Stay updated with the latest research and technology news
arXiv:2602.00364v2 Announce Type: replace Abstract: Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR),...
arXiv:2602.00391v2 Announce Type: replace Abstract: In this study, we develop a novel methodology for annotating the brain vasculature using dynamic 4D-CTA head scans. By using...
arXiv:2602.00636v2 Announce Type: replace Abstract: Ensuring the safety of environmental exploration is a critical problem in reinforcement learning (RL). While limiting exploration to a feasible...
arXiv:2602.00841v2 Announce Type: replace Abstract: Visual Place Recognition (VPR) demands representations robust to drastic environmental and viewpoint shifts. Current aggregation paradigms, however, either rely on...
arXiv:2602.00906v3 Announce Type: replace Abstract: Large language models often hallucinate with high confidence on "random facts" that lack inferable patterns. We formalize the memorization of...
arXiv:2602.01009v2 Announce Type: replace Abstract: Foundation models have transformed language, vision, and time series data analysis, yet progress on dynamic predictions for physical systems remains...
arXiv:2602.01075v2 Announce Type: replace Abstract: Convex analysis is a modern branch of mathematics with many applications. As Large Language Models (LLMs) start to automate research-level...
arXiv:2602.01317v2 Announce Type: replace Abstract: Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but...
arXiv:2602.01435v2 Announce Type: replace Abstract: We propose BioTamperNet, a novel framework for detecting duplicated regions in tampered biomedical images, leveraging affinity-guided attention inspired by State...
arXiv:2602.01589v2 Announce Type: replace Abstract: Many genus-0 surface mapping tasks such as landmark alignment, feature matching, and image-driven registration, can be reduced (via an initial...
arXiv:2602.01602v2 Announce Type: replace Abstract: Recently, the Foundation Error Correction Code Transformer (FECCT) has emerged as a promising universal channel decoder, achieving competitive decoding performance...
arXiv:2602.01656v2 Announce Type: replace Abstract: We revisit the inverse problem of reconstructing a spatially varying diffusion coefficient in stationary elliptic equations from boundary Cauchy data....
arXiv:2602.01705v2 Announce Type: replace Abstract: Recent reinforcement learning (RL) methods improve LLM reasoning by optimizing discrete Chain-of-Thought (CoT) generation; however, exploration in token space often...
arXiv:2602.01873v2 Announce Type: replace Abstract: Log-Structured Merge-Trees (LSM-trees) dominate persistent key-value storage but suffer from high write amplification from 10x to 30x under random workloads...
arXiv:2602.02164v2 Announce Type: replace Abstract: Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and...
arXiv:2602.02343v2 Announce Type: replace Abstract: Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in...
arXiv:2602.02388v2 Announce Type: replace Abstract: Imagine Alice has a specific image $x^\ast$ in her mind, say, the view of the street in which she grew...
arXiv:2602.02437v2 Announce Type: replace Abstract: Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image...
arXiv:2602.02499v2 Announce Type: replace Abstract: Long-context capability and computational efficiency are among the central challenges facing today's large language models. Existing efficient attention methods reduce...
arXiv:2602.02515v2 Announce Type: replace Abstract: Leaderboard scores on public benchmarks have been steadily rising and converging, with many frontier language models now separated by only...
arXiv:2602.02579v2 Announce Type: replace Abstract: The prefill stage of long-context Retrieval-Augmented Generation (RAG) is severely bottlenecked by computational overhead. To mitigate this, recent methods assemble...
arXiv:2602.02599v2 Announce Type: replace Abstract: Long-context inference in large language models is increasingly bottlenecked by the memory and compute cost of the KV-Cache. Low-rank factorization...
arXiv:2602.02619v2 Announce Type: replace Abstract: While Large Language Models (LLMs) excel at short-term tasks, scaling them to long-horizon agentic workflows remains challenging. The core bottleneck...
arXiv:2602.02743v2 Announce Type: replace Abstract: Cross-disciplinary teams increasingly work with high-dimensional scientific datasets, yet fragmented toolchains and limited support for shared exploration hinder collaboration. Prior...