Knowledge catalogue
arXiv:2605.25846v1 Announce Type: new Abstract: Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-speci
arXiv:2605.24741v1 Announce Type: cross Abstract: We study the sample complexity of robust binary hypothesis testing under three standard contamination models: arepsilon-additive (Huber), arepsilon-su
arXiv:2605.24649v1 Announce Type: cross Abstract: Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as run
arXiv:2603.07523v2 Announce Type: replace Abstract: Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a p
arXiv:2509.25507v2 Announce Type: replace-cross Abstract: How can we generate samples from a conditional distribution that we never fully observe? This question arises across a broad range of applicat
arXiv:2601.21924v2 Announce Type: replace Abstract: We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where experience from related source tasks is available
arXiv:2605.25423v1 Announce Type: new Abstract: Autonomous exploration is critical for robot mapping unknown environments. Desirable characteristics of exploration algorithms include compute efficienc
arXiv:2605.23935v1 Announce Type: new Abstract: Autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime. Prior work
arXiv:2605.25663v1 Announce Type: new Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space wit
arXiv:2605.25888v1 Announce Type: new Abstract: We study how an e-commerce firm should make real-time fulfillment decisions in a two-layer distribution network when multi-item customer orders arrive s
arXiv:2605.25592v1 Announce Type: cross Abstract: We study optimal experimental design for multinomial logit (MNL) bandits, where an agent repeatedly selects a subset of K items from a ground set of s
arXiv:2605.24072v1 Announce Type: cross Abstract: Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanish
arXiv:2603.16481v2 Announce Type: replace Abstract: Non-conservative uncertainty bounds are essential for making reliable predictions about latent functions from noisy data, and thus, a key enabler fo
arXiv:2605.24261v1 Announce Type: new Abstract: A critical challenge facing clinicians managing chronic disease interventions is sustaining long-run patient health given limited information and resour
arXiv:2605.25124v1 Announce Type: new Abstract: The Gini Multidimensional Scaling (Gini MDS) framework extends the Euclidean multidimensional scaling. We introduce a Gini pseudo-distance based on valu
arXiv:2511.04556v2 Announce Type: replace Abstract: Urban flooding triggered by intense rainfall is becoming increasingly frequent and widespread. While flood prediction and monitoring in high spatio-
arXiv:2508.11925v3 Announce Type: replace-cross Abstract: Protecting intellectual property on LLM-generated code necessitates effective watermarking systems that can operate within code's highly struc
arXiv:2603.28128v2 Announce Type: replace Abstract: Although Graph Neural Networks (GNNs) have shown promise for smart contract vulnerability detection, they still face significant limitations. Homoge
arXiv:2605.26092v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and t
arXiv:2605.24969v1 Announce Type: cross Abstract: Long-tailed recognition suffers from a persistent head--tail trade-off: improving tail performance often degrades head accuracy and can increase train
arXiv:2605.24106v1 Announce Type: cross Abstract: Rapid and accurate flood extent mapping from Remote Sensing data, such as Synthetic Aperture Radar (SAR), is critical for operational disaster respons
arXiv:2605.24907v1 Announce Type: new Abstract: We present an overview of PsyDefDetect, the shared task on detecting levels of psychological defense mechanisms in emotional support dialogues, co-locat
arXiv:2605.25312v1 Announce Type: new Abstract: We introduce P1SCO, a dataset of social media comments collected from three distinct platforms, annotated according to ten social dimensions to capture
arXiv:2605.25678v1 Announce Type: cross Abstract: We study the problem of multiclass PAC learning with bandit feedback in the realizable setting. In this framework, there is an unknown data distributi
arXiv:2605.24350v1 Announce Type: new Abstract: Robotic assistants in long-term human-robot collaboration need to assist users under partial observations while leveraging cross-day interaction history
arXiv:2605.06505v2 Announce Type: replace-cross Abstract: We introduce PACZero, a family of PAC-private zeroth-order mechanisms for fine-tuning large language models that delivers usable utility at I(
arXiv:2506.09084v2 Announce Type: replace-cross Abstract: Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new
arXiv:2512.20063v3 Announce Type: replace Abstract: We introduce exttt{PairFlow}, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiri
arXiv:2605.24154v1 Announce Type: new Abstract: Current safety alignment of foundation models largely follows a one-size-fits-all paradigm, applying the same refusal policy across users and contexts.
arXiv:2605.24549v1 Announce Type: new Abstract: Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adapta
arXiv:2605.24785v1 Announce Type: new Abstract: Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill di
arXiv:2605.25346v1 Announce Type: cross Abstract: Neural network (NN) dynamics models and control policies achieve strong performance in robotics, but providing sound guarantees under uncertainty rema
arXiv:2605.25348v1 Announce Type: cross Abstract: Low-dose computed tomography (LDCT) reconstruction faces a critical tradeoff between reconstruction quality and resource requirements. While recent de
arXiv:2605.23984v1 Announce Type: cross Abstract: Industrial anomaly detection has attracted significant attention as a fundamental challenge in industrial systems. The rapid advancement of heterogene
arXiv:2605.24792v1 Announce Type: cross Abstract: The major limitations of gastrointestinal (GI) endoscopy AI systems arise from a shortage of annotated data, strict privacy policies, and significant
arXiv:2605.26064v1 Announce Type: cross Abstract: We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv
arXiv:2605.25029v1 Announce Type: new Abstract: Autonomous parking demands precise low-speed maneuvering within narrow, cluttered, and highly constrained environments, where vehicles must navigate tig
arXiv:2605.25782v1 Announce Type: new Abstract: Humanoid parkour requires locomotion policies to coordinate whole-body dynamics across rapidly changing terrains such as stairs, gaps, slopes, and obsta
arXiv:2602.00511v2 Announce Type: replace Abstract: Despite their empirical success, neural network classifiers remain difficult to interpret. In softmax-based models, class regions are defined implic
arXiv:2605.24352v1 Announce Type: new Abstract: Multi-agent collaboration, especially in human-AI teaming, requires agents that can adapt to novel partners with diverse and dynamic behaviors. Conventi
arXiv:2605.10977v2 Announce Type: replace-cross Abstract: Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. Ho
arXiv:2605.24731v1 Announce Type: cross Abstract: This paper presents a novel passivity-based semi-autonomous attitude control framework, with a particular focus on attitude kinematics defined on the
arXiv:2605.25401v1 Announce Type: new Abstract: Biomimetic autonomous underwater vehicle (BAUV) with multi-link mechanism is widely used in aquatic life observation and environmental surveys due to it
arXiv:2603.09943v2 Announce Type: replace Abstract: Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading
arXiv:2601.20539v3 Announce Type: replace Abstract: Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks'
arXiv:2502.10906v2 Announce Type: replace Abstract: Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, s
arXiv:2605.25353v1 Announce Type: new Abstract: Inverse problems in partial differential equations (PDEs) involve estimating the physical parameters of a system from observed spatiotemporal solution f
arXiv:2605.26037v1 Announce Type: new Abstract: We test the standard RLVR tool-use recipe -- GRPO on Qwen2.5-7B-Instruct -- on a deliberately minimal knowledge-graph tool API: four Freebase navigation
arXiv:2605.24562v1 Announce Type: cross Abstract: Pedestrian intention and trajectory prediction are critical for the safe deployment of autonomous driving systems, directly influencing navigation dec
arXiv:2605.25572v1 Announce Type: cross Abstract: The growing complexity of quantum programming frameworks has exposed a critical limitation in existing large language model (LLM)-based code assistant
arXiv:2605.25010v1 Announce Type: cross Abstract: Integrating artificial intelligence (AI) into sampling-based motion planning provides new possibilities for improving autonomous navigation efficiency
arXiv:2602.19333v2 Announce Type: replace Abstract: This research introduces the first large-scale, well-balanced Persian social media text classification dataset, specifically designed to address the
arXiv:2605.25535v1 Announce Type: new Abstract: Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are wor
arXiv:2605.25212v1 Announce Type: new Abstract: Federated learning (FL) is an effective paradigm for enhancing the learning capability of edge devices while preserving data privacy. In geographically
arXiv:2502.21297v2 Announce Type: replace Abstract: Persuasive dialogue is central to human communication, yet existing datasets often rely on a single language model generating both roles, producing
arXiv:2605.24621v1 Announce Type: cross Abstract: Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in
arXiv:2605.25554v1 Announce Type: new Abstract: As a core task in intelligent transportation systems, traffic forecasting plays a critical role in urban traffic management. Accurate traffic forecastin
arXiv:2605.24509v1 Announce Type: cross Abstract: Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs
arXiv:2605.24451v1 Announce Type: new Abstract: Vietnamese exhibits substantial dialectal phonetic variation across Northern, Central, and Southern regions, where identical lexical items may be realiz
arXiv:2605.24590v1 Announce Type: cross Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise. Ex