Knowledge catalogue
arXiv:2605.20982v1 Announce Type: cross Abstract: AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations
arXiv:2605.12960v2 Announce Type: replace Abstract: Towards more general and human-like intelligence, large language models should seamlessly integrate both multilingual and multimodal capabilities; h
arXiv:2605.20856v1 Announce Type: cross Abstract: Language-conditioned manipulation policies typically process instructions and observations through shared network parameters. This task-state entangle
arXiv:2605.20689v1 Announce Type: new Abstract: High-dimensional embeddings from large language models impose significant storage and computational costs on vector search systems. Recent embedding com
arXiv:2605.21060v1 Announce Type: new Abstract: Accurate and well-calibrated Machine Learning (ML) models are mandatory in high-stakes settings, yet effective multiclass calibration remains challengin
arXiv:2605.21227v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for writing assistance in small contact languages, yet it is unclear whether they respect community n
arXiv:2605.20448v1 Announce Type: new Abstract: Vision--language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-c
arXiv:2605.21273v1 Announce Type: new Abstract: Driving Vision-Language-Action Models (Driving VLAs) commonly introduce natural-language reasoning as an intermediate interface for end-to-end planning,
arXiv:2512.14896v2 Announce Type: replace Abstract: In our study, we evaluated large language model (LLM) performance on pharmacy licensure-style question-answering tasks and developed an external kno
arXiv:2605.21042v1 Announce Type: new Abstract: Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due t
arXiv:2605.21028v1 Announce Type: new Abstract: Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity w
arXiv:2605.20490v1 Announce Type: cross Abstract: In high-stakes automated decision-making, access to predictive uncertainty is essential for enabling users -- human or downstream systems -- to accept
arXiv:2605.21213v1 Announce Type: cross Abstract: In this work, we present quantum reinforcement learning (RL) as a solution strategy for process synthesis problems. Building on our prior work, we dev
arXiv:2602.06511v3 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but design
arXiv:2601.18696v4 Announce Type: replace Abstract: Hardware trojans are malicious circuits which compromise the functionality and security of an integrated circuit (IC). These circuits are manufactur
arXiv:2603.08235v2 Announce Type: replace Abstract: Diabetic retinopathy (DR) and diabetic macular edema (DME) are leading causes of preventable blindness among working-age adults. Traditional approac
arXiv:2508.02291v3 Announce Type: replace Abstract: Structured pruning is a standard tool for compressing deep neural networks, but its practical performance depends on how sparsity is allocated acros
arXiv:2605.20256v1 Announce Type: new Abstract: Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training l
arXiv:2605.21264v1 Announce Type: new Abstract: Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving distributed learning. However, existing FL methods face a fundamental
arXiv:2605.21418v1 Announce Type: cross Abstract: In sixth-generation (6G) ultra-dense networks, aggressive frequency reuse amplifies inter-cell interference (ICI), making multi-cell orthogonal freque
Reuters: Federal records: Grok was utilized in only 3 of 400+ publicly identified federal AI use cases in 2025, behind 234 for ChatGPT, 33 for Gemini, 26 for Claude — SpaceX's initial public offering
arXiv:2605.21217v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has emerged as a powerful tool for parameter-efficient fine-tuning of large language models (LLMs). This paper studies LoRA
arXiv:2605.20965v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have shown remarkable performance on a wide range of vision-language tasks. Despite this progress, they are still p
arXiv:2605.20761v1 Announce Type: new Abstract: The rapid proliferation of AI-generated text has introduced significant challenges in maintaining the integrity of digital content. Advanced generative
arXiv:2605.21071v1 Announce Type: new Abstract: The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs
arXiv:2510.14737v3 Announce Type: replace Abstract: Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the
arXiv:2603.01712v2 Announce Type: replace-cross Abstract: Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, an
arXiv:2605.20316v1 Announce Type: new Abstract: Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified visi
arXiv:2602.10408v2 Announce Type: replace-cross Abstract: Normalization layers are standard in transformers, but it is not clear whether their sample-dependent computations are necessary throughout bo
arXiv:2605.20896v1 Announce Type: cross Abstract: Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft in
arXiv:2605.20241v1 Announce Type: cross Abstract: Prompt-level safety probes for large language models use hidden-state representations to separate safe from unsafe prompts, but strong average detecti
Google just revealed Omni, personalized cross-device intelligence, and Spark agents at I/O 2025. I sat down with CEO Sundar Pichai to figure out what comes next: 1:46 Omni: 'Nano Banana for video' 4:5
arXiv:2505.24275v3 Announce Type: replace Abstract: We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector g=(g_i)_
arXiv:2605.20815v1 Announce Type: new Abstract: Graph-based Retrieval Augmented Generation (GraphRAG) extends retrieval-augmented generation to support structured reasoning over complex corpora, but i
arXiv:2605.20440v1 Announce Type: new Abstract: We introduce the star_G tensor algebra, in which any finite group G defines the multiplication rule, making equivariance an intrinsic algebraic property
arXiv:2605.20744v1 Announce Type: new Abstract: Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby
arXiv:2605.20469v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible b
arXiv:2605.21266v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for reasoning in language models, with GRPO as its primary exam
arXiv:2605.20613v1 Announce Type: new Abstract: The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foun
Hugging Face just released LeRobot Humanoid An open-source, low-cost (~$2.5k), 3D-printed humanoid built for robot learning and not just demos. What’s cool is it’s a full stack release: • hardware + C
@huggingface's @LeRobotHF team announced LeRobot Humanoid, an open-source bipedal robot platform built for roughly $2,500 using mostly 3D-printed and off-the-shelf parts: The release provides complete
arXiv:2605.21133v1 Announce Type: new Abstract: In this paper, we explore spatial-aware humanoid whole-body manipulation task. Compared with tabletop settings, this task poses two key challenges: 1) S
arXiv:2605.21309v1 Announce Type: new Abstract: Cooperative perception enabled by Vehicle-to-Everything (V2X) communication enhances autonomous driving safety by creating a unified environmental repre
I released the first alpha of Datasette Agent - a conversational AI assistant for Datasette that can answer questions about data in SQLite databases, and can be extended with plugins to add extra tool
If this is true, using the best public estimates we have of LLM resource use, solving this Erdos problem took 0.6–6.3 kWh of electricity and about 3–31 liters of water. So that is less than three almo
arXiv:2605.20193v1 Announce Type: new Abstract: Quantized Large Language Models (LLMs) are used more often in qualitative analysis because they run fast and need fewer computing resources. This study
The next version of Claude Code will introduce a `/usage` command that provides a detailed breakdown of token consumption across different components including Skills, Agents, MCPs (Model Context Prot
arXiv:2508.08636v2 Announce Type: replace Abstract: Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities. While recent advancements in re
arXiv:2605.20904v1 Announce Type: new Abstract: We propose JFAA, a JEPA-based Future Action Anticipation method for the EPIC-KITCHENS-100 (EK-100) Action Anticipation task. Inspired by the representat
arXiv:2605.20960v1 Announce Type: new Abstract: This paper introduces JobArabi, a large-scale corpus of Arabic job announcements collected from social media between January 2024 and October 2025. The
arXiv:2605.20284v1 Announce Type: new Abstract: Industrial anomaly detection has been significantly advanced by Large Multimodal Models (LMMs), enabling diverse human instructions beyond detection, pa
arXiv:2506.16950v2 Announce Type: replace Abstract: Out-of-distribution (OOD) robustness is a desired property of computer vision models. Improving model robustness requires high-quality signals from
arXiv:2605.21235v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathemat
arXiv:2605.21292v1 Announce Type: cross Abstract: Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the fini
arXiv:2605.20244v1 Announce Type: cross Abstract: We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of L
arXiv:2605.20242v1 Announce Type: new Abstract: Efficient discovery of precursor additives is essential for improving the performance of perovskite solar cells, yet the large chemical space makes conv
arXiv:2605.20883v1 Announce Type: new Abstract: Dictionary learning is a powerful tool for creating interpretable representations. When applied to functional magnetic resonance imaging (fMRI) data, th
arXiv:2602.06025v2 Announce Type: replace Abstract: Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offl
arXiv:2603.14324v3 Announce Type: replace-cross Abstract: Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert
arXiv:2605.20667v1 Announce Type: new Abstract: Detecting small unmanned aerial vehicles from RGB-infrared remote-sensing pairs remains challenging due to tiny target scale, cluttered backgrounds, and