Knowledge catalogue
arXiv:2604.13071v1 Announce Type: new Abstract: We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Int
arXiv:2604.13426v1 Announce Type: new Abstract: Existing Vision Mamba-based RGB-Event(RGBE) tracking methods suffer from using static state transition matrices, which fail to adapt to variations in ev
arXiv:2604.13327v1 Announce Type: cross Abstract: Modern GPU workloads, especially large language model (LLM) inference, suffer from kernel launch overheads and coarse synchronization that limit inter
arXiv:2604.13533v1 Announce Type: cross Abstract: Achieving general-purpose robotics requires empowering robots to adapt and evolve based on their environment and feedback. Traditional methods face li
arXiv:2604.13279v1 Announce Type: new Abstract: Fall detection in elderly care requires not only accurate classification but also reliable explanations that clinicians can trust. However, existing pos
arXiv:2604.13050v1 Announce Type: cross Abstract: Urban areas are intricate systems shaped by socioeconomic, environmental, and infrastructural factors, with land use patterns serving as aspects of ur
arXiv:2601.06536v2 Announce Type: replace Abstract: We present Exposia, the first public dataset that connects writing and feedback in higher education, enabling research on educationally grounded com
arXiv:2601.08605v2 Announce Type: replace Abstract: Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insi
arXiv:2601.11329v3 Announce Type: replace Abstract: Spoken conversational systems require more than accurate speech generation to have human-like conversations: to feel natural and engaging, they must
arXiv:2604.13788v1 Announce Type: cross Abstract: Imitation learning (IL) policies in robotics deliver strong performance in controlled settings but remain brittle in real-world deployments: rare even
arXiv:2509.18847v3 Announce Type: replace-cross Abstract: Tool-augmented large language models (LLMs) are usually trained with supervised imitation or coarse-grained reinforcement learning that optimi
arXiv:2604.13453v1 Announce Type: new Abstract: Traffic forecasting requires modeling complex temporal dynamics and long-range spatial dependencies over large sensor networks. Existing methods typical
arXiv:2505.12600v3 Announce Type: replace-cross Abstract: We study the densest subgraph problem and its NP-hard densest at-most-k subgraph variant through the lens of learning-augmented algorithms. We
arXiv:2405.20836v3 Announce Type: replace-cross Abstract: Solving time-dependent Partial Differential Equations (PDEs) is one of the most critical problems in computational science. While Physics-Info
arXiv:2604.13191v1 Announce Type: cross Abstract: Many materials show anisotropic light scattering patterns due to the shape and local alignment of their underlying micro structures: surfaces with sma
arXiv:2508.05153v2 Announce Type: replace Abstract: Category-level generalization for robotic garment manipulation, such as bimanual smoothing, remains a significant hurdle due to high dimensionality,
arXiv:2604.14025v1 Announce Type: new Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and i
arXiv:2508.08791v3 Announce Type: replace Abstract: Effective tool use is essential for large language models (LLMs) to interact with their environment. However, progress is limited by the lack of eff
arXiv:2505.19662v3 Announce Type: replace-cross Abstract: This paper introduces FieldWorkArena, a benchmark for agentic AI targeting real-world field work. With the recent increase in demand for agent
arXiv:2509.16445v2 Announce Type: replace Abstract: Enabling robotic assistants to navigate complex environments and locate objects described in free-form language is a critical capability for real-wo
arXiv:2604.14035v1 Announce Type: new Abstract: Fairness in algorithmic decision-making is often defined in the predictive space, where predictive performance - used as a proxy for decision-maker (DM)
arXiv:2602.23636v3 Announce Type: replace Abstract: Ensuring the safety of LLM-generated content is essential for real-world deployment. Most existing guardrail models formulate moderation as a fixed
arXiv:2505.16051v4 Announce Type: replace-cross Abstract: Predicting potential and counterfactual outcomes from observational data is central to individualized decision-making, particularly in clinica
arXiv:2602.15472v4 Announce Type: replace-cross Abstract: We present a novel property-preserving kernel-based operator learning method for incompressible flows governed by the incompressible Navier--S
arXiv:2511.21760v3 Announce Type: replace Abstract: Recent advances in multimodal large language models (LLMs) have enabled unified reasoning across images, audio, and video, but extending such capabi
arXiv:2604.13592v1 Announce Type: new Abstract: Reasoning capabilities in large language models (LLMs) have generally advanced significantly. However, it is still challenging for existing reasoning-ba
arXiv:2604.13052v1 Announce Type: cross Abstract: Moltbook is a social network where every participant is an AI agent. We analyze 1,312,238 posts, 6.7~million comments, and over 120,000 agent profiles
arXiv:2604.14048v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test s
arXiv:2604.13540v1 Announce Type: new Abstract: Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable
arXiv:2604.13518v1 Announce Type: new Abstract: Self-supervised learning has emerged as a major technique for the task of learning from unlabeled data, where the current methods mostly revolve around
arXiv:2604.13777v1 Announce Type: new Abstract: Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has
arXiv:2604.14137v1 Announce Type: new Abstract: Evaluating LLMs is challenging, as benchmark scores often fail to capture models' real-world usefulness. Instead, users often rely on ``vibe-testing'':
arXiv:2601.21667v2 Announce Type: replace-cross Abstract: Current mobile manipulation research predominantly follows an instruction-driven paradigm, where agents rely on predefined textual commands to
arXiv:2604.13460v1 Announce Type: new Abstract: A central challenge in continual learning is forgetting, the loss of performance on previously learned tasks induced by sequential adaptation to new one
arXiv:2604.13667v1 Announce Type: new Abstract: DNA-based storage has emerged as a promising approach to the global data crisis, offering molecular-scale density and millennial-scale stability at low
arXiv:2603.19790v3 Announce Type: replace Abstract: Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We ident
arXiv:2604.13398v1 Announce Type: new Abstract: While Aspect-based Sentiment Analysis (ABSA) systems have achieved high accuracy in identifying sentiment polarities, they often operate as 'black boxes
arXiv:2604.14142v1 Announce Type: cross Abstract: While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM reasoning by optimizing the conditional distribution P(y|x), it
arXiv:2604.13468v1 Announce Type: cross Abstract: Generative information retrieval (GenIR) formulates the retrieval process as a text-to-text generation task, leveraging the vast knowledge of large la
arXiv:2604.13067v1 Announce Type: cross Abstract: SpeechLLMs process spoken language directly from audio, but accent and vocal identity cues can lead to biased behaviour. Current bias evaluations ofte
arXiv:2604.13793v1 Announce Type: new Abstract: Exo-to-Ego video generation aims to synthesize a first-person video from a synchronized third-person view and corresponding camera poses. While paired s
arXiv:2604.14090v1 Announce Type: new Abstract: Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficie
arXiv:2604.14053v1 Announce Type: new Abstract: Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves infe
arXiv:2507.13942v2 Announce Type: replace Abstract: Forecasting future events is a fundamental capability for general-purpose systems that plan or act across different levels of abstraction. Yet, eval
arXiv:2604.13466v1 Announce Type: cross Abstract: The Claude Mythos Preview system card deploys emotion vectors, sparse autoencoder (SAE) features, and activation verbalisers to study model internals
arXiv:2604.13803v1 Announce Type: new Abstract: Vision-language models are increasingly deployed in high-stakes settings, yet their susceptibility to sycophantic manipulation remains poorly understood
arXiv:2506.23640v2 Announce Type: replace-cross Abstract: Recently, researchers have explored ML-based Traffic Engineering (TE), leveraging neural networks to solve TE problems traditionally addressed
arXiv:2604.13130v1 Announce Type: new Abstract: We study learning to learn for regression problems through the lens of hyperparameter tuning. We propose the Langevin Gradient Descent Algorithm (LGD),
arXiv:2512.02697v3 Announce Type: replace Abstract: Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the trad
arXiv:2604.13183v1 Announce Type: new Abstract: Generalizable cross-view geo-localization aims to match the same location across views in unseen regions and conditions without GPS supervision. Its cor
arXiv:2604.14141v1 Announce Type: new Abstract: Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric acc
arXiv:2604.13248v1 Announce Type: new Abstract: Remote medical response systems are increasingly being deployed to support emergency care in disaster-affected and infrastructure-limited environments.
arXiv:2510.02213v2 Announce Type: replace Abstract: Density map estimation enables accurate object counting in heavily occluded, and densely packed scenes where detection-based counting fails. In mult
arXiv:2604.13288v1 Announce Type: new Abstract: We present a unified pipeline for synthesizing high-quality Quechua and Spanish speech for the Peruvian Constitution using three state-of-the-art text-t
arXiv:2604.13942v1 Announce Type: new Abstract: Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on
arXiv:2604.13609v1 Announce Type: new Abstract: Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand th
arXiv:2604.13870v1 Announce Type: cross Abstract: We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and
arXiv:2604.13722v1 Announce Type: new Abstract: We address the challenge of synthetic-to-real transfer in forestry perception where real data have only coarse Tree labels while synthetic data provide
arXiv:2603.12725v3 Announce Type: replace Abstract: In-context operator learning enables neural networks to infer solution operators from contextual examples without weight updates. While prior work h
arXiv:2604.13127v1 Announce Type: new Abstract: The need to selectively and efficiently erase learned information from deep neural networks is becoming increasingly important for privacy, regulatory c