Knowledge catalogue
arXiv:2510.15313v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly applied to creative domains, yet their performance in classical Chinese poetry generation and evaluati
arXiv:2601.05019v2 Announce Type: replace-cross Abstract: Recent Large Reasoning Models trained via reinforcement learning exhibit a 'natural' alignment with human cognitive costs. However, we show th
I had a range of models 'build me a procedurally generated 3D simulation showing the evolution of a harbor town from 3000 BCE to 3000 AD' in one prompt. You can play the full gallery here: https://hg-
The Klein 9B Distilled is a distilled image generation model enabling sub-second image generation with text-to-image and image-to-image editing capabilities in a single unified model, designed for rea
Listening to startups like @InstalilyAI, @UnslothAI, @splinetool, @ollama, and more talk about how they're using Gemini and Gemma models in production. 🙌🚀 Can't wait for the @garrytan @demishassabis f
arXiv:2511.20697v4 Announce Type: replace-cross Abstract: Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of
arXiv:2604.21036v1 Announce Type: new Abstract: Text-to-image(T2I) models like Stable Diffusion and DALL-E have made generative AI widely accessible, yet recent studies reveal that these systems often
arXiv:2510.08465v2 Announce Type: replace-cross Abstract: Estimating how individual input variables affect the output of a black-box model is a central task in explainable machine learning. However, e
In this post, we'll explore how multimodal BioFMs work, showcase real-world applications in drug discovery and clinical development, and contextualize how AWS enables organizations to build and deploy
arXiv:2604.16902v2 Announce Type: replace Abstract: Native Omni-modal Large Language Models (OLLMs) have shifted from pipeline architectures to unified representation spaces. However, this native inte
By end of next year. End of year after for 16gb vram. Do folk really need more for most things? Not really. But just call the cloud models when you do. What's a reasonable timeline for a GPT 5.4/Opus
arXiv:2604.20370v1 Announce Type: new Abstract: Forecasting the life-cycle trajectory of a newly launched product is important for launch planning, resource allocation, and early risk assessment. This
arXiv:2604.19887v1 Announce Type: cross Abstract: Depression is one of the most prevalent and debilitating mental health conditions worldwide, frequently underdiagnosed and undertreated. The prolifera
arXiv:2511.06209v4 Announce Type: replace Abstract: LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve LLM performance by samplin
How close are models to building a perfect Slack clone with less than 50,000 of tokens? I feel like not that far... Claude Code spend had gotten to 10.95M runrate peak at SemiAnalysis But then Opus 4.
arXiv:2601.13240v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at general programming but struggle with domain-specific software development, necessitating domain special
arXiv:2604.20652v1 Announce Type: new Abstract: Large language models trained on human feedback may suppress fraud warnings when investors arrive already persuaded of a fraudulent opportunity. We test
arXiv:2604.20143v1 Announce Type: cross Abstract: This is our fourth work in the series on machine learning (ML) moment closure models for the radiative transfer equation (RTE). In the first three pap
arXiv:2604.20467v1 Announce Type: cross Abstract: Artificial Intelligence (AI) weather models are improving rapidly, and their forecasts are already competitive with long-established traditional Numer
arXiv:2604.20366v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability.
arXiv:2604.19791v1 Announce Type: new Abstract: Attitude change - the process by which individuals revise their evaluative stances - has been explained by a set of influential but competing verbal the
arXiv:2604.20293v1 Announce Type: new Abstract: The increasing adoption of synthetic data in aviation research offers a promising solution to data scarcity and confidentiality challenges. This study i
arXiv:2604.20225v1 Announce Type: new Abstract: Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current bench
arXiv:2507.21166v2 Announce Type: replace-cross Abstract: Human intelligence scales through cumulative cultural evolution (CCE), a ratchet process in which innovations are retained against entropic dr
arXiv:2604.20151v1 Announce Type: cross Abstract: Autonomous mechanical thrombectomy (MT) presents substantial challenges due to highly variable vascular geometries and the requirements for accurate,
arXiv:2602.12755v2 Announce Type: replace Abstract: Diffusion-based image generators are promising priors for ill-posed inverse problems like sparse-view X-ray Computed Tomography (CT). As most studie
arXiv:2604.18612v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thou
All of the AI models have preferred names. If you asked Claude 4.5 for a software developer, you are going to get Marcus Chen. Wizards are mostly named Aldric. Space pilots are Kira from Claude, Mara
arXiv:2509.26238v4 Announce Type: replace Abstract: Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, tra
arXiv:2603.16497v2 Announce Type: replace-cross Abstract: Time series foundation models (TSFMs) require diverse, real-world datasets to adapt across varying domains and temporal frequencies. However,
arXiv:2505.16968v4 Announce Type: replace-cross Abstract: Cross-architecture GPU code transpilation is essential for unlocking low-level hardware portability, yet no scalable solution exists. We intro
arXiv:2604.19323v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) route predictions exclusively through a clinically grounded concept layer, binding interpretability to concept-label
arXiv:2604.19135v1 Announce Type: new Abstract: This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-bas
arXiv:2604.18829v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved impressive performance on visual perception and reasoning tasks with RGB imagery, yet they remain
arXiv:2604.19357v1 Announce Type: new Abstract: The evaluation of machine learning models typically relies mainly on performance metrics based on loss functions, which risk to overlook changes in perf
arXiv:2604.18867v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their
arXiv:2510.08564v2 Announce Type: replace Abstract: How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills wh
arXiv:2604.19673v1 Announce Type: new Abstract: Training embodied agents to understand 3D scenes as humans do requires large-scale data of people meaningfully interacting with diverse environments, ye
arXiv:2604.19167v1 Announce Type: cross Abstract: Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBL
arXiv:2604.19087v1 Announce Type: new Abstract: We introduce Options LLM (OLLM), a simple, general method that replaces the single next-token prediction of standard LLMs with a extit{set of learned op
arXiv:2502.16161v2 Announce Type: replace-cross Abstract: Visually-situated text parsing (VsTP) has recently seen notable advancements, driven by the growing demand for automated document understandin
arXiv:2602.05437v2 Announce Type: replace Abstract: Vision-language models (VLMs) can achieve high accuracy while still accepting culturally plausible but visually incorrect interpretations. Existing
Presumably GPT-imagegen-2 (aka ChatGPT Images 2.0 aka gpt-image-2) works as a tool which the models generate prompts for? I wish we could see those prompts, like back in the DALL-E 3 days https://simo
arXiv:2604.00161v2 Announce Type: replace Abstract: Optical Character Recognition (OCR) is increasingly regarded as a foundational capability for modern vision-language models (VLMs), enabling them no
arXiv:2604.18995v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. Ho
arXiv:2604.19299v1 Announce Type: cross Abstract: Despite the impressive capabilities of large language models, their substantial computational costs, latency, and privacy risks hinder their widesprea
arXiv:2604.19639v1 Announce Type: cross Abstract: Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner mu
arXiv:2604.19295v1 Announce Type: new Abstract: Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the r
arXiv:2603.04545v2 Announce Type: replace Abstract: Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference qu
arXiv:2509.15974v2 Announce Type: replace Abstract: Fine-tuning the bias terms of large language models (LLMs) has the potential to achieve unprecedented parameter efficiency while maintaining competi
arXiv:2601.05543v2 Announce Type: replace Abstract: Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on s
arXiv:2511.02757v2 Announce Type: replace Abstract: Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the
arXiv:2604.17988v1 Announce Type: new Abstract: Background: The potential of large language models (LLMs) to automate and support pharmacoepidemiologic study design is an emerging area of interest, ye
arXiv:2604.16481v1 Announce Type: new Abstract: Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable
arXiv:2410.04509v3 Announce Type: replace Abstract: As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particular
arXiv:2505.15353v3 Announce Type: replace Abstract: Log-likelihood vectors define a common space for comparing language models as probability distributions, enabling unified comparisons across heterog
arXiv:2604.17241v1 Announce Type: new Abstract: Implicit spatial relations and deep semantic structures encoded in object attributes are crucial for procedural planning in embodied AI systems. However
arXiv:2510.06700v3 Announce Type: replace Abstract: Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning proble
arXiv:2505.15404v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enha
arXiv:2604.16714v1 Announce Type: new Abstract: Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance