Stay updated with the latest research and technology news
arXiv:2509.23480v2 Announce Type: replace Abstract: Current approaches for restoration of degraded images face a trade-off: high-performance models are slow for practical use, while fast models...
arXiv:2509.23694v4 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces...
arXiv:2509.24050v3 Announce Type: replace Abstract: Device-cloud collaboration holds promise for deploying large language models (LLMs), leveraging lightweight on-device models for efficiency while relying on powerful...
arXiv:2509.24386v3 Announce Type: replace Abstract: We have recently observed the commercial roll-out of robotaxis in various countries. They are deployed within an operational design domain...
arXiv:2509.24472v2 Announce Type: replace Abstract: Permutation equivariant neural networks employing parameter-sharing schemes have emerged as powerful models for leveraging a wide range of data symmetries,...
arXiv:2509.24583v2 Announce Type: replace Abstract: Modal separability for modal fixpoint formulae is the problem to decide for two given modal fixpoint formulae $\varphi,\varphi'$ whether there...
arXiv:2509.24906v2 Announce Type: replace Abstract: We demonstrate that embeddings derived from large language models, when processed with "Survey and Questionnaire Item Embeddings Differentials" (SQuID), can...
arXiv:2509.25214v2 Announce Type: replace Abstract: As increasingly large pre-trained models are released, deploying them on edge devices for privacy-preserving applications requires effective compression. Recent works...
arXiv:2509.25239v2 Announce Type: replace Abstract: Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought reasoning...
arXiv:2509.25701v2 Announce Type: replace Abstract: Peer review is the primary mechanism for evaluating scientific contributions, yet prior studies have mostly examined paper features or external...
arXiv:2509.25731v2 Announce Type: replace Abstract: Recent multimodal models for instruction-based face editing enable semantic manipulation but still struggle with precise attribute control and identity preservation....
arXiv:2509.25851v2 Announce Type: replace Abstract: Multimodal symbolic logical reasoning, which aims to deduce new facts from multimodal input via formal logic, is critical in high-stakes...
arXiv:2509.26157v2 Announce Type: replace Abstract: Patch-based transformers have emerged as efficient and improved long-horizon modeling architectures for time series modeling. Yet, existing approaches rely on...
arXiv:2510.01824v2 Announce Type: replace Abstract: We introduce an order-invariant reinforcement learning framework for black-box combinatorial optimization. Classical estimation-of-distribution algorithms (EDAs) often rely on learning explicit...
arXiv:2510.02081v2 Announce Type: replace Abstract: Flow Matching (FM) models achieve remarkable results in generative tasks. Building upon diffusion models, FM's simulation-free training paradigm enables simplicity...
arXiv:2510.02190v2 Announce Type: replace Abstract: As an embodiment of intelligence evolution toward interconnected architectures, Deep Research Agents (DRAs) systematically exhibit the capabilities in task decomposition,...
arXiv:2510.02422v3 Announce Type: replace Abstract: Existing gradient-based jailbreak attacks typically optimize an adversarial suffix to induce a fixed affirmative response, e.g., ``Sure, here is...''. However,...
arXiv:2510.02999v3 Announce Type: replace Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined...
arXiv:2510.03217v2 Announce Type: replace Abstract: Agentic Automated Program Repair (APR) is increasingly tackling complex, repository-level bugs in industry, but ultimately these patches still need to...
arXiv:2510.07132v2 Announce Type: replace Abstract: Clustered Federated Learning (CFL) improves performance under non-IID client heterogeneity by clustering clients and training one model per cluster, thereby...
arXiv:2510.07213v2 Announce Type: replace Abstract: Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language...
arXiv:2510.07666v2 Announce Type: replace Abstract: Existing pyramid registration networks may accumulate anatomical misalignments and lack an effective mechanism to dynamically determine the number of optimization...
arXiv:2510.07823v2 Announce Type: replace Abstract: Visual prompting (VP) has emerged as a promising parameter-efficient fine-tuning approach for adapting pre-trained vision models to downstream tasks without...
arXiv:2510.08592v2 Announce Type: replace Abstract: Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the...