Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2606. 08347v1 Announce Type: cross Abstract: Modern language models represent text using discrete token-level embeddings, which forces recurring multi-token patterns to be learned implicitly across Transformer layers.
arXiv:2606. 08893v1 Announce Type: cross Abstract: A small transformer encoder is trained to map Terminal-Wrench trajectories onto a unit sphere where embedding distance approximates the $L_1$ distance between reward and metadata signals.
arXiv:2602. 00238v2 Announce Type: replace-cross Abstract: Existing retrieval-augmented generation (RAG) systems often assume that each query has a single correct answer.
arXiv:2606. 07843v1 Announce Type: cross Abstract: Schema matching, a critical task for integrating data from diverse sources, seeks to identify correspondences between columns across different schemas.
arXiv:2606. 08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action time.
arXiv:2604. 06893v3 Announce Type: replace-cross Abstract: Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious background correlations.
arXiv:2606. 08212v1 Announce Type: new Abstract: Solving machine learning problems is complex and typically reserved for experts.
arXiv:2606. 09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedded in retrieved documents backfire against the attacker, suppressing the target brand below the injection-free baseline.
arXiv:2606. 09311v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods like the Cross-Entropy Method (CEM).
arXiv:2606. 09441v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) injects LLM queries with relevant documents to improve response quality.
arXiv:2606. 09800v1 Announce Type: cross Abstract: Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle.
arXiv:2606. 07692v1 Announce Type: cross Abstract: Foundation models for wearable biosignals have matched or exceeded supervised specialists across a range of clinical tasks, yet all rely on modalities that require deliberate user action--wearing a device or visiting a sleep lab.
arXiv:2606. 09520v1 Announce Type: cross Abstract: Can a general-purpose large language model design molecules with the precision of a seasoned chemist?
arXiv:2606. 09331v1 Announce Type: cross Abstract: Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is difficult since these modalities differ in data distribution, architecture, and optimization dynamics.
arXiv:2606. 09287v1 Announce Type: new Abstract: Understanding how transformer representations evolve across layers, not merely what they encode, remains an open problem in mechanistic interpretability.
arXiv:2606. 07649v1 Announce Type: cross Abstract: Long-form video generation requires systematic narrative planning and visual consistency that current short-clip methods cannot provide.
arXiv:2512. 20978v2 Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech.
arXiv:2601. 21149v3 Announce Type: replace-cross Abstract: Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations, particularly points-of-interest (POIs) where human activity concentrates.
arXiv:2606. 08067v1 Announce Type: new Abstract: Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.
arXiv:2606. 08303v1 Announce Type: new Abstract: This paper investigates a novel concept of time series geolocalization, where the goal is to infer the geographic origin of each raw time series.