Knowledge catalogue
arXiv:2608.03855v1 Announce Type: new Abstract: Transformer models have revolutionized natural language processing (NLP), and text-based molecular representations like SMILES have successfully extende
arXiv:2506.13502v3 Announce Type: replace Abstract: Next-word prediction (NWP) trains language models against a single observed continuation, even though many contexts admit multiple plausible next wo
arXiv:2608.03357v1 Announce Type: new Abstract: Spatial instruction following has become a crucial requirement for text-to-image (T2I) generation. A common challenge arises when directional expression
arXiv:2608.03673v1 Announce Type: new Abstract: Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in whi
arXiv:2608.03160v1 Announce Type: cross Abstract: When asked which of two events came first, video large language models can fail in two opposite ways: cave to a false claim, or reject a true one. Pri
arXiv:2608.02935v1 Announce Type: new Abstract: Arabic script uses 28 letters, many of which share a common base shape (rasm) and are distinguished only by dot placement. Because early Arabic manuscri
arXiv:2608.03360v1 Announce Type: cross Abstract: Non-intrusive reduced-order models (NIROMs) have become a standard tool for approximating parametric partial differential equations from computer desi
arXiv:2608.03628v1 Announce Type: new Abstract: Adaptive conformal prediction can recover clinically important heartbeat classes missed by a point classifier, but delayed feedback makes its decisions
arXiv:2608.03505v1 Announce Type: new Abstract: Constructed languages (conlangs) are intentionally created human languages with a rich tradition of linguistic creativity. Despite their potential for s
arXiv:2608.03874v1 Announce Type: new Abstract: Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these syst
arXiv:2608.02646v1 Announce Type: cross Abstract: Decoders of anesthetic state from cortical activity fail across drug classes, most notoriously ketamine, but reported accuracy cannot say whether the
arXiv:2608.03862v1 Announce Type: new Abstract: Emergency triage requires reliable decisions within a short time period. However, the available electronic health record (EHR) data, including structure
arXiv:2608.02643v1 Announce Type: cross Abstract: Computer-use agents (CUAs) operate real desktop and web interfaces through screenshots, mouse and keyboard actions, and stateful UI feedback, yet thei
arXiv:2608.03051v1 Announce Type: new Abstract: Model Predictive Control (MPC) delivers constraint-aware control, but its reliance on online optimization limits its use on systems with fast dynamics,
arXiv:2608.02769v1 Announce Type: cross Abstract: Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance. A central challenge is determi
arXiv:2608.03655v1 Announce Type: cross Abstract: Abstractive summarization models remain vulnerable to factual inconsistency, redundancy, and weak length control. We propose a modular generation-and-
arXiv:2608.02628v1 Announce Type: cross Abstract: Symbolic regression (SR) is the task of discovering underlying patterns from data and representing them using mathematical expressions. Current machin
arXiv:2608.02678v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems are vulnerable to corpus poisoning: an attacker who inserts a crafted document into the retrieval corpus
arXiv:2608.02904v1 Announce Type: new Abstract: Delivering sustained power to distributed equipment in unstructured field environments using pre-planned wired networks or battery-based solutions prese
arXiv:2608.03674v1 Announce Type: new Abstract: Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments. Yet serious cases are scarce,
arXiv:2608.03025v1 Announce Type: new Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual ev
arXiv:2608.03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant infor
arXiv:2608.03566v1 Announce Type: cross Abstract: The drift diffusion model (DDM) is a cornerstone of cognitive decision-making research. Although numerous estimation methods exist, researchers contin
arXiv:2608.03388v1 Announce Type: new Abstract: Abductive reasoning requires forming hypotheses that explain observed evidence and revising them as new evidence becomes available. While large language
arXiv:2608.02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art s
arXiv:2510.11834v3 Announce Type: replace-cross Abstract: Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs. A common strategy is to fine-tun
arXiv:2608.02673v1 Announce Type: cross Abstract: Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language pr
arXiv:2608.03101v1 Announce Type: new Abstract: Near-duplicate image matching is crucial for trust and safety, provenance verification, copyright enforcement, and large-scale visual search. Modern pla
arXiv:2608.03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attribu
arXiv:2608.03410v1 Announce Type: new Abstract: Earth observation is moving from foundation models that users must run themselves toward embedding products that package model feature outputs as reusab
arXiv:2608.03179v1 Announce Type: new Abstract: Controllable local editing of 3D assets requires precise target localization and appropriate visual guidance. However, existing methods lack a simple ye
arXiv:2608.03480v1 Announce Type: new Abstract: The adoption of large pre-trained multilingual models for neural machine translation (MNMT) faces a major challenge: excessive memory and computational
arXiv:2608.03044v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate human opinions, but prior work reports conflicting results: some studies find promising alignm
arXiv:2608.03875v1 Announce Type: cross Abstract: Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL). Recent work uses large foundation Vision-Language Mode
arXiv:2608.03920v1 Announce Type: cross Abstract: Humans recognize a musical passage even when it is shifted in time or transposed in pitch, indicating a notion of equivariance in the representation s
arXiv:2608.03498v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. How
arXiv:2608.02939v1 Announce Type: new Abstract: Electronic health record foundation models are limited by institutionally siloed data and substantial performance degradation under cross-site transfer.
arXiv:2608.02919v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-
arXiv:2608.03822v1 Announce Type: cross Abstract: Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generat
arXiv:2604.01832v1 Announce Type: cross Abstract: We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge. The system integrates a
arXiv:2608.03588v1 Announce Type: cross Abstract: AI coding agents are stochastic workflows: prompts are interpreted, artifacts are sampled, validators produce observations, and orchestrators commit o
arXiv:2608.02633v1 Announce Type: new Abstract: Regional surveillance data reflect local transmission, reporting, seeding, and external infection pressure, which are difficult to identify separately.
arXiv:2608.02690v1 Announce Type: new Abstract: On-device training of deep neural networks is fundamentally constrained by the computational and memory costs of large-scale datasets. Coreset selection
arXiv:2608.02877v1 Announce Type: new Abstract: Causal discovery recovers directed structure from observational data and is increasingly used in clinical settings to support mechanism reasoning and fa
arXiv:2608.03083v1 Announce Type: cross Abstract: Video large language models (VideoLLMs) achieve strong video understanding performance, but their inference remains expensive due to the large number
arXiv:2608.03966v1 Announce Type: new Abstract: Large language models can generate fluent Arabic answers while introducing factual errors that are difficult to identify and verify. Existing Arabic hal
arXiv:2608.03471v1 Announce Type: new Abstract: Generative Vision-Language Models (VLMs) commonly treat bounding-box coordinates as independent output symbols, leaving numerical order and axis semanti
arXiv:2509.23690v2 Announce Type: replace-cross Abstract: Safety hazards in the home are a leading cause of preventable domestic injuries, motivating an automated inspector that actively explores a ho
arXiv:2608.03138v1 Announce Type: cross Abstract: Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identif
arXiv:2608.03961v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that s
arXiv:2608.03892v1 Announce Type: new Abstract: We study linear representations of temporal horizon in the large language model Qwen3-32B and use them to change the model's time-related preferences, r
arXiv:2608.02957v1 Announce Type: new Abstract: Steering vectors (SVs) are widely used to influence the expression of concepts (e.g., truthfulness) in large language model outputs. A key assumption un
arXiv:2608.02604v1 Announce Type: new Abstract: LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their perform
arXiv:2608.03974v1 Announce Type: new Abstract: Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term tempo
arXiv:2608.02621v1 Announce Type: cross Abstract: Legal benchmarks typically score final answers even when models also state legal authority. We test whether answer correctness can serve as a proxy fo
arXiv:2608.02915v1 Announce Type: cross Abstract: Domain-specific Instruction Set Architecture eXtensions (ISAX) are widely adopted in the RISC-V ecosystem to accelerate emerging workloads, but implem
arXiv:2608.03234v1 Announce Type: new Abstract: Motion priors provide powerful guidance for learning naturalistic humanoid behaviors. However, existing methods typically learn a general, task-agnostic
arXiv:2608.03705v1 Announce Type: new Abstract: Real-time bidding (RTB) ad exchanges typically forward nearly all incoming requests to demand-side platforms (DSPs), even though only a small fraction r
arXiv:2608.03489v1 Announce Type: cross Abstract: Combining Bayesian learning and quantitative verification is a powerful toolset for analysing key quantitative properties of software systems, like re
arXiv:2608.03148v1 Announce Type: cross Abstract: RAG improves the factual grounding of LLM by incorporating external knowledge, but deploying RAG on mobile and edge devices remains challenging becaus