Knowledge catalogue
arXiv:2506.08244v2 Announce Type: replace-cross Abstract: Equivariant neural networks incorporate symmetries through group actions, embedding them as an inductive bias to improve performance. Existing
arXiv:2605.17010v1 Announce Type: cross Abstract: Algorithmic feeds have become primary environments for encountering information online, yet while they shape what people see, less is known about how
arXiv:2511.06316v3 Announce Type: replace Abstract: In low- and middle-income countries, public safety and urban planning initiatives frequently face a critical shortage of accurate, location-specific
arXiv:2605.18629v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into high
arXiv:2505.17352v2 Announce Type: replace Abstract: Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignmen
arXiv:2605.16516v1 Announce Type: cross Abstract: Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the use
arXiv:2605.18309v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alig
arXiv:2605.18592v1 Announce Type: cross Abstract: Rubric-based reward shaping is an effective method for fine-tuning LLMs via RL, where structured rubrics decompose standard outcome rewards into multi
arXiv:2605.17352v1 Announce Type: new Abstract: Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remai
arXiv:2605.17806v1 Announce Type: new Abstract: Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with orthogonalization via Newton-Schulz (NS) iterations a
arXiv:2510.12999v2 Announce Type: replace Abstract: Time integration of stiff systems is a primary source of computational cost in combustion, hypersonics, and other reactive transport systems. This s
arXiv:2605.18529v1 Announce Type: new Abstract: The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, st
arXiv:2602.08916v2 Announce Type: replace-cross Abstract: Objective: Acute mountain sickness (AMS) is the most prevalent altitude illness, affecting unacclimatized individuals ascending above 2,500 m
arXiv:2509.06503v2 Announce Type: replace Abstract: The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experimentsite{hannay
arXiv:2605.17151v1 Announce Type: new Abstract: In sales and marketing, customer segmentation is an important tool for formulating strategies for customer treatment and supply chain management. Most s
arXiv:2605.18623v1 Announce Type: cross Abstract: In the graph label selection problem, one is given an n-vertex graph and a budget k, and seeks to select k vertices whose labels enable accurate predi
arXiv:2605.18648v1 Announce Type: cross Abstract: Central to human-aligned AI is understanding the benefits of human-elicited labels over synthetic alternatives. While human soft-labels improve calibr
arXiv:2605.17245v1 Announce Type: cross Abstract: Telecommunication fraud is an acute problem that leads to substantial material losses and compromises the reliability of telecom systems worldwide. On
arXiv:2605.17921v1 Announce Type: new Abstract: Streaming video requires handling dynamic information density under strict latency budgets. Yet, existing methods typically employ static strategies, su
arXiv:2605.18133v1 Announce Type: cross Abstract: LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These ca
arXiv:2605.16379v1 Announce Type: cross Abstract: Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic ac
arXiv:2605.17468v1 Announce Type: cross Abstract: This paper presents an interpretable closed-loop Intelligent Tutoring System (ITS) that supports feedback-guided practice for developing on-camera ora
arXiv:2602.07715v2 Announce Type: replace Abstract: Recovering a signal from its degraded measurements is a long standing challenge in science and engineering. Recently, zero-shot diffusion based meth
arXiv:2605.17443v1 Announce Type: new Abstract: We analyze how automatic speech recognition (ASR) errors propagate through ASR-LLM cascades in Korean spoken question answering (SQA), focusing on downs
arXiv:2405.14657v2 Announce Type: replace Abstract: Preferential Bayesian optimization (PBO) learns latent utilities from pairwise comparisons, but most existing methods assume homoscedastic compariso
arXiv:2605.17071v1 Announce Type: new Abstract: Radiology report generation (RRG) aims to automatically produce clinically accurate textual reports from medical images. Existing methods predominantly
arXiv:2605.18504v1 Announce Type: new Abstract: Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parall
arXiv:2605.16309v1 Announce Type: new Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operato
arXiv:2605.16295v1 Announce Type: cross Abstract: We present ANVIL, a multimodal generative system that automates the production of analogy-based instructional animations for computer science topics.
arXiv:2605.17212v1 Announce Type: new Abstract: A unified framework for learning under covariate shift is presented, in which a constrained density-ratio network approximates the Radon-Nikodym derivat
arXiv:2603.04727v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have demonstrated impressive general competence in video understanding, yet their reliability for rea
arXiv:2605.16294v1 Announce Type: cross Abstract: A Nature survey from 2023 involving 1,600 researchers shows that scientists are ``concerned, as well as excited, by the increasing use of artificial-i
arXiv:2605.18229v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are a core interpretability tool for large language models, and progress on SAE architectures depends on benchmarks that re
arXiv:2603.11395v2 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving pe
arXiv:2605.18645v1 Announce Type: new Abstract: Retrieving the 3D kinematics of articulated objects from monocular video is a fundamental challenge in computer vision. Existing methods rely on complex
arXiv:2605.16902v1 Announce Type: new Abstract: Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have
arXiv:2605.16844v1 Announce Type: new Abstract: Between the narrow systems we deploy and the general intelligence we speculate about lies an entire regime of machine behavior that has never received i
arXiv:2605.17461v1 Announce Type: cross Abstract: Whether an interviewee's honest and deceptive responses can be detected by facial expression signals in videos has been debated and requires further r
arXiv:2605.17228v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation. However, the
arXiv:2605.16582v1 Announce Type: new Abstract: We present ArtMesh, a mesh-native method for reconstructing articulated objects explicitly as connected triangle meshes with per-part rigid motion from
arXiv:2603.23566v2 Announce Type: replace-cross Abstract: Optimizing AscendC (Ascend C) operators for Ascend NPUs is difficult for two reasons. First, unlike CUDA, the ecosystem offers few public kern
arXiv:2605.16462v1 Announce Type: cross Abstract: Detecting unauthorized knowledge distillation from a deployed LLM API is hard because the defender controls neither the attacker's training pipeline n
arXiv:2605.17324v1 Announce Type: cross Abstract: Clarification-seeking behavior is widely regarded as a desirable property of LLM agents, enabling them to resolve ambiguity before acting on underspec
arXiv:2605.18295v1 Announce Type: new Abstract: Robust pedestrian safety is crucial to the next-generation of intelligent transportation systems. Such systems rely on active pedestrian localization an
arXiv:2512.23978v2 Announce Type: replace Abstract: Generative artificial intelligence (GenAI) is shifting from conversational assistants toward agentic systems -- autonomous decision-making systems t
arXiv:2605.17933v1 Announce Type: new Abstract: Vision-language model (VLM) agents increasingly rely on memory-augmented reinforcement learning to reuse experience across long-horizon tasks, yet most
arXiv:2605.16649v1 Announce Type: new Abstract: Recent diffusion-based video generators have achieved remarkable visual fidelity and prompt controllability, yet scaling them to ultra-high-resolution (
arXiv:2605.16823v1 Announce Type: new Abstract: Molecular representation learning has become a central approach in AI-driven drug discovery, yet existing molecular tokenizations such as SMILES remain
arXiv:2605.17123v1 Announce Type: cross Abstract: At a time when drones are increasingly associated with hostile operations, we re-purpose them for humanitarian and life-saving applications. However,
arXiv:2605.18231v1 Announce Type: new Abstract: Binary function classifiers play a crucial role in maintaining the security and integrity of software systems by detecting malicious code and unauthoriz
arXiv:2605.16579v1 Announce Type: new Abstract: Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attenti
arXiv:2605.16550v1 Announce Type: new Abstract: Video periocular recognition is the task of recognizing an individual's identity based on the region around an individual's eyes. The periocular area is
arXiv:2605.17685v1 Announce Type: cross Abstract: Electrocardiogram (ECG)-based biometric recognition has emerged as a promising solution for secure authentication and liveness detection. However, mos
arXiv:2605.17310v1 Announce Type: cross Abstract: Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiven
arXiv:2605.17887v1 Announce Type: cross Abstract: We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional dept
arXiv:2605.16386v1 Announce Type: new Abstract: Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal cl
arXiv:2605.16354v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as automated evaluators of AI systems, including in high-stakes applications. In this role, LLMs ar
arXiv:2605.17765v1 Announce Type: new Abstract: Recent healthcare foundation models have achieved strong predictive performance through large scale self supervised learning, yet their latent represent
arXiv:2605.18748v1 Announce Type: new Abstract: Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and ref
arXiv:2603.23069v2 Announce Type: replace-cross Abstract: The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original tex