Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2609.00866v1 Announce Type: cross Abstract: The rapid advancement of vision-language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pa...
The paper introduces the Unified Memory Agent (UMA), a system that builds a query‑agnostic external memory from a data stream and reuses it across multiple question‑answering sessions. UMA employs a single policy to manage a structured Memory Bank via CRUD operations and uses Task‑Stratified GRPO to supervise memory maintenance based on QA trajectory rewards. The authors also present Ledger‑QA, a benchmark for long‑horizon state tracking, and demonstrate that UMA outperforms other methods on test‑time learning and accurate‑retrieval tasks, with UMA‑Specialist further improving performance after task adaptation.
Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round. While this enables frequent replanning, it is...
Bitcoin's pseudonymous nature makes it challenging to analyze user-level activity, since a single user may control multiple identifiers (addresses). Existing heuristic-based methods attempt to identif...
Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large...
This paper introduces the Sierpiński-Knopp (SK) Wasserstein distance, a fast metric between persistence diagrams. The SK-Wasserstein distance, denoted $d_{\mathrm{SK}}$, maps diagram points and their...
Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversation...
Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remote cloud. In this setting, token reduction lowers c...
Tables are ubiquitous across diverse domains, yet reasoning over them remains a significant challenge for modern large language models (LLMs). Current approaches typically linearize tables into sequen...
Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping i...
Monocular videos record 3D scenes as sequences of 2D image-plane projections, obscuring depth and spatial relationships. Multi-object trackers localize and associate objects primarily using appearance...
The rapid advancement of vision-language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pathology report generation remains limited by the sc...
arXiv:2601.12075v2 Announce Type: replace Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information...
arXiv:2608.29715v1 Announce Type: cross Abstract: Transformers rely on position embedding mechanisms in long context modeling in most cases. Rotary Position Embedding (RoPE) embeds positional informa...
arXiv:2608.29426v1 Announce Type: cross Abstract: Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonom...
arXiv:2608.29313v1 Announce Type: cross Abstract: CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embed...
arXiv:2608.28671v1 Announce Type: cross Abstract: AI-generated art has sparked debates around potential plagiarism, as these images may closely resemble existing artworks. This research quantifies th...
arXiv:2608.31082v1 Announce Type: new Abstract: Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI...
arXiv:2608.29953v1 Announce Type: new Abstract: Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce Search...
arXiv:2608.29951v1 Announce Type: new Abstract: Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by representing each page as per patch embeddings and match...