Knowledge catalogue
arXiv:2512.20817v2 Announce Type: replace Abstract: Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility int
arXiv:2509.13281v5 Announce Type: replace Abstract: Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simpl
arXiv:2604.19648v1 Announce Type: cross Abstract: SAM3 advances open-vocabulary semantic segmentation by introducing a prompt-driven mask generation paradigm. However, in multi-class open-vocabulary s
arXiv:2604.14519v1 Announce Type: cross Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a ne
arXiv:2601.04567v2 Announce Type: replace Abstract: Harmful memes are ever-shifting in the Internet communities, which are difficult to analyze due to their type-shifting and temporal-evolving nature.
arXiv:2604.09988v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are widely used by engineers to solve difficult problems that require predictive modeling from data. However, these models
arXiv:2512.09056v3 Announce Type: replace Abstract: Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurr
arXiv:2604.07019v1 Announce Type: cross Abstract: Neural networks deliver impressive predictive performance across a variety of tasks, but they are often opaque in their decision-making processes. Des
arXiv:2610.06383v1 Announce Type: new Abstract: Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space
arXiv:2610.08132v1 Announce Type: cross Abstract: Concept drift threatens production machine learning, yet the empirical behavior of multivariate two-sample drift detectors at scale remains under-char
Reasoning from scratch, round number 5! This time, talking about log-probability scoring (also a great fundamental concept for loss functions like cross-entropy in pre-training and distillation) and s
arXiv:2609.11918v1 Announce Type: new Abstract: Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, id
arXiv:2609.09442v1 Announce Type: cross Abstract: In network traffic, legitimate behaviours and attack techniques evolve jointly - the phenomenon known as 'concept drift' [1]. Every detector is thereb
Here's a Blender model of a Pluribus themed Fabergé egg I had GPT-6 Astra build - I generated the concept image using ChatGPT Images 2.5, then pasted the image into Codex and told Astra to turn that i
arXiv:2602.19001v2 Announce Type: replace Abstract: As large language models increasingly power personal assistants, users expect them to reason over multimodal life histories, from recognizing people
arXiv:2608.19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain. Retraining is cos
arXiv:2608.15601v1 Announce Type: new Abstract: Compositional Concept Generalization (CoCoGen), the ability to systematically recombine learned primitives in novel contexts, is a key challenge for mul
arXiv:2608.16251v1 Announce Type: new Abstract: Face recognition templates are compact identity representations, yet they also encode rich semantic information about facial appearance. Prior work has
arXiv:2608.16812v1 Announce Type: new Abstract: Existing image editing frameworks predominantly follow the training paradigm of text-to-image diffusion models. However, extending this paradigm to imag
arXiv:2607.15142v2 Announce Type: replace Abstract: World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, leaving their standalone reliability understu
arXiv:2608.05743v1 Announce Type: new Abstract: Few-shot industrial anomaly detection (FS-IAD) focuses on detecting and localizing visual defects in industrial inspection during the cold-start phase,
arXiv:2608.01663v1 Announce Type: new Abstract: Promptable segmentation foundation models (FMs) such as SAM3 and Medical SAM3 promise few-shot, interactively-specified segmentation for medical imaging
Using optimization at inference time is a foundational concept of Energy-Based Models (EBM) and Objective-Driven AI architectures (ODAI). When the variables to be inferred are continuous, it makes sen
arXiv:2607.27763v1 Announce Type: new Abstract: We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with tw
I have question. I am trying to train a LORA, and my concept is for Indian wedding and tradional wardrobe based on Regions. I was planning to train a model which understand each region clothing style
Really interesting concept -- instead of optimizing against static benchmarks or internally generated reward models, agents are evaluated through real economic interactions. Using an external market a
arXiv:2607.12042v1 Announce Type: new Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation. Yet prevailing m
arXiv:2511.19636v2 Announce Type: replace-cross Abstract: In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on funda
arXiv:2607.04801v1 Announce Type: new Abstract: Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each s
arXiv:2602.17395v2 Announce Type: replace-cross Abstract: Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known clas
arXiv:2607.04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large
An AI system successfully created a functional demo game while reducing development costs, and is now advancing to develop an original first-person shooter concept with WebGL compatibility for browser
ai pickleball tournament was actually so good. they executed the concept perfectly. glad @MehulKalia_ and i showed up from Notion to see some familiar faces :) @braintrust @modal @browserbase @llama_i
arXiv:2606.30322v1 Announce Type: new Abstract: We propose a hybrid active-online learning framework for label-efficient concept drift adaptation in optical network failure detection. Using margin-bas
arXiv:2606.29888v1 Announce Type: cross Abstract: Vision-language models map images and text into a joint embedding space. However, these embeddings often entangle multiple semantic features, which li
arXiv:2606.25234v1 Announce Type: new Abstract: What is the geometry of a visual percept? The most widely used protocols for decomposing neural network representations into interpretable parts treat c
arXiv:2602.03448v2 Announce Type: replace Abstract: Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following text
A developer expanded on Andrej Karpathy's LLM Council concept by implementing an enhanced system with Docker containerization, Model Context Protocol (MCP) integration, skill modules, web search capab
arXiv:2606.10892v1 Announce Type: cross Abstract: To showcase products, merchants often incur substantial costs creating high-quality display images. Foreground Conditioned Outpainting (FCO) meets thi
arXiv:2606.09868v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial so
arXiv:2606.07789v1 Announce Type: new Abstract: Data stream mining is fundamentally challenged by concept drift, where distributional changes can degrade model performance. Despite the proliferation o
🚨This is how you turn a crash into a great depression. This is a public bailout of the worst bubble in history. “It’s a concept out there that’s so much money and it’s so big… where the American publi
NOTUS: Sources: US officials have held talks with AI companies about the government acquiring shares; Sam Altman first pitched the concept directly to Trump in 2025 — Senior U.S. officials have held p
arXiv:2606.03864v1 Announce Type: cross Abstract: We introduce an explainable machine-learning approach that forecasts the structural precursors of scientific breakthroughs -- the emergence and intens
Todd Bishop / GeekWire: Microsoft unveils Project Solara, an Android-based platform for agent-first devices, with concept hardware and pilots planned at Best Buy, Target, and others — [Editor's Note:
arXiv:2605.31591v1 Announce Type: new Abstract: Models for AI-based skin cancer screening suffer a severe performance drop when shifting from expert dermoscopic (source) images to consumer-grade clini
arXiv:2605.24294v1 Announce Type: cross Abstract: Android malware detectors often degrade after deployment because of concept drift, while full retraining at each maintenance step is costly. We propos
arXiv:2605.24903v1 Announce Type: cross Abstract: Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on ful
Love this concept. Always been a proponent of event-driven architectures, and the actor model. Neat to see how it’s applied to the agent runtime here. i'm excited to open source Active Graph: an event
the core concept is a graph that represents everything about the agents knowledge, history, behaviors, capabilities graph is made of events behaviors react to graph changes relationships can carry beh
arXiv:2605.11247v1 Announce Type: new Abstract: This paper presents a proof-of-concept digital twin framework for simulation-driven diabetes modeling using benchmark clinical data, synthetic temporal
How to create a 'miniature person' sequence with Seedance 2.0. This breakdown shows the process of adapting a skateboarding concept into a snowboarding scene inside a freezer using ComfyUI. Try the wo
arXiv:2604.26997v1 Announce Type: cross Abstract: Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance.
arXiv:2604.28119v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption
arXiv:2512.10955v2 Announce Type: replace Abstract: Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen conte
arXiv:2604.25376v1 Announce Type: new Abstract: Accurate brain lesion segmentation in MRI is vital for effective clinical diagnosis and treatment planning. Due to high annotation costs and strict data
arXiv:2604.22629v1 Announce Type: cross Abstract: This work proposes a structural approach to concept drift detection in malware classification using decision tree rulesets. Classifiers are trained ac
arXiv:2604.15967v1 Announce Type: cross Abstract: Despite the remarkable synthesis capabilities of text-to-image (T2I) models, safeguarding them against content violations remains a persistent challen
`citracer` is a small Python CLI tool available on PyPI that traces citation chains for any keyword across research papers, helping researchers identify where a concept originates in a citation gra...
arXiv:2610.12345v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially dif