr
arXiv:2605.18911v1 Announce Type: cross Abstract: Wildfire prediction is important for early warning and resource allocation, yet existing Earth foundation models (Earth FMs) are pretrained for genera
arXiv:2605.19457v1 Announce Type: new Abstract: Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approa
arXiv:2605.19101v1 Announce Type: cross Abstract: Training general-purpose Audio Large Language Models (ALLMs) across diverse datasets is essential for holistic audio understanding, yet it faces signi
arXiv:2511.11688v3 Announce Type: replace-cross Abstract: Diffusion probabilistic models have set a new standard for generative fidelity but are hindered by a slow iterative sampling process. A powerf