Search: “index”

arXiv:2601.20107v2 Announce Type: replace-cross Abstract: Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index sto

arXiv:2605.19735v1 Announce Type: cross Abstract: Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on larg

arXiv:2605.17415v1 Announce Type: cross Abstract: We propose IVF-TQ, an IVF index with a codebook-free residual layer: a fixed random rotation followed by precomputed Lloyd-Max scalar quantization dep

arXiv:2605.14983v1 Announce Type: cross Abstract: An index is a function that given an election outputs a value between 0 and 1, indicating the extent to which this election has a particular feature.

arXiv:2605.11502v1 Announce Type: new Abstract: Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowl

Full text search systems enable efficient querying of large document collections by indexing and searching text content across multiple fields and documents. This article from Pinecone likely covers t

Builder tier. $20/month, flat. Pricing should match the stage of building, not just the scale of it. For the stretch when free feels tight but you're not yet at usage-based scale. 10 indexes, 1,000 na

arXiv:2605.00662v1 Announce Type: cross Abstract: Sequence learning reduces to similarity-based retrieval over a temporally indexed representation space, a constraint on any sequence model, not a prop

A lot of work around AI in 2023 was spent on building picks and shovels. I would know this because that was basically the core goal of the original @llama_index framework. Today, a lot of that is no l

arXiv:2604.26382v1 Announce Type: cross Abstract: Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's

arXiv:2408.08686v4 Announce Type: replace-cross Abstract: Language Models (LMs) have been widely used in recommender systems to incorporate textual information of items into item IDs, leveraging their

arXiv:2604.20844v1 Announce Type: cross Abstract: Recent GraphRAG methods integrate graph structures into text indexing and retrieval, using knowledge graph triples to connect text chunks, thereby imp

The referenced tweet (https://x.com/rodriguespn23/status/2042575609067352561) is not publicly accessible via web search, and no cached or indexed version of its specific content was found. Based on...

The specific tweet from @c_valenzuelab (tweet ID 2042752829362778196) is not publicly accessible via web search — X/Twitter restricts direct content retrieval, and no cached or indexed version of t...

I was unable to retrieve the specific tweet at the URL provided (status ID 2042151857074639221). This tweet ID is from the future relative to current indexed content, the post may have been deleted...

Applying PCA as a rotation step before naively truncating embeddings from non-Matryoshka models like BGE-M3 can recover much of the retrieval quality that is otherwise lost when simply chopping dim...

I was unable to retrieve the specific tweet from the provided X (Twitter) URL, and the web search did not surface its exact content. The tweet ID `2042312014979051778` does not appear in any indexe...

I was unable to retrieve the specific tweet at the URL provided. The tweet ID `2042219773627449404` does not appear to be publicly accessible or indexed, and the search results do not surface its s...

Niel Pal hosted the Agent Economy Gala last week—a rare Black‑Tie event held in San Francisco that drew approximately 300 builders and investors. The evening featured participants from the llama_index

arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ

arXiv:2610.13690v1 Announce Type: new Abstract: Diffusion models typically learn the generative dynamics of a single target distribution or a family of distributions indexed by conditioning variables

Introducing Decision 3.0: towards open multimodal foundation decision models ⚡ Open and state-of-the-art from 0.6B to 27B: #1 on both Jev Decision Index boards in our evaluation, on a new Pareto front

musa: use the tile lightning indexer kernel (#30080) Signed-off-by: Xiaodong Ye xiaodong.ye@mthreads.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/535

arXiv:2610.07565v1 Announce Type: cross Abstract: Complementary Feature Domains (CFD) theory characterizes predictive value as a context-indexed contribution system induced jointly by representations

Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully curate the papers, so you can expect mostly bangers. The index

I’m hitting rate limits on Together AI. For context, I’ve been working on an agentic repository indexing and benchmark generation tool, and I’m running multiple agents in parallel across models like L

arXiv:2610.06902v1 Announce Type: new Abstract: Retrieval-augmented generation grounds language models in external context, but for long documents flat top-k retrieval can cluster on a single region a

We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use these to index multimodal data with 9B, and query on device

arXiv:2511.16976v3 Announce Type: replace Abstract: Deep equilibrium models (DEQs) have recently emerged as a powerful paradigm for training infinitely deep weight-tied neural networks that achieve st

On my two DGX Sparks, Swift 1.5 (UkisAI's reasoning-efficient fine-tune of Qwen3.8-Flash-Next) running on veloGB10 (https://github.com/sf-stav/veloGB10, sf-stav's Rust/CUDA engine built only for GB10)

arXiv:2610.03329v1 Announce Type: cross Abstract: Large language models are increasingly used where small syntactic errors matter, yet character-level reasoning is still evaluated mostly through isola

arXiv:2610.01831v1 Announce Type: new Abstract: Group attention, introduced by the time series forecasting model Chronos-2, attends over the variates of a group at a fixed patch index and serves both

arXiv:2610.00398v1 Announce Type: new Abstract: Overnight impedance pneumography (IP) is used to monitor paediatric respiratory health. Its current clinical readout, the Expiratory Variability Index (

arXiv:2609.38181v1 Announce Type: new Abstract: Survival analysis estimates time-to-event outcomes from patient covariates and is widely used for medical risk assessment. Patients seeking prognostic i

add GLM-5.3-Flash (GLM5-Next) support (#27773) Rebase GLM-Next support onto master, and migrate to llama-memory-hybrid-idx Add initial MTP support Merge branch optimizations. Reduce allocated compute

arXiv:2510.04525v3 Announce Type: replace Abstract: Masked diffusion models have shown promising performance in generating high-quality samples in a wide range of domains, but accelerating their sampl

arXiv:2609.34602v1 Announce Type: new Abstract: Frozen Earth-observation embeddings are judged almost entirely by spatially blocked cross-validation inside one study region. We show that this number d

Claude Sonnet 5.5 is live in Hermes Agent Enjoy Anthropic has launched Claude Sonnet 5.5: it scores 56 on the Artificial Analysis Intelligence Index, just 2 points behind Opus 5.5 (max), but at the hi

Not bad Grok 4.7 xHigh ranks #1 in Artificial Analysis Cyber Index It's a powerful frontier model performing at the highest level in enterprise cyber defense Outperforming Fable 5.1 Max, Opus 5.5, Ast

arXiv:2609.30576v1 Announce Type: new Abstract: Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation

I maintain a starter kit where the LLM provider is a runtime-swappable DB row, not a hardcoded constant — OpenAI, Anthropic, or a local Ollama instance. Mostly so I can demo without burning API credit

In real-time streaming, every millisecond counts. For example, at 30 frames per second (fps), developers have a strict frame budget of just 33.3 ms (and only 16.6 ms at 60 fps) to ingest camera frames

Excited for next Tuesday, Sept 29, and our monthly @daytonaio AI Builders Demo Night in SF! We’re hosting at @WorkOS SF Office in partnership with @llama_index. Join us for an evening of great demos,

Upload a short file and ChatGPT reads all of it. Upload a long one, a contract, a thesis, a 200 page report, and most of it goes into a search index instead. Every answer is then built from whichever

arXiv:2609.23971v1 Announce Type: cross Abstract: Two transformative classes of AI systems are reshaping how organizations operate: extit{digital AI}, which reasons over enterprise knowledge to power

Grok 4.7 places @SpaceXAI as third, after Anthropic & OpenAI, for agentic coding. When factoring in that Grok is significantly faster & lower cost, it’s a great choice for your everyday workhorse. Gro