Knowledge catalogue
arXiv:2606.09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees. How
arXiv:2606.08340v1 Announce Type: new Abstract: As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks.
arXiv:2606.08881v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation, yet existing evaluations are primarily conducted
arXiv:2606.08780v1 Announce Type: new Abstract: Existing zero-shot video editing methods rely on pre-trained diffusion models, successfully achieving spatial control and basic temporal consistency but
arXiv:2606.07853v1 Announce Type: cross Abstract: Large Language Models are transforming the support for clinical decision and their application in real scenarios. Yet, most benchmarks are conducted i
arXiv:2606.07805v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational
arXiv:2606.08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance va
arXiv:2606.07833v1 Announce Type: cross Abstract: Standard AI red teaming evaluations reduce adversarial campaigns to a single binary outcome, attack success rate (ASR), not taking into account the se
arXiv:2606.07538v1 Announce Type: cross Abstract: Large language model (LLM)-based agents provide a novel paradigm for the automated processing of remote sensing(RS) data. Their success in complex RS
arXiv:2606.07519v1 Announce Type: cross Abstract: We introduce the novel task of bidirectional small-granularity search between code and text, where the queries are small snippets of text or code and
arXiv:2606.08674v1 Announce Type: cross Abstract: Existing video generation frameworks treat sequence duration as an externally prescribed parameter -- fixed frame counts or text prompts -- producing
arXiv:2606.08684v1 Announce Type: new Abstract: We present BLUE, a minimal method for better language use in vision-language-action (VLA) models for autonomous driving (AD). Through extensive analysis
arXiv:2503.08434v5 Announce Type: replace-cross Abstract: Recent advances in large-scale text-to-image models have revolutionized creative fields by generating visually captivating outputs from textua
BREAKING: Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world. We've been testing it internally @every for the last week or so
arXiv:2606.07881v1 Announce Type: new Abstract: Pipeline parallelism is essential for training large neural networks, but existing schedules trade off throughput, memory, and optimization consistency.
arXiv:2606.09155v1 Announce Type: new Abstract: Accurate calibration of particle-based simulators is crucial for robotic earthwork simulation, but analytical calibration is challenging due to this tas
arXiv:2606.09257v1 Announce Type: cross Abstract: High-Dimensional Low-Sample Size (HDLSS) tabular domains (e.g., omics) are characterized by n ll m, where n = number of samples, and m = number of fea
btw insane amounts of alpha in telling claude code to 'review my code for issues' on Fable rn while it is not pay per use be prepared to be in abject horror that you shipped anything to prod without a
arXiv:2606.09514v1 Announce Type: new Abstract: Large language models (LLMs) incur high inference cost due to their depth and parameter scale. Depth pruning can reduce latency by skipping redundant Tr
but but i thought it was magic? What we learned testing Claude Fable/Mythos 5 on Vending-Bench: > Performance: Makes less money than Opus 4.7 and GPT-5.5 > Alignment: A step back. (Opus 4.8 was better
arXiv:2606.07891v1 Announce Type: new Abstract: 3D reconstruction could improve colonoscopy by estimating mucosal coverage and alerting clinicians to missed regions during screening. However, algorith
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:2504.00375v2 Announce Type: replace Abstract: The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing signific
arXiv:2505.11189v3 Announce Type: replace Abstract: Large language models (LLMs) can amplify misinformation, undermining societal goals such as the UN SDGs. We study three documented drivers of misinf
arXiv:2606.09237v1 Announce Type: new Abstract: Time-of-flight cameras are popular in robotics for providing direct depth information while being compact, inexpensive, and robust to lighting condition
arXiv:2606.07613v1 Announce Type: cross Abstract: Visual evidence has long been treated as a reliable form of legal proof, but advances in artificial intelligence (AI) are undermining that assumption.
arXiv:2606.08346v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving the reasoning capabilities of large language models
arXiv:2606.08275v1 Announce Type: cross Abstract: When an LLM agent fails -- issues a refund it should not have, calls the wrong tool, leaks data -- existing tooling answers what happened (observabili
arXiv:2606.05797v2 Announce Type: replace Abstract: Longitudinal treatment decisions from multivariate time-series data require predicting potential outcomes under future treatment sequences in the pr
arXiv:2602.22919v2 Announce Type: replace Abstract: Cardiac cine magnetic resonance imaging (MRI) is central to functional cardiac assessment, yet a full current cine sequence may not always be direct
arXiv:2603.13431v3 Announce Type: replace-cross Abstract: Computational antibody design has seen rapid methodological progress, with dozens of deep generative methods proposed in the past three years,
arXiv:2606.08959v1 Announce Type: new Abstract: We introduce ChinaHeritaQA, a multimodal benchmark dataset for evaluating the cultural reasoning abilities of vision-language models (VLMs) on UNESCO Wo
arXiv:2606.08864v1 Announce Type: new Abstract: The rapid adoption of diffusion and large-scale generative models has made it increasingly challenging to distinguish synthetic imagery from real photog
arXiv:2606.07962v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in open-world reasoning and understanding. Howe
arXiv:2606.08169v1 Announce Type: cross Abstract: Enabling robots to understand and execute tasks from natural language commands while maintaining data efficiency remains challenging. Foundation model
arXiv:2606.09180v1 Announce Type: new Abstract: We present our submission to the CVPR 2026 Argoverse 2 Scenario Mining Challenge. Our system uses a four-stage pipeline: (1) autonomous code generation
This article discusses Claude Fable 5, likely exploring Anthropic's latest version of their AI model and examining new fables or narratives related to AI safety concepts. The piece probably analyzes h
Claude Fable 5, Anthropic’s latest frontier model, is now generally available on Google Cloud. This launch is the latest proof point of our ongoing commitment to bring the industry's latest models str
Ethan Mollick / One Useful Thing: Claude Fable 5 hands-on: impressive results working on complex projects, like building an interactive isochrone map or a data analysis tool in just 9.5 hours — Claude
Claude Fable 5 is now available for use in the Cursor IDE, achieving a new state-of-the-art performance on CursorBench with a score of 72.9%, an 8-point improvement over the previous best result. This
Claude Fable 5 has been integrated into Devin and achieved the top ranking on FrontierCode, Cognition AI's benchmark for real-world engineering tasks. This integration represents an advancement in Dev
Claude Fable 5 is now available as a model option on the Databricks platform, integrated with Unity AI Gateway to provide governance controls for enterprise users. This integration allows organization
Nous Research announced support for Claude Fable 5 integration with Hermes Agent through the Nous Portal, offering new users a promotional one-month free trial of the Plus plan for the first 500 signu
Claude Fable 5 is now available through Vercel's AI Gateway, expanding the model options developers can access through the platform. This announcement likely details how developers can integrate and u
Gary Marcus critiques Anthropic's rapid shift in positioning Claude from a model deemed too dangerous for public release to one made widely available with safety measures, suggesting this represents i
Jerry Liu's post urges Anthropic to rapidly expand its data center infrastructure to support Claude AI's growing demand and operational needs. The post reflects concerns about scaling computational re
arXiv:2606.08168v1 Announce Type: cross Abstract: Leading commercial endpoint detection and response (EDR) products have shifted from operator-configured rule sets to multi-component systems where aut
arXiv:2512.13869v3 Announce Type: replace Abstract: Training object detectors demands extensive, task-specific annotations, yet this requirement becomes impractical in UAV-based human detection due to
arXiv:2603.04177v2 Announce Type: replace-cross Abstract: LLM coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human devel
Cohere announced the release of another open source model, receiving positive reception from the community. The post was shared on X (formerly Twitter) and highlights Cohere's continued contribution t
arXiv:2606.09118v1 Announce Type: new Abstract: As LLM capabilities advance rapidly, the evaluation methods used to assess them increasingly lag behind. Traditional benchmarks relied on programmatic v
arXiv:2603.22473v2 Announce Type: replace-cross Abstract: Hybrid language models combine softmax attention with linear-time sequence mechanisms such as state-space or linear-attention layers, but the
arXiv:2606.09331v1 Announce Type: cross Abstract: Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is di
arXiv:2602.17911v3 Announce Type: replace-cross Abstract: Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is
arXiv:2601.07013v2 Announce Type: replace-cross Abstract: Traditional filtering algorithms for state estimation -- such as classical Kalman filtering, unscented Kalman filtering, and particle filters
arXiv:2606.09090v1 Announce Type: cross Abstract: Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.md, AGENTS.md, and .cursorrule
arXiv:2606.09495v1 Announce Type: new Abstract: Modern object detectors achieve strong performance on standard benchmarks, yet their robustness to contextual variation remains insufficiently understoo
arXiv:2507.01598v5 Announce Type: replace Abstract: Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical per
arXiv:2606.08584v1 Announce Type: new Abstract: Sparse coding provides a principled framework for signal representation by expressing an input as a linear combination of only a small number of basis f
arXiv:2511.11041v2 Announce Type: replace-cross Abstract: We find that current sentence-embedding models produce outputs with a consistent bias: every embedding e decomposes as ilde e + mu, where the