Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2601.14895v3 Announce Type: replace Abstract: SpatialMem is a memory-based system which integrates 3D geometry, semantics, and language with one another in one combined, queryable representatio...
arXiv:2605.07846v4 Announce Type: replace Abstract: Coarse-mask local editing must preserve the background while allowing new content to depart from the mask contour. Existing mask-conditioned editor...
arXiv:2604.12196v2 Announce Type: replace Abstract: Solving complex problems with large language models (LLMs) often requires selecting the best answer from multiple candidate responses (best-of-$N$)...
arXiv:2610.24478v2 Announce Type: replace Abstract: Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines. We show that, und...
arXiv:2605.18767v2 Announce Type: replace-cross Abstract: Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applicat...
arXiv:2610.30444v1 Announce Type: new Abstract: Signed graph learning has emerged as a powerful framework for modeling networks with both positive and negative interactions. While graph-filter-based...
arXiv:2610.30167v1 Announce Type: cross Abstract: Optimizing Information Retrieval (IR) pipelines for Retrieval-Augmented Generation (RAG) requires jointly selecting structural components and numeric...
arXiv:2610.28882v1 Announce Type: cross Abstract: Long-horizon robotic operation requires memory that scales with essential information rather than execution time. We present a parameter-space memory...
arXiv:2610.25402v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong performance across diverse reasoning tasks, yet it remains unclear whether this performance refle...
arXiv:2610.30843v1 Announce Type: new Abstract: We introduce Lean Finder V2, a semantic search framework for Mathlib that disambiguates user queries through complementary model-level adversarial trai...
arXiv:2610.30148v1 Announce Type: cross Abstract: Objective: Emergency department (ED) overcrowding threatens care quality, yet Full Capacity Protocols (FCPs) are typically activated only after crowd...
arXiv:2610.31235v1 Announce Type: cross Abstract: Transformer-based models have shown strong performance across diverse tasks, but their reliance on self-attention mechanisms often leads to high comp...
arXiv:2601.09373v3 Announce Type: replace Abstract: Do Large Language Models (LLMs) genuinely grasp the compositional semantics of events, or do they rely on surface-level probabilistic heuristics? W...
arXiv:2610.31162v1 Announce Type: new Abstract: Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requiring both long-horizon autonomy and r...
The article reports on an experiment where an AI agent was allowed to search for evidence whenever it chose. The agent discovered some papers that a standard search missed, but also lost some that the plain search had found, and overall the gains were insufficient to be trusted. The post examines whether agentic Retrieval-Augmented Generation (RAG) truly retrieves better evidence across 298 questions.
Clinical Question Answering (QA) underpins Clinical Intelligent Decision Support Systems, but progress is severely limited for low-resource languages such as Indonesian by the absence of public domain...
We introduce Lean Finder V2, a semantic search framework for Mathlib that disambiguates user queries through complementary model-level adversarial training and input-level query rewriting. Human mathe...
Text embedding and text generation are two of the most useful capabilities of modern large language models, yet they are typically provided by separate specialized models (an embedder and a generator)...
The paper introduces a trace-level divergence framework for evaluating multilingual large language models, breaking down agreement into structural similarity, order consistency, and holistic similarity. Experiments across three reasoning benchmarks, seven languages, and six leading LLMs show that conventional holistic similarity metrics overstate agreement, with up to 67.3% of top-scoring examples lacking structural alignment. Human judgments align more closely with structural similarity, highlighting language-specific divergence and the need for trace-level evaluation in multilingual deployments.