Stay updated with the latest research and technology news
arXiv:2510.25497v2 Announce Type: replace Abstract: Neurosymbolic AI is growing in popularity thanks to its ability to combine neural perception and symbolic reasoning in end-to-end trainable...
arXiv:2510.25975v2 Announce Type: replace Abstract: Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions....
arXiv:2510.26441v2 Announce Type: replace Abstract: Test-time prompt tuning (TPT) has emerged as a promising technique for adapting large vision-language models (VLMs) to unseen tasks without...
arXiv:2510.26442v4 Announce Type: replace Abstract: Semantic communication focuses on conveying the task-relevant meaning rather than exact bitwise recovery. For image transmission with a generative receiver,...
arXiv:2510.26861v3 Announce Type: replace Abstract: Multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the...
arXiv:2510.27017v2 Announce Type: replace Abstract: Several previous works concluded that the largest part of generation capabilities of large language models (LLM) are learned (early) during...
arXiv:2511.00129v3 Announce Type: replace Abstract: Accurate downhole depth measurement is essential for oil and gas well operations, directly influencing reservoir contact, production efficiency, and operational...
arXiv:2511.00847v4 Announce Type: replace Abstract: The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: the potential for...
arXiv:2511.01294v3 Announce Type: replace Abstract: A deep understanding of kinematic structures and movable components is essential for enabling robots to manipulate objects and model their...
arXiv:2511.01632v2 Announce Type: replace Abstract: Biological neural networks exist in physical space where distance influences communication delays: a fundamental coupling between space and time absent...
arXiv:2511.01989v3 Announce Type: replace Abstract: The sixth generation (6G) of wireless networks will require fundamentally new orchestration paradigms to meet stringent requirements for ultra-low latency,...
arXiv:2511.02599v2 Announce Type: replace Abstract: Modelling student knowledge is a key challenge when leveraging AI in education, with major implications for personalised learning. The Knowledge...
arXiv:2511.02844v2 Announce Type: replace Abstract: Quantum computing education requires students to move beyond classical programming intuitions related to state, determinism, and debugging, and to develop...
arXiv:2511.03369v3 Announce Type: replace Abstract: Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs...
arXiv:2511.04084v2 Announce Type: replace Abstract: Medical image segmentation is critical for accurate diagnostics and treatment planning, but remains challenging due to complex anatomical structures and...
arXiv:2511.04235v3 Announce Type: replace Abstract: Constructing a consistent shared spatial memory is a critical challenge in multi-agent systems, where partial observability and limited bandwidth often...
arXiv:2511.04427v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated the promise to revolutionize the field of software engineering. Among other things, LLM agents...
arXiv:2511.04659v4 Announce Type: replace Abstract: Reliable nowcasting of extreme precipitation remains difficult because convective systems are strongly nonlinear, multiscale, and nonstationary in 3D. Radar is...
arXiv:2511.04768v2 Announce Type: replace Abstract: As deep learning models scale, sparse computation and specialized dataflow hardware have emerged as powerful solutions to address efficiency. We...
arXiv:2511.05293v2 Announce Type: replace Abstract: Electroencephalogram (EEG)-based emotion recognition is vital for affective computing but faces challenges in feature utilization and cross-domain generalization. This work...
arXiv:2511.05843v2 Announce Type: replace Abstract: Multi-Byzantine Fault Tolerant (Multi-BFT) consensus, which runs multiple BFT instances in parallel, has recently emerged as a promising approach to...
arXiv:2511.05903v2 Announce Type: replace Abstract: User simulation is important for developing and evaluating human-centered AI, yet current student simulation in educational applications has significant limitations....
arXiv:2511.08091v2 Announce Type: replace Abstract: Pearl's Causal Hierarchy (PCH) is a central framework for reasoning about probabilistic, interventional, and counterfactual statements, yet the satisfiability problem...
arXiv:2511.08150v5 Announce Type: replace Abstract: Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly...