Knowledge catalogue
We're excited to introduce US-based frontier open-weight models in AWS GovCloud (US). With this release, Amazon Bedrock now supports OpenAI’s open-weight GPT OSS models (120B and 20B) and NVIDIA Nemot
arXiv:2606.15032v2 Announce Type: replace Abstract: World models have become a central abstraction in modern AI. The term now refers to several different objects: action-conditioned environment models
arXiv:2606.28864v1 Announce Type: new Abstract: Test-time scaling is a paradigm where large models use additional compute at inference to achieve better performance, without changing model weights. Wh
arXiv:2606.29196v1 Announce Type: cross Abstract: Do language models know when they are being tested? This question matters for AI safety: a model that recognises an evaluation context could alter its
arXiv:2606.29815v1 Announce Type: new Abstract: Evaluating code large language models (Code LLMs) requires reliable detection of data leakage, where benchmark performance is artificially inflated by e
arXiv:2606.28325v1 Announce Type: cross Abstract: Large language models process the world's writing systems with radical inequality. We constructed the Digital Script Representation Index (DSRI), a se
arXiv:2602.10179v2 Announce Type: replace-cross Abstract: Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user int
arXiv:2606.26566v1 Announce Type: cross Abstract: Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LL
arXiv:2606.14122v2 Announce Type: replace Abstract: Byte-level tokenization enables language models to handle any Unicode input, but models can generate invalid UTF-8 sequences when encountering rare
arXiv:2606.26287v1 Announce Type: new Abstract: With the increase in model parameters and training data, the instruction following and generalization capabilities of Large VisionLanguage Models (LVLMs
arXiv:2606.27326v1 Announce Type: cross Abstract: Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fl
arXiv:2606.27187v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have recently shown immense potential in automated content moderation, sparking growing interest in developing ha
arXiv:2606.26529v1 Announce Type: cross Abstract: AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified. We
arXiv:2606.25476v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes appl
arXiv:2606.24998v1 Announce Type: new Abstract: Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition. Earlier cont
arXiv:2606.24890v1 Announce Type: new Abstract: Can a small group of volunteers shape how AI systems discuss animal welfare, just by editing Wikipedia? We show that they can. Wikipedia appears in near
arXiv:2606.24506v1 Announce Type: cross Abstract: Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold. This creates a GPU memory pro
arXiv:2603.20510v2 Announce Type: replace Abstract: Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel. We introd
arXiv:2606.24855v1 Announce Type: new Abstract: Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable ag
arXiv:2606.21775v1 Announce Type: new Abstract: Recently, world models have emerged as a promising paradigm for building intelligent agents by learning predictive models that estimate future environme
arXiv:2606.21795v1 Announce Type: new Abstract: Despite their widespread use, the role of reward models in shaping reinforcement learning is poorly understood. Reward models offer a tempting promise:
arXiv:2510.02561v2 Announce Type: replace Abstract: Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual
arXiv:2606.23057v1 Announce Type: cross Abstract: Large language models now mediate how buyers discover products and services, making the competitive structure of AI-generated recommendations a strate
arXiv:2606.11722v1 Announce Type: cross Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (
arXiv:2606.10135v1 Announce Type: cross Abstract: Transitioning bidirectional video diffusion models into an autoregressive paradigm improves the interactivity of video world models, but existing caus
arXiv:2606.08571v1 Announce Type: cross Abstract: Large language models frequently fail in a characteristic way: rather than acknowledging ignorance, they produce fluent but incorrect answers to quest
arXiv:2606.07967v1 Announce Type: new Abstract: Controllable video world models target interactive world exploration, where models must faithfully execute explicit action commands while preserving vis
arXiv:2606.08956v1 Announce Type: new Abstract: Scientists have historically relied on mathematical models based on differential equations to relate system inputs -- forces, fluxes, or heat sources --
arXiv:2606.08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale. Our curr
arXiv:2604.00903v2 Announce Type: replace Abstract: Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos fo
arXiv:2606.07974v1 Announce Type: cross Abstract: A learned world model provides a powerful physical intuition for evaluating future states. But its effectiveness in continuous control also depends cr
arXiv:2606.09705v1 Announce Type: new Abstract: Scientific generative modeling often requires size transfer, where models trained on small systems are evaluated on larger ones. While translation-invar
arXiv:2606.07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the mod
arXiv:2606.07481v1 Announce Type: new Abstract: While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid expl
arXiv:2606.05112v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed as clinical agents, yet static, single-turn benchmarks cannot capture how a model dynamically del
arXiv:2606.04525v1 Announce Type: new Abstract: Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reportin
arXiv:2603.03205v2 Announce Type: replace Abstract: Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon ac
arXiv:2606.03660v1 Announce Type: new Abstract: Large language models are increasingly used as chemistry assistants, yet most chemistry benchmarks still score only final answers. This masks a critical
arXiv:2606.02741v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in sustainability-related decision support, reporting, and public communication, yet little systemati
arXiv:2606.02436v1 Announce Type: new Abstract: Video world models aim to simulate controllable visual environments, but long-horizon rollouts depend on what the model remembers after observations lea
arXiv:2606.00793v1 Announce Type: new Abstract: Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences. However, a fund
arXiv:2504.04718v2 Announce Type: replace-cross Abstract: Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However,
arXiv:2606.01247v1 Announce Type: new Abstract: Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has la
arXiv:2605.30713v1 Announce Type: cross Abstract: Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their applicati
arXiv:2510.04704v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to propert
arXiv:2605.28830v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly deployed in safety-critical applications, robust content moderation becomes essential. We present a c
arXiv:2510.16060v2 Announce Type: replace-cross Abstract: The recent development of foundation models for time series data has generated considerable interest in using such models across a variety of
arXiv:2605.28919v1 Announce Type: cross Abstract: Large language models have achieved strong reasoning capabilities, though often at the cost of massive parameter counts and expensive inference. In th
arXiv:2605.29247v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underp
arXiv:2605.30161v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D und
arXiv:2605.27618v1 Announce Type: new Abstract: Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may
arXiv:2512.15791v2 Announce Type: replace-cross Abstract: In Artificial Intelligence (AI), language models have gained significant importance due to the widespread adoption of systems capable of simul
arXiv:2605.28347v1 Announce Type: new Abstract: Multi-Label Recognition (MLR) based on Vision-Language Models (VLMs) aims to leverage their pre-trained knowledge to better adapt complex recognition sc
arXiv:2510.15839v2 Announce Type: replace Abstract: Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learni
arXiv:2605.28032v1 Announce Type: new Abstract: Large Language Models are increasingly applied in the petroleum industry, highlighting the need for a domain-specific evaluation framework. This study d
arXiv:2601.21666v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, wh
arXiv:2605.27851v1 Announce Type: new Abstract: Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational
arXiv:2605.28626v1 Announce Type: new Abstract: Hybrid interpretable models combine a transparent component with a black-box model by assigning some examples to the former and deferring the rest to th
ITBench-AA is a new benchmark developed by Artificial Analysis and IBM that evaluates frontier AI models on agentic enterprise IT tasks, with results showing that current leading models score below 50
arXiv:2511.14993v3 Announce Type: replace-cross Abstract: This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis.