Knowledge catalogue
arXiv:2603.19275v2 Announce Type: replace-cross Abstract: Automatic summarization of radiology reports is an essential application to reduce the burden on physicians. Previous studies have widely used
if you've read software history everything in your bone tells you open models have to win we are just in a weird anthropic fanboy moment we're seeing that open source models are getting good at file o
arXiv:2604.07879v1 Announce Type: new Abstract: Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content
arXiv:2512.21602v2 Announce Type: replace-cross Abstract: Millions of patients pass through emergency departments and intensive care units each year, where clinicians must make high-stakes decisions u
arXiv:2604.06211v1 Announce Type: cross Abstract: Natural language explanations produced by large language models (LLMs) are often persuasive, but not necessarily scrutable: users cannot easily verify
arXiv:2412.20718v2 Announce Type: replace Abstract: The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alig
arXiv:2604.06291v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions fur
arXiv:2604.07960v1 Announce Type: cross Abstract: Computer-Aided Design (CAD) is an expert-level task that relies on long-horizon reasoning and coherent modeling actions. Large Language Models (LLMs)
I spent the night testing open-source coding models against Claude Opus in production. Same codebase. Same tasks. Real API calls, real file edits, real bugs. Tested: Arcee Trinity-Large-Thinking, http
Ollama is now an inference provider on the Replicas platform, enabling users to deploy and run open‑source models directly within Replicas. The partnership supports popular models such as Claude Code,
arXiv:2605.05251v2 Announce Type: replace-cross Abstract: Function association is a useful process for binary reverse engineers. Search tools exist to perform association at scale, but they do not uti
arXiv:2610.21176v1 Announce Type: cross Abstract: Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and error
arXiv:2610.21185v1 Announce Type: new Abstract: Modern generative models produce high-quality individual outputs but struggle to sample diversely, even when explicitly instructed to do so. We introduc
arXiv:2610.21573v1 Announce Type: new Abstract: Decision trees can make vision-language model (VLM) classification interpretable by replacing a single prediction with a sequence of root-to-leaf questi
arXiv:2610.22053v1 Announce Type: new Abstract: Names carry demographic indicators such as age, gender, and race, which makes them a subtle but strong target of bias in large language models (LLMs). I
arXiv:2610.20852v1 Announce Type: cross Abstract: Negation is a fundamental aspect of language understanding and it is important vision-language models (VLMs) are able to process it effectively. We in
arXiv:2610.22364v1 Announce Type: cross Abstract: Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither dir
arXiv:2610.19080v1 Announce Type: new Abstract: Reinforcement learning (RL) has substantially improved the reasoning of autoregressive and discrete-diffusion language models. Language models that gene
arXiv:2610.20472v1 Announce Type: new Abstract: Cultural attitudes and social norms evolve over time, yet most cultural benchmarks for large language models (LLMs) treat culture as a static attribute
arXiv:2610.15239v1 Announce Type: new Abstract: Most benchmarks for large language models in medicine are built from licensing examinations and theoretical questions. The few that draw on real clinica
arXiv:2506.23101v2 Announce Type: replace-cross Abstract: Ensuring the trustworthiness of Multimodal Large Language Models (MLLMs) requires rigorous evaluation of gender bias, particularly in socially
arXiv:2610.18878v1 Announce Type: new Abstract: Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requi
arXiv:2610.18610v1 Announce Type: cross Abstract: Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends. Typed decision models offer a potential alternative
arXiv:2610.19165v1 Announce Type: cross Abstract: Many real-world questions demand not a single fact but an organized collection of them, yet existing factual knowledge benchmarks almost exclusively t
arXiv:2610.20288v1 Announce Type: new Abstract: Conditional generative models are increasingly used for scientific prediction beyond the direct training support. Yet scientific questions often concern
arXiv:2610.19327v1 Announce Type: new Abstract: Robotic ultrasound can standardize image acquisition and reduce operator workload and variability, but policy learning remains limited by the lack of re
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitat
What can large-scale AI models bring to the growing complexity of particle physics? @CERN and Mistral join forces to explore this question. The ambition: a single Large Physics Model, trained on billi
arXiv:2610.18161v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong zero-shot reasoning across diverse domains, but their potential for Human-Object Inter
arXiv:2610.15159v1 Announce Type: new Abstract: Existing depth-compression methods for large language models (LLMs) score layers individually or group only adjacent or contiguous layers, implicitly as
arXiv:2610.17466v1 Announce Type: new Abstract: Frechet Distributional (FD) objectives provide an effective distribution-level signal for post-training generative models. For latent generative models,
arXiv:2610.14579v1 Announce Type: cross Abstract: Embedding models underpin modern job-candidate matching: resumes, job descriptions, and queries are encoded as dense vectors, and recommendations come
arXiv:2610.14351v1 Announce Type: new Abstract: World-action models inherit broad visual and physical priors from video pre-training. However, standard within-video next-frame prediction allows them t
arXiv:2610.15267v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) learn world models directly in latent space, but unconstrained autoregressive predictors may contract t
arXiv:2610.16980v1 Announce Type: cross Abstract: Artificial Intelligence (AI) models are increasingly developed, published and used across scientific fields. Researchers, students and industry profes
arXiv:2610.14018v1 Announce Type: new Abstract: The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world
arXiv:2610.15415v1 Announce Type: cross Abstract: Before an agent acts, it must decide whether action is warranted. A single accuracy cannot distinguish failure to recognize a warranted action from re
arXiv:2610.18135v1 Announce Type: new Abstract: World-model-based visual navigation enables action planning by predicting future states under candidate trajectories. However, long-horizon rollout rema
arXiv:2610.16946v1 Announce Type: new Abstract: Descriptions of how people use AI are becoming training data for the next generation of models. We ask whether what a model reads about its users change
The first clear sighting of a rogue agent fleet from China using open weights models. Like the OpenAI swarms, the goal was seemingly AIs single-mindedly doing research (apparently mapping the most-use
Mistral AI announced its Le Chonk model, which performs visual grounding by accurately locating objects within images. On the Dense 200 benchmark it achieved a 42 % score, outperforming even frontier‑
arXiv:2601.18901v2 Announce Type: replace Abstract: Knowledge probing quantifies how much relational knowledge a language model (LM) has acquired during pre-training. Existing knowledge probes evaluat
arXiv:2610.12806v1 Announce Type: cross Abstract: We study byte-level autoregressive language models whose hidden state is a small quantum register, whose transitions are learned token-conditioned qua
arXiv:2610.12016v1 Announce Type: new Abstract: World models for control must capture which aspects of the environment respond to the agent's actions and which are relevant to reward. Generative world
arXiv:2610.10727v1 Announce Type: cross Abstract: Forecasting resale prices of used electronics is critical for subscription-based platforms where pricing errors translate directly into risk. Unlike s
arXiv:2610.11670v1 Announce Type: new Abstract: Diffusion models generalize early in training and later reproduce individual training samples. Standard tests detect memorization only once one-shot gen
arXiv:2407.14562v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities as general-purpose assistants, excelling in a wide range of reasoning tasks and supp
arXiv:2610.09464v1 Announce Type: new Abstract: Political discourse often uses rhetorical and persuasive language to frame narratives, influence public opinion, and mobilize audiences. While Bangla na
arXiv:2610.10198v1 Announce Type: new Abstract: Behavior Foundation Models (BFMs) are emerging as a paradigm for translating human intentions into executable humanoid behaviors. As these models evolve
arXiv:2610.10515v1 Announce Type: cross Abstract: Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled
arXiv:2610.10506v1 Announce Type: cross Abstract: Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should cho
arXiv:2610.10057v1 Announce Type: new Abstract: With the rise of univariate time series foundation models (e.g., Sundial, Timer), initial efforts have been made to extend them to multivariate settings
arXiv:2610.07232v1 Announce Type: new Abstract: Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation
arXiv:2610.07337v1 Announce Type: new Abstract: Removing copyrighted, unsafe, or user-specified concepts from a deployed text-to-image diffusion model is now a practical requirement. Weight-editing me
arXiv:2610.07711v1 Announce Type: new Abstract: Accurate nuclei instance segmentation is essential for quantitative renal pathology, yet general-purpose models often struggle with low contrast, dense
arXiv:2511.11500v3 Announce Type: replace Abstract: Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accuracy
arXiv:2610.05094v1 Announce Type: cross Abstract: Researchers increasingly use Large Language Models as judges (LLM-as-a-judge) to evaluate model outputs. Yet there are no standards for how to design
arXiv:2610.07028v1 Announce Type: new Abstract: Diffusion-based world models can generate and predict trajectories in high-dimensional dynamical systems, but predictive accuracy does not imply that th
arXiv:2610.07607v1 Announce Type: cross Abstract: Model-guided directed evolution seeks to identify high-fitness protein variants under limited oracle budgets. Protein language models (PLMs) provide r
arXiv:2610.07853v1 Announce Type: cross Abstract: Ternary language models such as BitNet b1.58, Falcon-E and BitCPM are fine-tuned with higher-precision latent weights and deployed as ternary codes pr