arXiv:2511.07629v1 Announce Type: new Abstract: Offline multi-agent reinforcement learning (MARL) is severely hampered by the challenge of evaluating out-of-distribution (OOD) joint actions. Our core finding is that when the behavior policy is factorized – a common scenario where agents act…
arXiv:2511.07198v2 Announce Type: replace Abstract: Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-domain interference. To overcome this challenge, we propose a partition-based multi-stage fine-tuning framework designed to…
arXiv:2511.07633v1 Announce Type: new Abstract: We introduce FlowTIE, a neural-network-based framework for phase reconstruction from 4D-Scanning Transmission Electron Microscopy (STEM) data, which integrates the Transport of Intensity Equation (TIE) with a flow-based representation of the phase gradient. This formulation allows…
arXiv:2505.00661v3 Announce Type: replace-cross Abstract: Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical…
arXiv:2511.07637v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving documents from an external corpus at inference time. When this corpus contains sensitive information, however, unprotected RAG systems are at risk of leaking private information.…
arXiv:2509.03764v2 Announce Type: replace-cross Abstract: Relevance evaluation plays a crucial role in personalized search systems to ensure that search results align with a user’s queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost…
arXiv:2511.07649v1 Announce Type: new Abstract: Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for…
arXiv:2511.05540v2 Announce Type: replace-cross Abstract: We challenge the long-standing assumption that exhaustive scene modeling is required for high-performance end-to-end autonomous driving (E2EAD). Inspired by cognitive science, we propose that effective planning arises not from reconstructing the world, but from the…
arXiv:2511.07651v1 Announce Type: new Abstract: Effective crime linkage analysis is crucial for identifying serial offenders and enhancing public safety. To address limitations of traditional crime linkage methods in handling high-dimensional, sparse, and heterogeneous data, we propose a Siamese Autoencoder framework…
arXiv:2511.08360v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are used in many applications, but their large size and high computational cost make them hard to run on devices with limited resources. Two widely used techniques to address this challenge…
