Knowledge catalogue
arXiv:2604.12911v1 Announce Type: cross Abstract: Multilingual benchmarks guide the development of frontier models. Yet multilingual evaluations reported by frontier models are structured similar to p
arXiv:2603.07436v2 Announce Type: replace Abstract: Training-free one-shot segmentation offers a scalable alternative to expert annotations where knowledge is often transferred from support images and
arXiv:2509.18127v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, un
arXiv:2411.19392v3 Announce Type: replace Abstract: Most Graph Neural Networks (GNNs) operate at the first-order scale, even though multi-scale representations are known to be crucial in domains such
arXiv:2604.12502v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost
arXiv:2510.10073v2 Announce Type: replace-cross Abstract: Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed
arXiv:2604.13019v1 Announce Type: new Abstract: Computer Use Agents (CUAs) fundamentally rely on graphical user interface (GUI) grounding to translate language instructions into executable screen acti
arXiv:2509.26404v2 Announce Type: replace-cross Abstract: Fingerprinting Large Language Models (LLMs)is essential for provenance verification and model attribution. Existing fingerprinting methods are
arXiv:2604.12322v1 Announce Type: new Abstract: The push for efficient text to image synthesis has moved the field toward one step sampling, yet existing methods still face a three way tradeoff among
arXiv:2604.11914v1 Announce Type: new Abstract: Self-monitoring capabilities -- metacognition, self-prediction, and subjective duration -- are often proposed as useful additions to reinforcement learn
arXiv:2505.18646v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenge
arXiv:2603.01045v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agen
arXiv:2410.01473v2 Announce Type: replace Abstract: Soil sinkholes significantly influence soil degradation, infrastructure vulnerability, and landscape evolution. However, their irregular shapes, com
arXiv:2604.12040v1 Announce Type: cross Abstract: We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic in
arXiv:2506.14512v4 Announce Type: replace Abstract: Large Language Models (LLMs) have undergone rapid progress, largely attributed to reinforcement learning on complex reasoning tasks. In contrast, wh
arXiv:2604.12245v1 Announce Type: cross Abstract: Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications.
The US Space Force is reassessing its launch strategy following repeated technical malfunctions experienced by ULA's Vulcan rocket, particularly issues with its solid boosters. These reliability conce
SpaceX is moving at literal light speed right now SpaceX launched 2 more Falcon 9s in under 24 hours AGAIN - Florida in the morning, California at night Even with unlimited budgets, government space p
arXiv:2603.23998v2 Announce Type: replace Abstract: Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive
arXiv:2511.22039v3 Announce Type: replace Abstract: This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on
arXiv:2604.12102v1 Announce Type: new Abstract: We introduce compute-grounded reasoning (CGR), a design paradigm for spatial-aware research agents in which every answerable sub-problem is resolved by
Lauren Forristal / TechCrunch: Spotify launches a feature to buy physical books in the US and UK, powered by Bookshop.org, and expands its Page Match tool to support 30 additional languages — In Febru
Starlink, SpaceX's satellite internet service, has been praised for delivering superior connectivity compared to competing options, including in-flight internet services on commercial aircraft. The se
arXiv:2604.03136v4 Announce Type: replace Abstract: As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluate
arXiv:2604.12257v1 Announce Type: new Abstract: Underwater Image Enhancement (UIE) is essential for robust visual perception in marine applications. However, existing methods predominantly rely on uni
arXiv:2309.13904v3 Announce Type: replace Abstract: Unsupervised anomaly localization aims to identify anomalous regions that deviate from normal sample patterns. Most recent methods perform feature m
arXiv:2512.09664v2 Announce Type: replace-cross Abstract: We describe SynthPix, a synthetic image generator for Particle Image Velocimetry (PIV) with a focus on performance and parallelism on accelera
arXiv:2604.12481v1 Announce Type: new Abstract: Text-to-image (T2I) generative models achieve impressive visual fidelity but inherit and amplify demographic imbalances and cultural biases embedded in
arXiv:2604.12891v1 Announce Type: new Abstract: Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on
arXiv:2509.03234v2 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), have significantly reduced the number of trainable parameters ne
Tesla has just released a new app update. Clips downloaded to your phone now finally include details such as speed, steering wheel angle, and Self-Driving state. No more screen recording FSD clips! He
Google's Gemini 3.1 Flash TTS (text-to-speech) model includes a notably elaborate or extensive example prompt, which Simon Willison highlighted as noteworthy. The post likely comments on the complexit
arXiv:2604.11978v1 Announce Type: new Abstract: Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, in
OpenAI's Agents SDK represents an evolution of their framework for building agentic AI applications, providing developers with tools to create, orchestrate, and deploy AI agents that can perform multi
arXiv:2604.12951v1 Announce Type: new Abstract: The most cited calibration result in deep learning -- post-temperature-scaling ECE of 0.012 on CIFAR-100 (Guo et al., 2017) -- is below the statistical
This is becoming a pattern in AI that makes talking about capabilities challenging. First, there are overstated claims (like the flubbed Erdos problems last year), then minor wins (AI helps with disco
arXiv:2604.12231v1 Announce Type: new Abstract: Large language models (LLMs) have transformed AI research thanks to their powerful internal capabilities and knowledge. However, existing LLMs still fai
arXiv:2604.12012v1 Announce Type: new Abstract: Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classificat
Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to g
arXiv:2509.07177v3 Announce Type: replace Abstract: Large language models have demonstrated impressive capabilities across various domains. However, their general-purpose nature often limits their eff
arXiv:2604.12890v1 Announce Type: cross Abstract: Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, mana
arXiv:2604.12321v1 Announce Type: new Abstract: Existing Chinese toxic content detection methods mainly target sentence-level classification but often fail to provide readable and contiguous toxic evi
arXiv:2604.12717v1 Announce Type: new Abstract: LLM-based autonomous agents perform well on general reasoning tasks but still struggle to reliably use task structure, key constraints, and prior experi
arXiv:2604.12733v1 Announce Type: cross Abstract: In recent years, Sound AI is being increasingly used to predict machine failures. By attaching a microphone to the machine of interest, one can get re
arXiv:2604.12610v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. Howe
arXiv:2604.12909v1 Announce Type: new Abstract: As reinforcement learning for humanoid robots evolves from single-task to multi-skill paradigms, efficiently expanding new skills while avoiding catastr
arXiv:2604.12026v1 Announce Type: new Abstract: Predicting the functional impact of single amino acid substitutions (SAVs) is central to understanding genetic disease and engineering therapeutic prote
arXiv:2604.12184v1 Announce Type: new Abstract: TRUST Agents is a collaborative multi-agent framework for explainable fact verification and fake news detection. Rather than treating verification as a
arXiv:2601.09313v2 Announce Type: replace-cross Abstract: Language models perform well on grammatical agreement, but it is unclear whether this reflects rule-based generalization or memorization. We s
arXiv:2604.12744v1 Announce Type: new Abstract: While multilingual language models promise to bring the benefits of LLMs to speakers of many languages, gold-standard evaluation benchmarks in most lang
arXiv:2604.12346v1 Announce Type: new Abstract: Spatio-temporal video grounding (STVG) aims to localize queried objects within dynamic video segments. Prevailing fully-trained approaches are notorious
arXiv:2604.11913v1 Announce Type: new Abstract: Nutrition estimation of meals from visual data is an important problem for dietary monitoring and computational health, but existing approaches largely
arXiv:2509.17995v2 Announce Type: replace-cross Abstract: Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems acro
arXiv:2512.06443v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed
arXiv:2604.13029v1 Announce Type: cross Abstract: The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal ta
arXiv:2604.12831v1 Announce Type: new Abstract: Indoor fire disasters pose severe challenges to autonomous search and rescue due to dense smoke, high temperatures, and dynamically evolving indoor envi
arXiv:2604.12540v1 Announce Type: cross Abstract: Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods -- LLM-based generation (Gemini 2.5
arXiv:2604.11840v1 Announce Type: new Abstract: Large language models are increasingly used as agents in social, economic, and policy simulations. A common assumption is that stronger reasoning should
arXiv:2604.12128v1 Announce Type: new Abstract: We investigate how self-referential inputs alter the internal matrix dynamics of large language models. Measuring 106 scalar metrics across up to 7 anal
arXiv:2604.05818v2 Announce Type: replace-cross Abstract: Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-