Stay updated with the latest research and technology news
arXiv:2510.07915v2 Announce Type: replace Abstract: The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs)...
arXiv:2510.08005v2 Announce Type: replace Abstract: Traditional bug-tracking systems rely heavily on manual reporting, reproduction, classification, and resolution, involving multiple stakeholders such as end users, customer...
arXiv:2510.08048v3 Announce Type: replace Abstract: Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping,...
arXiv:2510.08741v2 Announce Type: replace Abstract: Geocoding is the task of linking a location reference to an actual geographic location and is essential for many downstream...
arXiv:2510.08996v4 Announce Type: replace Abstract: Current benchmarks for evaluating software engineering agents, such as SWE-Bench Verified, are predominantly derived from GitHub issues and fail to...
arXiv:2510.09017v3 Announce Type: replace Abstract: Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These...
arXiv:2510.09394v4 Announce Type: replace Abstract: The ``pre-train, prompt" paradigm, designed to bridge the gap between pre-training tasks and downstream objectives, has been extended from the...
arXiv:2510.09882v2 Announce Type: replace Abstract: We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the...
arXiv:2510.09897v2 Announce Type: replace Abstract: Scientific document retrieval is a critical task for enabling knowledge discovery and supporting research across diverse domains. However, existing dense...
arXiv:2510.10157v2 Announce Type: replace Abstract: Multi-LLM systems enhance the creativity of large language models by simulating human collective intelligence but suffer from significant drawbacks, such...
arXiv:2510.10203v3 Announce Type: replace Abstract: Ensuring the reliability of autonomous driving perception systems requires extensive environment-based testing, yet real-world execution is often impractical. Synthetic datasets...
arXiv:2510.10785v2 Announce Type: replace Abstract: Previous accent conversion (AC) methods, including foreign accent conversion (FAC), lack explicit control over the degree of modification. Because accent...
arXiv:2510.10977v2 Announce Type: replace Abstract: Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically...
arXiv:2510.10978v3 Announce Type: replace Abstract: Large language models (LLMs), owing to their extensive open-domain knowledge and semantic reasoning capabilities, have been increasingly integrated into recommender...
arXiv:2510.10994v2 Announce Type: replace Abstract: Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential...
arXiv:2510.11020v2 Announce Type: replace Abstract: Auxiliary lines are essential for solving complex geometric problems but remain challenging for large vision-language models (LVLMs). Recent attempts construct...
arXiv:2510.11056v3 Announce Type: replace Abstract: Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models...
arXiv:2510.11178v2 Announce Type: replace Abstract: As vision-language models (VLMs) are deployed globally, their ability to understand culturally situated knowledge becomes essential. Yet, existing evaluations largely...
arXiv:2510.11604v2 Announce Type: replace Abstract: In online retail, customer acquisition typically incurs higher costs than customer retention, motivating firms to invest in churn analytics. However,...
arXiv:2510.12668v2 Announce Type: replace Abstract: Context-grounded generation underpins many LLM applications, including long-document question answering (QA), conversational personalization, and retrieval-augmented generation (RAG). However, classic token-based...
arXiv:2510.13551v2 Announce Type: replace Abstract: As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for...
arXiv:2510.14005v3 Announce Type: replace Abstract: LLM-integrated applications are vulnerable to prompt injection attacks, where an attacker contaminates the input to inject malicious instructions, causing the...
arXiv:2510.14305v2 Announce Type: replace Abstract: Mathematical reasoning remains one of the most challenging domains for large language models (LLMs), requiring not only linguistic understanding but...
arXiv:2510.14308v2 Announce Type: replace Abstract: AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they...