Knowledge catalogue
arXiv:2609.23231v1 Announce Type: new Abstract: Cross-lingual information retrieval (CLIR) is increasingly important in multi-national industries, where critical technical evidence may exist in a diff
Claude Opus 5.5, Anthropic's most capable Opus model for agentic coding, knowledge work, and long-running tasks, is now available on Amazon Bedrock and Claude Platform on AWS. This post covers what's
arXiv:2609.22183v1 Announce Type: new Abstract: Public benchmark scores may reflect skill, prior exposure to the questions, or both, and for most models the training data are unknown. We present Clean
arXiv:2609.22752v1 Announce Type: new Abstract: Diffusion models have demonstrated strong power in generative modeling tasks across multiple domains, exhibiting a remarkable capability of learning com
arXiv:2609.22925v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a compelling foundation for reasoning-driven mobile navigation, offering rich contextual understanding and strong
It’s been a busy few months for AI hype. At the end of April, Anthropic claimed that its model Claude Mythos is better at finding software vulnerabilities than most security experts. Then we had the O
arXiv:2609.22271v1 Announce Type: new Abstract: Multimodal stroke recurrence prediction requires effective integration of heterogeneous clinical and imaging data, yet modality imbalance often causes m
arXiv:2609.23205v1 Announce Type: new Abstract: Reasoning language models are trained to produce solutions, not to refuse them, and this bias persists when the problem they are handed is false. Asked
arXiv:2505.16227v4 Announce Type: replace Abstract: Personalizing jargon detection and explanation is essential for making technical documents accessible to readers with diverse disciplinary backgroun
arXiv:2609.22188v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into AI-assisted hiring pipelines, including automated resume generation and screening. Under t
arXiv:2509.05259v2 Announce Type: replace Abstract: Automatic Generation Control (AGC) plays a critical role in maintaining power balance across multi-area power systems. However, its complete relianc
arXiv:2601.22033v2 Announce Type: replace Abstract: Holography, in the form of the anti-de Sitter/conformal field theory (AdS/CFT) correspondence, offers a natural setting for generative modelling. Da
arXiv:2609.24979v1 Announce Type: new Abstract: On-device large language models (`LLMs'), e.g. running on mobile phones, are ripe for improvement via personalization. The limited compute resources of
arXiv:2609.23371v1 Announce Type: new Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent i
arXiv:2609.24161v1 Announce Type: cross Abstract: As LLM agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet under
arXiv:2609.22778v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used as evaluators, yet their reliability in professional assessment tasks that require expert
arXiv:2609.23417v1 Announce Type: cross Abstract: Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor traject
arXiv:2609.24983v1 Announce Type: new Abstract: We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as i
arXiv:2609.24202v1 Announce Type: new Abstract: Sparse attention reduces the quadratic cost of global self-attention while retaining strong empirical performance, but how its restricted interactions s
People got upset at me for saying this, but there are no companies outside the US and China even *trying* to build frontier AI (perhaps Korea and UK are close), despite marketing claims. Governments s
Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to sup
arXiv:2609.24249v1 Announce Type: cross Abstract: Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small pertur
arXiv:2609.22478v1 Announce Type: cross Abstract: Behavioural evaluations of hosted language models can vary because the evaluated service, the measurement instrument, or both differ across runs. We s
arXiv:2609.22359v1 Announce Type: new Abstract: An aligned model asked to hold its answer against a manipulative source must still update on a reliable one and reject an unreliable one: resistance, re
arXiv:2609.22258v1 Announce Type: cross Abstract: Large language model-driven remote sensing (RS) agents offer a promising approach to automating geospatial analysis. However, lightweight RS agents ba
arXiv:2609.23290v1 Announce Type: cross Abstract: High-dimensional count data are common in scientific applications, but most diffusion and flow models are designed for continuous or categorical data,
arXiv:2609.22198v1 Announce Type: new Abstract: The rapid adoption of large language models (LLMs) creates new opportunities for strategic content generation on online platforms, including potentially
arXiv:2609.22195v1 Announce Type: new Abstract: Large language models can convincingly adopt personas, recall past dialogues, and weave rich autobiographies. Yet this conversational eloquence conceals
arXiv:2609.24635v1 Announce Type: new Abstract: When a language model reads an operation such as 'Swap the contents of Box F and Box B', its forward pass writes keys and values for those tokens into t
arXiv:2609.22043v1 Announce Type: new Abstract: Memory systems for large language models have focused predominantly on efficient retrieval, whereas the decision of whether retrieved memories should be
arXiv:2609.21340v1 Announce Type: cross Abstract: Empirical identity leakage from released text is increasingly driven by attackers that combine large language models (LLMs) with auxiliary knowledge t
arXiv:2609.21595v1 Announce Type: new Abstract: In-context learning using Large Language Models (LLMs) offers a compelling path to training-free post-OCR correction, yet its effectiveness for Devanaga
Demand for AI infrastructure is at an all-time high. Global accelerator shortages mean engineering teams can rarely get all the compute they need from just one data center — capacity comes a cluster h
arXiv:2609.21381v1 Announce Type: cross Abstract: We investigate whether coupling a time-series foundation model to hydraulic project knowledge improves surrogate forecasting of HEC-RAS water-surface
arXiv:2609.21870v1 Announce Type: cross Abstract: Modern deep learning models achieve impressive generalization through over-parameterization, but this paradigm often struggles with overfitting and me
arXiv:2609.21527v1 Announce Type: new Abstract: Graph-enhanced multi-agent systems (G-MAS) coordinate large language model agents through communication graphs and role assignments, which determine how
If anyone is interested in using Ollama with the Prism-ML model prism-ml/Bonsai-27B-gguf · Hugging Face I setup a repo with an install script that patches Ollama and pulls the Prism-LM llama.cpp code
arXiv:2609.21522v1 Announce Type: new Abstract: Recent pre-trained foundation models provide rich multi-modal priors for downstream 3D vision tasks. However, the effectiveness of these representations
Positron, Posit's IDE for data science, now runs on Amazon SageMaker AI. This post shows how a data scientist explores an Amazon Athena table, validates features in R, trains an XGBoost model in Pytho
arXiv:2609.21989v1 Announce Type: new Abstract: Latent flow models have proven to be a reliable and cost-effective method for time series generation. However, the latent compression induces unwanted a
xAI's Grok 4.6 is now available in Amazon Bedrock: a frontier model for long-running agents, coding, and knowledge work, with a 500K token context window and four reasoning effort levels. It runs on b
AGI FTW @ FT “The most popular AI models from ChatGPT, Claude, Copilot, Grok and Gemini provided wrong answers to financial queries 57 per cent of the time on average, according to research from techn
I got early access to Qwen-Image-2.1 My first impression: Fantastic editing, new standard for open models, support for a lot of references (I tested with 10), consistent, pixel precise at 2K, text ren
Qwen‑Image‑2.1, released by Alibaba’s Qwen team, is an image generation model that handles a broad spectrum of editing tasks while maintaining balanced performance across them. For instance, when prov
Sharing my successful experience here. My setup: RTX 5060 Ti 16GB (x16 PCIe slot) RTX 3060 12GB (x4 PCIe slot) RAM: 32GB CPU: Ryzen 5 5600 OS: Linux So I have a total of 28GB. Average tk/s: 50, and th
Now you understand why Dario is panicking. Only a fool would join his planned $2 trillion IPO. Looks like today may be a record day for token volume % of open models on Vercel AI Gateway: 🟦 Open 78.4%
Meet Inco Splash, open-source inference engine, built around the model and around Apple silicon. Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents. Req
arXiv:2603.02540v2 Announce Type: replace Abstract: Large language models (LLMs) display a unified 'general factor' of capability across 10 benchmarks (a finding confirmed by our factor analysis of 15
arXiv:2609.19180v1 Announce Type: new Abstract: Language models face unique challenges in analyzing interdisciplinary scientific research literature. In biophysics research, faithful answers require g
arXiv:2509.09121v2 Announce Type: replace Abstract: Large language models (LLMs) excel in general-domain applications, yet their performance often degrades in specialized tasks requiring domain-specif
I just released a new dataset https://huggingface.co/datasets/LocalLLaMA/deepswe-mini it is meant to be more efficent when testing and benchmarking local models on DeepSwe https://deepswe.datacurve.ai
arXiv:2609.20574v1 Announce Type: new Abstract: Answer grounding in document visual question answering remains an open challenge: most benchmarks lack grounding annotations or provide limited-quality
Engram Embedding Entendre is a model‑architecture optimization that extends standard token embeddings with learned multi‑token lookups, enabling recurring local patterns to be retrieved directly from
arXiv:2609.20814v1 Announce Type: cross Abstract: Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear
arXiv:2609.19213v1 Announce Type: cross Abstract: In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from
arXiv:2609.20068v1 Announce Type: new Abstract: This paper builds a theoretical bridge between the economic notion of marginal utility and two machine-learning constructs, matrix factorization and the
Hey community, Jovan from UkisAI here, We're the team behind Swift Qwen3.8 27B, the Qwen model with token usage and overthinking error improvements Our estimate is that we can make a great improvement
arXiv:2609.19149v1 Announce Type: new Abstract: Subliminal learning shows that language models can transmit a hidden trait through outputs that appear unrelated to it. One proposed explanation, token
arXiv:2609.20214v1 Announce Type: cross Abstract: Early transformer fault diagnosis is challenged by nonlinear dissolved-gas interactions, overlapping fault signatures, and limited labeled data, while
arXiv:2609.19554v1 Announce Type: cross Abstract: Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence,