Knowledge catalogue
arXiv:2604.06832v2 Announce Type: replace Abstract: Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference
arXiv:2604.08903v1 Announce Type: new Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromati
arXiv:2604.09063v1 Announce Type: cross Abstract: Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiven
arXiv:2604.04089v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate code rapidly but remain unreliable for scientific algorithms whose correctness depends on structural
arXiv:2506.04676v2 Announce Type: replace-cross Abstract: The data scarcity, label noise, and long-tailed category imbalance remain important and unresolved challenges in many computer vision tasks, s
arXiv:2604.08896v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have accelerated progress in domain-oriented AI, yet their development in geoscience and rem
arXiv:2604.08553v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong performance on text-attributed graphs (TAGs) due to their superior semantic understanding ability on te
arXiv:2604.08877v1 Announce Type: new Abstract: In this paper, we study the text-based person search, which is to retrieve the person of interest via natural language description. Prevailing methods u
arXiv:2604.08872v1 Announce Type: new Abstract: Many language tasks can be modeled as classification problems where a large language model (LLM) is given a prompt and selects one among many possible a
arXiv:2604.09389v1 Announce Type: cross Abstract: Training Transformer language models is expensive, as performance typically improves with increasing dataset size and computational budget. Although s
arXiv:2604.08636v1 Announce Type: cross Abstract: Designing robot morphologies and kinematics has traditionally relied on human intuition, with little systematic foundation. Motion-design co-optimizat
Let me break down exactly how long it takes me to teach people AI agents. ⏱️Give business professionals their first big wow moment in under 2 minutes ⏱️Teach them meaningful use in under 17 ⏱️Teach th
arXiv:2509.24164v2 Announce Type: replace Abstract: We investigate the mechanistic underpinnings of in-context learning (ICL) in large language models by reconciling two dominant perspectives: the com
arXiv:2604.08980v1 Announce Type: cross Abstract: Graph neural networks (GNNs) have been widely adopted in engineering applications such as social network analysis, chemical research and computer visi
arXiv:2604.09258v1 Announce Type: new Abstract: Pretraining is the cornerstone of Large Language Models (LLMs), dominating the vast majority of computational budget and data to serve as the primary en
arXiv:2604.09072v1 Announce Type: new Abstract: Humans effortlessly navigate the physical world by predicting how objects behave under gravity and contact forces, yet how such judgments support sequen
arXiv:2506.17310v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) demonstrate strong performance across domains, their long-context capabilities are limited by transient neu
arXiv:2601.04884v2 Announce Type: replace Abstract: Executing a multi-agent plan can be challenging when an agent is delayed, because this typically creates conflicts with other agents. So, we need to
arXiv:2604.08685v1 Announce Type: new Abstract: Automated planning algorithms require an action model specifying the preconditions and effects of each action, but obtaining such a model is often hard.
arXiv:2512.07833v2 Announce Type: replace-cross Abstract: Humans do not just see attribute similarity -- we also see relational similarity. An apple is like a peach because both are reddish fruit, but
arXiv:2603.27979v2 Announce Type: replace Abstract: We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike gen
arXiv:2604.08764v1 Announce Type: new Abstract: Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inhere
arXiv:2604.09285v1 Announce Type: new Abstract: The development of Large Language Models (LLMs) has catalyzed automation in customer service, yet benchmarking their performance remains challenging. Ex
Natsuki Yamamoto / Nikkei Asia: Sources: SoftBank, Sony, Honda, and six other Japanese companies launch a new AI company to develop a 1T-parameter foundation model for “physical AI” by 2030 — TOKYO —
arXiv:2604.08620v1 Announce Type: cross Abstract: Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-differenc
arXiv:2604.08602v1 Announce Type: cross Abstract: Background: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills. Objectives: We developed a b
arXiv:2604.09519v1 Announce Type: new Abstract: World models have emerged as a unifying paradigm for learning latent dynamics, simulating counterfactual futures, and supporting planning under uncertai
arXiv:2604.09159v1 Announce Type: new Abstract: Maximum entropy reinforcement learning (MaxEnt RL) has become a standard framework for sequential decision making, yet its standard Gaussian policy para
arXiv:2508.06869v4 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) demonstrate exceptional performance in vision-language tasks, yet their processing of long videos is
arXiv:2604.09048v1 Announce Type: cross Abstract: While the large energy consumption of Large Language Models (LLMs) is recognized by the community, system operators lack guidance for energy-efficient
arXiv:2604.08958v1 Announce Type: cross Abstract: Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to
Each workflow in Thoth is a full LangGraph agent which can call subagents which themselves are LangGraph agents. Just describe what you want in plain English and it builds a full multi-step pipeline.
Nous Research shared a post describing the experience of discovering or first encountering Hermes, their fine-tuned large language model series. The post likely captures the excitement and impressions
Francois Chollet, AI researcher and creator of Keras, argues that good design is fundamentally an act of compression — distilling an enormous number of implementation decisions, constraints, and consi
I am a Web3 Ambassador at World Liberty Financial. There are 12 of us on the team page. 4 are named Trump. 3 are named Witkoff. The page calls us 'the passionate minds shaping the future of finance.'
arXiv:2501.16150v3 Announce Type: replace Abstract: Agents for computer use (ACUs) are an emerging class of systems capable of executing complex tasks on digital devices -- such as desktops, mobile ph
arXiv:2604.06327v1 Announce Type: cross Abstract: Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual
A playable, digital piano built with Gemma 4 E2B (2B). https://x.com/0xCVYH/status/2039929097141318129?s=20 Google lancou 'Agent Skills' junto com o Gemma 4 Um app Android onde voce importa skills e o
arXiv:2604.08050v1 Announce Type: new Abstract: In this study, we focus on video captioning by fully open multimodal large language models (MLLMs). The comprehension of visual sequences is challenging
arXiv:2604.08545v1 Announce Type: new Abstract: The advent of agentic multimodal models has empowered systems to actively interact with external environments. However, current agents suffer from a pro
arXiv:2503.03088v4 Announce Type: replace-cross Abstract: The Segment Anything Model (SAM) has revolutionized image and video segmentation with its powerful zero-shot capabilities. However, its massiv
arXiv:2604.08479v1 Announce Type: new Abstract: Recent research shows that greater numbers of people are turning to Large Language Models (LLMs) for emotional support, and that people rate LLM respons
arXiv:2604.07277v1 Announce Type: cross Abstract: Online reinforcement learning (RL) serves as an effective method for enhancing the capabilities of Android agents. However, guiding agents to learn th
arXiv:2604.07900v1 Announce Type: new Abstract: Industrial anomaly generation is a crucial method for alleviating the data scarcity problem in anomaly detection tasks. Most existing anomaly synthesis
arXiv:2604.07815v1 Announce Type: new Abstract: Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse att
arXiv:2509.23435v2 Announce Type: replace-cross Abstract: The creation of high-quality multimodal datasets remains fundamental for advancing role-playing capabilities in large language models (LLMs).
arXiv:2508.04691v2 Announce Type: replace-cross Abstract: As humans move toward collaborating with coordinated robot teams, understanding how these teams coordinate and fail is essential for building
In freeskiing and snowboarding, traditional video replay shows you what happened during a complex aerial maneuver, but it fails to explain the physics of how it was possible. At the speed of the sport
arXiv:2603.18019v2 Announce Type: replace Abstract: Do language model benchmarks actually measure what practitioners intend them to ? High-level metadata is too coarse to convey the granular reality o
arXiv:2604.08410v1 Announce Type: new Abstract: In unstructured environments, functional dexterous grasping calls for the tight integration of semantic understanding, precise 3D functional localizatio
arXiv:2604.08014v1 Announce Type: new Abstract: Spatio-Temporal Video Grounding requires jointly localizing target objects across both temporal and spatial dimensions based on natural language queries
arXiv:2604.07583v1 Announce Type: new Abstract: Real-world categorization is severely hampered by class imbalance because traditional ensembles favor majority classes, which lowers minority performanc
arXiv:2604.08523v1 Announce Type: new Abstract: AI agents may be able to automate your inbox, but can they automate other routine aspects of your life? Everyday online tasks offer a realistic yet unso
arXiv:2506.19420v2 Announce Type: replace Abstract: Multimodal sarcasm understanding is a high-order cognitive task. Although large language models (LLMs) have shown impressive performance on many dow
arXiv:2604.03836v2 Announce Type: replace-cross Abstract: Semantics are one of the primary sources of top-down preattentive information. Modern deep object detectors excel at extracting such valuable
arXiv:2603.20114v4 Announce Type: replace Abstract: We aim to examine the extent to which Large Language Models (LLMs) can 'talk much' about grammar modules, providing evidence from syntax core proper
arXiv:2510.20549v2 Announce Type: replace Abstract: Despite advancements in SLAM technologies, robust operation under challenging conditions such as low-texture, motion-blur, or challenging lighting r
arXiv:2508.19982v5 Announce Type: replace Abstract: Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, offering parallel sequence generation and fle
arXiv:2604.06491v1 Announce Type: cross Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matchi
arXiv:2602.13669v4 Announce Type: replace Abstract: Recent multi-modal video generation models have achieved high visual quality, but their prohibitive latency and limited temporal stability hinder re