Knowledge catalogue
arXiv:2508.19679v2 Announce Type: replace Abstract: Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on hu
arXiv:2511.15197v2 Announce Type: replace Abstract: Reference-based object composition involves integrating foreground reference image with background scene to produce harmonious fused image. This tas
arXiv:2604.23095v1 Announce Type: new Abstract: Indoor environments lack the spatial intelligence infrastructure that GPS provides outdoors; first responders arriving at unfamiliar buildings typically
arXiv:2604.22861v1 Announce Type: cross Abstract: Scientific research relies on accurate information retrieval from literature to support analytical decisions. In this work, we introduce a new task, I
arXiv:2604.24114v1 Announce Type: new Abstract: Curriculum learning helps language models tackle complex reasoning by gradually increasing task difficulty. However, it often fails to generate consiste
I've been trying to make transformers more agent-friendly: agentic CLI, a skill, doc rewrites, canonical examples. It felt a bit like shooting in the dark: hard to measure progress, and hard to ensure
arXiv:2604.23178v1 Announce Type: new Abstract: LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluati
arXiv:2604.22779v1 Announce Type: cross Abstract: Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucination
arXiv:2602.17547v3 Announce Type: replace Abstract: This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model
arXiv:2506.19089v5 Announce Type: replace-cross Abstract: We introduce StorySim, a programmable framework for synthetically generating stories to evaluate the theory of mind (ToM) and world modeling (
arXiv:2509.06337v2 Announce Type: replace Abstract: Questionnaire-based surveys are foundational to social science research and public policymaking, yet traditional survey methods remain costly, time-
arXiv:2604.24293v1 Announce Type: cross Abstract: Graph neural ordinary differential equations (Graph ODEs) extend graph learning from discrete message-passing layers to continuous-time representation
arXiv:2604.23324v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have demonstrated impressive performance in learning representations from graph-structured data. However, their message-p
arXiv:2510.14978v2 Announce Type: replace Abstract: Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine
arXiv:2604.23314v1 Announce Type: new Abstract: Segmentation is central to clinical diagnosis and monitoring, yet the reliability of modern foundation models in medical imaging still depends on the av
arXiv:2604.23000v1 Announce Type: new Abstract: In behavioral cloning (BC), policy performance is fundamentally limited by demonstration data quality. Real-world datasets contain trajectories of varyi
arXiv:2209.14742v2 Announce Type: replace Abstract: To address distribution shifts between training and test data, domain generalization (DG) leverages multiple source domains to learn a model that ge
arXiv:2604.22770v1 Announce Type: cross Abstract: Most digital language learning curricula rely on discrete-item quizzes that test recall rather than applied conversational proficiency. When progressi
arXiv:2509.10546v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in finance, where unsafe behavior can lead to serious regulatory risks. However, most r
arXiv:2604.23604v1 Announce Type: new Abstract: Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previous
arXiv:2509.00084v2 Announce Type: replace-cross Abstract: Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting
arXiv:2604.24608v1 Announce Type: cross Abstract: Large Language Models (LLMs) have recently been explored as fine-grained zero-shot re-rankers by leveraging attention signals to estimate document rel
arXiv:2604.23809v1 Announce Type: new Abstract: Small language models (SLMs) are promising for real-world deployment due to their efficiency and low operational cost. However, their limited capacity s
arXiv:2603.24143v2 Announce Type: replace Abstract: Neural operator learning directly constructs the mapping relationship from the equation parameter space to the solution space, enabling efficient di
arXiv:2604.00829v3 Announce Type: replace-cross Abstract: Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representat
arXiv:2604.23970v1 Announce Type: new Abstract: Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-bu
arXiv:2603.14882v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) typically assume a uniform spatial fidelity across the entire field of view of visual inputs, dedicating equal precisi
arXiv:2603.03269v2 Announce Type: replace Abstract: Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadr
arXiv:2604.24620v1 Announce Type: new Abstract: Temporal relation classification is the task of determining the temporal relation between pairs of temporal entities in a text. Despite recent advanceme
arXiv:2604.23908v1 Announce Type: new Abstract: Short term electricity price forecast is essential in competitive power markets, yet electricity price series exhibit high volatility, irregularity, and
arXiv:2602.00981v2 Announce Type: replace-cross Abstract: Spoken question-answering (SQA) systems relying on automatic speech recognition (ASR) often struggle with accurately recognizing medical termi
arXiv:2604.24564v1 Announce Type: new Abstract: Multimodal Retrieval-Augmented Generation (MRAG) addresses key limitations of Multimodal Large Language Models (MLLMs), such as hallucination and outdat
arXiv:2604.24222v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal privat
arXiv:2604.24178v1 Announce Type: cross Abstract: Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives
arXiv:2604.24625v1 Announce Type: cross Abstract: Unified multi-modal understanding/generative models have shown improved image editing performance by incorporating fine-grained understanding into the
arXiv:2604.24096v1 Announce Type: cross Abstract: Training reliable respiratory sound classification models remains challenging due to the limited size and subject diversity of datasets. Ensemble meth
Tuna-2 is a unified multimodal model that performs visual understanding and generation directly based on pixel embeddings, employing simple patch embedding layers to encode visual input without a VAE
arXiv:2604.23289v1 Announce Type: cross Abstract: Due to the unprecedented success of deep learning, it has become an integral component in several multimedia computing applications in todays world. U
This post criticizes Microsoft's approach to integrating AI assistants into Outlook, expressing frustration that the AI chatbot has limited functionality and capabilities despite Microsoft's ownership
arXiv:2604.24374v1 Announce Type: new Abstract: Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Repr
arXiv:2604.24332v1 Announce Type: new Abstract: Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representatio
arXiv:2604.23053v1 Announce Type: new Abstract: Mixed Binary Quadratic Programs (MBQPs) are an important and complex set of problems in combinatorial optimization. As solving large-scale combinatorial
arXiv:2604.23107v1 Announce Type: cross Abstract: Causal effect estimation from observational data requires careful adjustment for confounding. Classical estimators such as inverse probability weighti
arXiv:2604.24328v1 Announce Type: new Abstract: Monocular depth estimation (MDE) has witnessed remarkable progress driven by Convolutional Neural Networks and transformer-based architectures. However,
arXiv:2604.23264v1 Announce Type: new Abstract: Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich i
arXiv:2604.23620v1 Announce Type: new Abstract: We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coa
arXiv:2604.24186v1 Announce Type: cross Abstract: Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While Large Language Models (LLMs) have shown strong capab
arXiv:2604.23733v1 Announce Type: new Abstract: Asking inquisitive questions while reading, and looking for their answers, is an important part in human discourse comprehension, curiosity, and creativ
arXiv:2604.24370v1 Announce Type: new Abstract: The shift from stand-level to individual-tree-level forest assessments supports improved biodiversity mapping, particularly in boreal ecosystems where t
arXiv:2511.10047v2 Announce Type: replace Abstract: Zero-shot anomaly classification (AC) and segmentation (AS) methods aim to identify and outline defects without using any labeled samples. In this p
arXiv:2604.24696v1 Announce Type: new Abstract: Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (
arXiv:2604.24337v1 Announce Type: cross Abstract: In this work, we extend the class of previously introduced non-Euclidean neural quantum states (NQS) which consists only of Poincare hyperbolic GRU, t
arXiv:2604.23106v1 Announce Type: cross Abstract: Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Ou
Now Available on Qdrant Cloud: GPU Indexing, Multi-AZ, and Audit Logging We’re excited to announce some Qdrand Cloud upgrades to address AI workloads that write continuously, must meet higher uptime S
arXiv:2412.04468v3 Announce Type: replace Abstract: Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention
arXiv:2506.05480v4 Announce Type: replace-cross Abstract: We introduce ODE-GS, a novel approach that integrates 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to enabl
arXiv:2509.20086v2 Announce Type: replace Abstract: Phonemization is a critical component in text-to-speech synthesis. Traditional approaches rely on deterministic transformations and lexica, while ne
arXiv:2604.24191v1 Announce Type: new Abstract: Omnimodal understanding entails a massive, highly redundant search space of cross-modal interactions, demanding focused and deliberative reasoning. Curr
arXiv:2510.01409v2 Announce Type: replace Abstract: System logs represent a valuable source of Cyber Threat Intelligence (CTI), capturing attacker behaviors, exploited vulnerabilities, and traces of m
Open Models & a potential looming Haiku-apocalypse? 🚀 chart comparison UI courtesy of @OpenRouter there's a large class of problems where you don't need frontier intelligence. you want cheap, fast, an