Knowledge catalogue
arXiv:2609.19234v1 Announce Type: cross Abstract: This paper presents the AR fairness metamodel, a framework designed to represent, analyze, and compare different fairness scenarios. The metamodel con
arXiv:2609.16875v1 Announce Type: new Abstract: Upgrading embedding models typically requires expensive database re-indexing, as new query embeddings are incompatible with existing database embeddings
arXiv:2609.13263v1 Announce Type: new Abstract: Projective shape analysis provides a geometric framework for studying landmark configurations in digital images acquired by pinhole cameras. In the clas
The current AI and I suspect that all AI of the near future (few human generations that is) is in fact a more sophisticated form of data access methods in the same category as classic database indexes
arXiv:2609.14780v1 Announce Type: cross Abstract: Multi-tenant tools commonly accept a tenant identifier and validate it against the caller's entitlement. For a large language model (LLM) agent, that
arXiv:2505.15002v3 Announce Type: replace-cross Abstract: Combinatory Homomorphic Automatic Differentiation (CHAD) was originally formulated as a semantics-driven source-to-source transformation for r
The full K2 Horizon lineup is out on Artificial Analysis. The AA intelligence vs. parameters plots show that - 0.9B and 375B are bad - 3.7B and 7B are SOTA - 36B A4B is SOTA for hardware with poor mem
arXiv:2609.12913v1 Announce Type: new Abstract: Dense retrieval systems increasingly rely on multi-billion-parameter language models, whose memory and computational requirements make large-scale index
arXiv:2609.11365v1 Announce Type: new Abstract: In shared-genome language-model societies, restricted evidence visibility favors reusable, value-indexed latent packet interfaces, whereas the sole high
arXiv:2609.11689v1 Announce Type: cross Abstract: Area-based social risk indices summarize residents' socioeconomic conditions but incompletely capture physical features of place that may affect healt
Some people says terminal bench reflects model intelligence better than the intelligent index. From the look of it, the ranking does seem to reflect how people feel about the open and closed models. F
memory : avoid allocating V cache for indexer (it's not used) (#28330) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.
// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear
arXiv:2609.07262v1 Announce Type: cross Abstract: Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage a
https://github.com/paulknysh/raggy A lightweight CLI tool for Retrieval-Augmented Generation (RAG) over local documents built with Ollama. Hybrid database (vector + BM25 index) and embedding generatio
You can now use the Perplexity Search API in Hermes Agent Perplexity Search API is now available in Hermes Agent. Search API gives Hermes access to an index of more than 400 billion URLs. It returns r
tests : initialize the L2_NORM batch array (#28553) tests: bind the L2_NORM batch count to a local GCC cannot prove the loop fills norms up to the index read after it while the bound is a class member
sycl: fuse rms_norm+mul+add and add+add residual chains (#27610) Fuse RMS_NORM+MUL+ADD and ADD+ADD under GGML_SYCL_ENABLE_FUSION. ADD+ADD uses the same binbcast indexing and type matrix as standalone
model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444) hparams: add per-layer n_ff_exp/n_expert_used arrays with scalar-or-array loading G1/G2 infrastructure for variable-per-l
arXiv:2609.00342v1 Announce Type: new Abstract: Whole-slide images (WSIs) are challenging for vision-language reasoning because diagnostically relevant morphology is sparse, heterogeneous, and distrib
NVIDIA’s modern CUDA Toolkit (via CCCL launch API and indexing model) eliminates out‑of‑bounds shared‑memory errors and replaces hand‑written kernels with CUB block‑level primitives, reducing per‐imag
arXiv:2603.26024v2 Announce Type: replace Abstract: Identification of causal directionality in bivariate numerical data is a fundamental research problem with important practical implications. This pa
arXiv:2608.28622v1 Announce Type: cross Abstract: Large language model training corpora grow through successive, often redundant releases, so each release must be deduplicated against both itself and
Qdrant has released **Qdrant‑Fineweb‑10B**, a public benchmark dataset comprising dense and sparse embeddings for 10 billion documents from the FineWeb corpus and exact results for 120,000 queries to
Thanks @juliafedorin for a great conversation! Some tidbits from the podcast on the AI space: - We've pivoted from building a RAG framework towards building the document infrastructure for agents - Do
vulkan: Change mul_mat_id to pad K rather than N (#27925) The N padding is needed for mul_mat, but not mul_mat_id. For mul_mat_id, we indirect the row index through a shared memory lookup table which
arXiv:2608.25888v1 Announce Type: new Abstract: Timely detection of crop stress is critical for sustaining yields under increasing drought frequency, yet conventional vegetation index thresholds or im
arXiv:2608.23619v1 Announce Type: cross Abstract: Legacy software repositories embed decades of domain knowledge in undocumented code, making understanding and modernization difficult. We treat a prog
arXiv:2608.24782v1 Announce Type: new Abstract: Traditional image similarity metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Measure (S
arXiv:2608.24428v1 Announce Type: cross Abstract: Using monthly Nino-3.4 anomalies through July 2026, we investigate how much predictive information is contained in delayed observations of the index.
https://preview.redd.it/i8rjx0ar5mlh1.png?width=2160&format=png&auto=webp&s=c2588bc7b2519ea71b176ca73faf566dfc585496 I wanted to see whether a heavily quantized 27B model running entirely on an older
arXiv:2608.24113v1 Announce Type: cross Abstract: Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring temporal structure, such as shifted periodicity or
arXiv:2507.09924v2 Announce Type: replace-cross Abstract: Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally
arXiv:2603.06813v2 Announce Type: replace Abstract: In a stationary decentralized Markov game, learning peers generate an episode-indexed sequence of induced MDPs for any focal agent. The joint game r
arXiv:2608.22856v1 Announce Type: cross Abstract: A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval poli
Companion to the Qwen 3.8 Release Megathread. Compiled from ~2,000 posts scanned across both subs, with deep reads of the 45 highest-signal threads (560 posts and comments), Aug 15–22, 2026, plus inde
https://preview.redd.it/84zi5nsdawkh1.png?width=2368&format=png&auto=webp&s=1109e69db807b153064b1f5b61d22cf1e9fbca05 Another user posted the benchmarks for Qwen 3.8 27B today, and while I think Qwen 2
Grok 4.6 Grok 4.6 just tied for #1 on the Artificial Analysis Agentic Index • Grok 4.6 (high) — 59 • Claude Opus 5 (max) — 59 Outperforming Claude Fable 5 and GPT-5.6 Sol We’re entering the agentic er
arXiv:2608.18041v1 Announce Type: new Abstract: Language has two parameters. Count how often words occur together and you estimate amplitude, the strength of association. Word embeddings and attention
Strong enough to keep up with the frontier, light enough to run on your own laptop. Come see what it can do! ⚡ It's official: Qwen3.8-27B just scored 52 on the @ArtificialAnlys Intelligence Index. We
The amazingly fast (only 30M!) and extremely accurate @answerdotai ColBERT model is now supported in Sentence Transformers to make it easy to create and query embedding indexes locally directly in Pyt
arXiv:2608.16096v1 Announce Type: cross Abstract: Enterprises connect language models to their own data through retrieval. The benchmarks that rank multi-hop retrieval systems leave out two facts a bu
arXiv:2608.14011v1 Announce Type: cross Abstract: Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the
Artificial analysis index scores Qwen 3.5 27b: 35 Qwen 3.6 27b: 38 Qwen 3.8 27b: 52 What the hell kind of a jump was that? Even if it is benchmaxxed, the jump is insane. Qwen3.6 35b A3b: 32 That's ~6
Overview EVIE-Preview-4.5B is a state-of-the-art multilingual Visual Document Retrieval (VDR) model built upon Qwen3.5-4B. It employs ColBERT-style late interaction with native 128-dimensional multi-v
arXiv:2608.12987v1 Announce Type: cross Abstract: Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by trai
arXiv:2608.12990v1 Announce Type: new Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consol
anthropic’s best hope is that OpenAI falls apart. which it might. NEW from Ramp AI Index: disappointing adoption of Fable 5 We've heard several reasons from businesses...mainly Fable 5 is just too exp
arXiv:2608.12001v1 Announce Type: cross Abstract: Rapid urbanization in Dhaka District, Bangladesh has triggered substantial alterations in land use and environmental conditions, necessitating systema
arXiv:2608.08809v1 Announce Type: new Abstract: A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the rig
arXiv:2608.08826v1 Announce Type: new Abstract: Adaptive procedures must work without nuisance information an oracle may use, such as a gradient scale or smoothness index, and robust procedures may ha
ggml : require contiguous src for ROLL on CUDA and Metal (#25928) ggml_roll only asserts nb[0] == ggml_type_size, so a permuted src is a valid input, but the CUDA and Metal roll kernels index by ne al
llama : support multi-output backend sampling (#25532) Enable backend sampling with token speculation Clamp the mask sum before converting it into the sampled index Add a numeric context parameter dec
arXiv:2608.02641v1 Announce Type: cross Abstract: Large language models (LLMs) can translate natural-language optimization problems into solver-ready formulations, but direct code generation is brittl
arXiv:2608.00446v1 Announce Type: new Abstract: Lung cancer results in roughly 1.8 million fatalities annually worldwide, with non-small cell lung cancer (NSCLC) comprising the majority of cases. Desp
arXiv:2607.28671v1 Announce Type: cross Abstract: Accurate fracture risk prediction is important for osteoporosis management, but commonly used clinical tools may not fully use information available i
arXiv:2607.28641v1 Announce Type: cross Abstract: We introduce the extit{Agentic Formalism Trap} and the Evaluative Dissonance Index (D_E), quantifying how LLM-as-a-Judge systems conflate structural p
Eleanor Olcott / Financial Times: Chinese VC firms are rushing to raise new funds after three years of record-low fundraising, amid renewed enthusiasm for China's tech, AI, and robotics sectors — Mana
March 6th, 2026 the highest intelligence index score was 51 for frontier models. deepseek-ai/DeepSeek-V4-Flash-0731 that has an intelligence score of 50. If these benchmarks are accurate, models avail
arXiv:2607.27463v1 Announce Type: new Abstract: Dimensionality Reduction (DR) is a fundamental tool for high-dimensional data exploration, reducing the complexity of latent spaces of machine learning