Stay updated with the latest research and technology news
arXiv:2602.09765v1 Announce Type: new Abstract: Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to...
arXiv:2602.09767v1 Announce Type: new Abstract: Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data....
arXiv:2602.09772v1 Announce Type: new Abstract: The possibility to create reactive robot programs faster without the need for extensively trained programmers is becoming increasingly important. So...
arXiv:2602.09774v1 Announce Type: new Abstract: Static Application Security Testing (SAST) tools are integral to modern DevSecOps pipelines, yet tools like CodeQL, Semgrep, and SonarQube remain...
arXiv:2602.09775v1 Announce Type: new Abstract: Recent studies show that text-to-image models often fail to generate geographically representative images, raising concerns about the representativeness of their...
arXiv:2602.09776v1 Announce Type: new Abstract: This paper studies orthogonal time-frequency space (OTFS) modulation aided multistatic integrated sensing and communication (ISAC) in vehicular networks, whereby its...
arXiv:2602.09781v1 Announce Type: new Abstract: This study investigates the explainability of generative diffusion models in the context of medical imaging, focusing on Magnetic resonance imaging...
arXiv:2602.09782v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a critical method for enhancing the reasoning capabilities of Large Language...
arXiv:2602.09783v1 Announce Type: new Abstract: Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed...
arXiv:2602.09784v1 Announce Type: new Abstract: Circuit discovery and activation steering in transformers have developed as separate research threads, yet both operate on the same representational...
arXiv:2602.09785v1 Announce Type: new Abstract: This paper introduces the first standardized benchmark for evaluating Automatic Speech Recognition (ASR) in the Bambara language, utilizing one hour...
arXiv:2602.09789v1 Announce Type: new Abstract: Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior...
arXiv:2602.09794v1 Announce Type: new Abstract: Chain-of-Thought (CoT) has been shown to significantly improve the reasoning accuracy of large language models (LLMs) on complex tasks. However,...
arXiv:2602.09798v1 Announce Type: new Abstract: Recently, a Symbolic Pattern Planning (SPP) approach was proposed for numeric planning where a pattern (i.e., a finite sequence of...
arXiv:2602.09801v1 Announce Type: new Abstract: Most machine learning approaches to scientific discovery frame hypotheses as end-to-end predictions, obscuring the incremental structure of scientific reasoning. We...
arXiv:2602.09802v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed in applications such as travel assistance and purchasing support, they are often...
arXiv:2602.09805v1 Announce Type: new Abstract: Large language models trained for reasoning trade off inference tokens against accuracy, yet standard evaluations report only final accuracy, obscuring...
arXiv:2602.09809v1 Announce Type: new Abstract: Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing benchmarks...
arXiv:2602.09810v1 Announce Type: new Abstract: Transfer learning in deep reinforcement learning is often motivated by improved stability and reduced training cost, but it can also...
arXiv:2602.09813v1 Announce Type: new Abstract: Unsupervised Environment Design (UED) has emerged as a promising approach to developing general-purpose agents through automated curriculum generation. Popular UED...
arXiv:2602.09816v1 Announce Type: new Abstract: High-quality novel view synthesis (NVS) from real-world videos is crucial for applications such as cultural heritage preservation, digital twins, and...
arXiv:2602.09817v1 Announce Type: new Abstract: This paper introduces AnalyticsGPT, an intuitive and efficient large language model (LLM)-powered workflow for scientometric question answering. This underrepresented downstream...
arXiv:2602.09821v1 Announce Type: new Abstract: Text summarization is a fundamental task in natural language processing (NLP), and the information explosion has made long-document processing increasingly...
arXiv:2602.09822v1 Announce Type: new Abstract: Unlike Ethereum, which was conceived as a general-purpose smart-contract platform, Bitcoin was designed primarily as a transaction ledger for its...