Knowledge catalogue
Learn the architecture and design decisions behind an explainable next-best-product recommendation system for banking, built with Amazon SageMaker AI and PyTorch. A multi-tower neural network with lea
arXiv:2607.21076v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) require huge memory and computational costs, which limits their practical deployment. Post-training quantizatio
arXiv:2512.12086v2 Announce Type: replace Abstract: Data obfuscation is a promising technique for mitigating attribute inference attacks by semi-trusted parties with access to time-series data emitted
arXiv:2607.20530v1 Announce Type: cross Abstract: Semi-supervised anomaly detection plays a key role in diverse fields such as process monitoring, healthcare, and finance. However, lightweight methods
arXiv:2607.21219v1 Announce Type: new Abstract: Archival film restoration is a challenging problem because historical footage contains compound degradations such as scratches, dust, blur, noise, flick
arXiv:2509.03922v2 Announce Type: replace Abstract: Multiview video is a key format for 3D applications such as free-viewpoint broadcasting and virtual reality, yet its large data volume poses signifi
arXiv:2607.21529v1 Announce Type: cross Abstract: Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, there exists a foundational misma
arXiv:2607.20771v1 Announce Type: cross Abstract: We consider the problem of learning compositional robot policies end-to-end from expert demonstrations, without any pre-specified notion of task decom
arXiv:2509.21913v2 Announce Type: replace-cross Abstract: Background: Cone-beam computed tomography CBCT is a commonly used modality for image guided radiotherapy. It offers real time anatomical visua
arXiv:2603.26863v2 Announce Type: replace-cross Abstract: Answer Set Programming (ASP) is a declarative programming language used for modeling and solving complex combinatorial problems. It has been s
arXiv:2511.05611v2 Announce Type: replace Abstract: The core challenge in Action Quality Assessment (AQA) lies in extracting fine-grained motion features from redundant and complex video backgrounds.
I copy-pasted this cooking recipe and accidentally hit enter before adding the actual prompt. Normally this would result in ChatGPT interpreting the text, trying to guess what I need, and giving a wal
arXiv:2603.22216v2 Announce Type: replace Abstract: The slow, sequential nature of autoregressive (AR) language models has driven the adoption of parallel decoding methods. However, these non-AR model
arXiv:2607.20539v1 Announce Type: cross Abstract: While deep learning has accelerated drug discovery, its impact on biomanufacturing has been considerably more limited. The reason is data scarcity. Bi
arXiv:2607.20734v1 Announce Type: new Abstract: As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet g
arXiv:2607.21343v1 Announce Type: cross Abstract: Integrating heterogeneous biomedical data, including clinical metadata, histopathology images, and molecular profiles, is crucial for comprehensive di
arXiv:2607.20585v1 Announce Type: cross Abstract: Sample-based Quantum Diagonalization (SQD), an extension of Quantum Selected Configuration Interaction (QSCI), has emerged as a promising hybrid quant
arXiv:2607.20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermar
arXiv:2601.20174v3 Announce Type: replace-cross Abstract: Solving large-scale sparse linear systems originating from partial differential equations (PDEs) is a fundamental topic in high-performance sc
arXiv:2607.21067v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. H
arXiv:2607.19054v2 Announce Type: replace Abstract: In this work, we incorporate first principle physics into the construction of data-driven methods by considering a model that accounts for the diffe
arXiv:2607.21347v1 Announce Type: new Abstract: Conventional face recognition relies on static appearance cues and degrades in unconstrained settings with expression variation, occlusion, and poor lig
arXiv:2607.20445v1 Announce Type: new Abstract: In conversations, human emotions are transient; however, they tend to persist across multiple utterances. For example, we rarely switch instantly betwee
arXiv:2603.06642v2 Announce Type: replace-cross Abstract: Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering
arXiv:2510.24616v4 Announce Type: replace-cross Abstract: For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capac
arXiv:2607.20592v1 Announce Type: new Abstract: Spatio-temporal machine-learning modelling is an important tool in environmental research. However, machine-learning models are highly sensitive to both
Even if China was distilling from US models (assuming all accusations are true), nothing about it makes it illegal. It is like saying you distilled knowledge from your professor in colleges and now he
True story: About 10 years ago there was a long article (NYT maybe?) about the end of trucking, estimating that automating truck driving will wipe out something like 1%-2% of the GPD because a surpris
arXiv:2607.21542v1 Announce Type: new Abstract: We propose a new approach to two-sample testing for deciding whether two sets of samples are drawn from the same distribution. The test is built on a st
arXiv:2607.19086v1 Announce Type: new Abstract: Multimodal fusion learning (MFL) has shown great potential in the medical domain, where we are faced with disparate data modalities such as imaging, cli
arXiv:2607.20057v1 Announce Type: cross Abstract: Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein langua
arXiv:2607.19415v1 Announce Type: cross Abstract: High-content morphological profiling (Cell Painting) yields sensitive, high-dimensional signatures of cellular state, but translating longitudinal mor
arXiv:2607.19843v1 Announce Type: cross Abstract: Large language models (LLMs) have made automated program repair (APR) increasingly practical for real-world bugs, but repairing directly from bug repo
This post shows you how to build multi-Region carrier performance dashboards in Quick Sight using Highcharts custom visualizations to overcome native chart limitations. You will learn how to maintain
Together, Motorway and AWS built an end-to-end evaluation pipeline that reduced incorrect results from 1 in 8 queries to 1 in 50 and cut issue detection time from few hours to few minutes. The pipelin
arXiv:2607.19659v1 Announce Type: new Abstract: Time-series foundation models can forecast across heterogeneous domains without task-specific training, but their forecasts are fixed once produced and
arXiv:2607.19765v1 Announce Type: new Abstract: Large view synthesis models synthesize novel views through cross-view attention without explicit 3D representations, and recent studies have shown that
arXiv:2607.20022v1 Announce Type: new Abstract: Difference constraints of the form x - y leq d are well studied, with efficient algorithms for satisfaction and implication, because of their connection
arXiv:2607.19362v1 Announce Type: new Abstract: Graph RAG mitigates hallucinations and stale knowledge in LLMs, particularly for multi-hop question answering. However, existing approaches remain highl
arXiv:2607.20173v1 Announce Type: new Abstract: Imbalanced regression problems arise when the target variable has an asymmetric distribution, resulting in underrepresented value ranges in the dataset.
arXiv:2607.20339v1 Announce Type: new Abstract: Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformati
arXiv:2607.19000v1 Announce Type: new Abstract: Change detection aims to identify semantic changes between remote sensing images. However, features from models are easily disturbed by non-semantic var
arXiv:2607.19718v1 Announce Type: new Abstract: The HIPE-2026 shared task introduces person-place relation extraction from multilingual historical newspapers as a new evaluation track, classifying the
arXiv:2607.19365v1 Announce Type: new Abstract: When Large Language Models (LLMs) are used for semantic data extraction from unstructured text, producing candidate relational facts from natural langua
arXiv:2607.20357v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost,
arXiv:2607.19388v1 Announce Type: new Abstract: This work extends our one-dimensional single-sweep neural-operator studies to two dimensions. We consider one-group transport with isotropic scattering.
arXiv:2607.17718v2 Announce Type: replace Abstract: Volumetric segmentation of optical coherence tomography (OCT) images is essential for diagnosing ocular diseases but requires labor-intensive voxel-
arXiv:2607.20163v1 Announce Type: cross Abstract: The rapid growth of biomedical knowledge has made the validation of automatically generated biological annotations a major bottleneck in biomedical cu
arXiv:2607.19604v1 Announce Type: new Abstract: Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solutio
arXiv:2607.19620v1 Announce Type: cross Abstract: In this paper, we present SCPP (Soft Clustering Python Package), an open-source Python framework for soft clustering. SCPP establishes a canonical, sc
arXiv:2607.18990v1 Announce Type: new Abstract: SWITi is a test-time method for reducing artifacts in tiled predictions, particularly for neural networks that learn posterior distributions from which
arXiv:2607.18762v1 Announce Type: new Abstract: We propose a weakly supervised 18FFDG PET representation-learning framework for content based medical image retrieval, using H&E derived information dur
4yr throwback. feels like a long time ago! Training a language model from scratch and watching it learn to speak, then learn concepts, then learn to think, feels so completely different from using an
Are structured outputs in agents always good? This paper suggests that you might have to take a closer look. Your product's structured output surface is measurably more homogeneous than the chat surfa
The LangChain team has built some nice LangSmith tracing/observability integrations with voice AI orchestration frameworks and the speech-to-speech APIs from OpenAI and Google. LangChain pioneered a l
Canvases turn AI into interactive workspaces where you can visualize information, explore workflows, and take action across complex tasks. The post How to build interactive experiences with canvases a
My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me f
native integrations for four leading voice frameworks so you can see whats happening dont fly blind Voice agents are exploding. Don’t let them be a black box in production. Today, we’re launching Lang
Voice agents are exploding. Don’t let them be a black box in production. Today, we’re launching LangSmith tracing for 4 voice frameworks: 🎙️ @pipecat_ai 🎙️ @livekit 🎙️ @OpenAI Realtime 🎙️ @GeminiApp L
We had guessed reward seeking might increase over the course of capabilities-focused RL training, but had no way of measuring it until now. We’re continuing to collaborate with Apollo Research to impr