Knowledge catalogue
Anthropic PBC today announced the launch of Claude Sonnet 5.5, the most capable mid-tier model in the company’s AI family, designed for everyday tasks and a clear upgrade over the previous generation,
Anthropic: Anthropic releases Sonnet 5.5, saying it generates outputs 30%+ faster than Sonnet 5 and costs up to 30% less per task, and plans to release Haiku 5.5 soon — Sonnet 5.5 is a faster, lower-c
Anthropic's discovery of array-associated reverse transcriptases? Turns out it was already done by a Danish scientist. He used Claude for administrative tasks, but not in an agentic manner for the dis
Basically the idea is take your favorite model, for example qwen3.8-27b or say dsv4vision. Strip everything out that is not needed by that model so the only thing needed is just for the model. Optimiz
Apropos NVidia’s agent trust framework, anybody remember NemoClaw? Anyone using it? Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed w
We’re collecting real stories of builders, tinkerers, researchers, and creators who are using Codex to do incredible things. If you want to be a part of the next chapter of the Codex Originals program
Artificial Analysis: Artificial Analysis launches the Cyber Index Alliance with partners Collinear, IBM, Nvidia, and Vercel to evaluate how AI agents find and fix vulnerabilities — The Artificial Anal
I shared the first version here as a prompt builder for Qwen image editing. I've been expanding it into something more useful for visual prompting in general, and the 2.0 beta is ready to try. It's a
arXiv:2609.30566v1 Announce Type: new Abstract: We present a new inference-time sampler for diffusion models that gives a pretrained model a capability it was never trained for: constructing the atlas
arXiv:2604.05224v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly used to support search and information retrieval, it is critical that they accurately attribute con
arXiv:2609.30290v1 Announce Type: new Abstract: Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked
arXiv:2609.31110v1 Announce Type: new Abstract: Large language models are increasingly used as high-level planners for mobile robots, robot manipulators, and autonomous vehicles. Recent studies show t
vulkan: fix wrong results when a mul_mat reads a slice of a larger cache (#28956) vulkan: read the batch stride of an in place src0 from nb[2] A dim01 contiguous tensor can still be a view whose batch
tests : fix ggml init (#29554) tests : init ggml for test-recurrent-state-rollback cont : same for test-save-load-state cont : add to test-state-restore-fragmented + add TODOs Website: https://llama.a
Enables Windows ARM64 build with MSVC cl.exe (#28362) can reproduce the issue vlad sees fix fma issue drop volatile fix volatile runtime task add arm flag if needed fix hsum compile error fix syntax i
context : do not re-reserve the scheduler when toggling causal_attn (#28751) context : do not re-reserve the scheduler when toggling causal_attn llama_context::set_causal_attn() marks the scheduler to
metal: support left and circular padding in GGML_OP_PAD (#29561) metal: support left and circular padding in GGML_OP_PAD Align Metal with CPU, CUDA and Vulkan: shift the source coordinates by the left
HIP: fix template skip for DKQ > 256 mfma kernels (#29559) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50767985 macOS/iOS: macOS Apple Silicon (arm64) m
ggml-cpu: enable tiled flash attention for non-vector-multiple head dims on x86 (#29423) ggml-cpu: enable tiled flash attention for non-vector-multiple head dims on x86 add AVX2 support for masked loa
tests : refactor test-recurrent-state-rollback (#29426) tests : use llama_context_ptr in test-recurrent-state-rollback Replace raw llama_context pointers with llama_context_ptr and drop the manual lla
webgpu: Handle unaligned writes in ggml_backend_webgpu_buffer_set_tensor (#29471) Fix: Handle unaligned writes in ggml_backend_webgpu_buffer_set_tensor Clang formatting Website: https://llama.app Atte
common : fix HF cache paths on Windows (#29475) Supersedes #29158 Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/atte
batch: migrate speculative, mtmd and server to batch_ext (#29385) adapt common add common_batch wip wip: spec cont common_speculative_process server_batch to use common_batch rm some stale calls Assis
ggml-openvino: mark unaligned batch-stride views unsupported (#29603) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50908876 macOS/iOS: macOS Apple Silico
models: pad on the left with ggml_pad_ext (#29567) models: pad on the left with ggml_pad_ext The Parakeet, LFM2-Audio, Granite Speech and Gemma 4 audio encoders build a left padding as a right pad fol
vulkan: include functional header (#29597) Fixes the compile error: no template named 'function' in namespace 'std' Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attes
server : support typed content (vision/audio/video) input for /v1/embeddings endpoint (#29556) server : support multimodal input for /v1/embeddings (Qwen3-VL-Embedding) Accept the OpenAI-style wrapped
mtmd: fix GCC 15 stringop-overflow in decode_embd_batch (#29607) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50949667 macOS/iOS: macOS Apple Silicon (ar
arXiv:2512.06902v2 Announce Type: replace-cross Abstract: As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from on
arXiv:2609.30751v1 Announce Type: new Abstract: Pairwise language-model judges can gather evidence through direct comparison, reasoning, or reference-based verification, but no single protocol is best
Banger paper from Microsoft Research. (bookmark it) They run 1K+ coding agents at once to test a scalable self-organized multi-agent harness. This is an interesting test because most multi-agent syste
arXiv:2609.31180v1 Announce Type: cross Abstract: Decoding and interpreting naturalistic speech from the brain increasingly relies on alignment to pretrained speech and language representation spaces.
arXiv:2609.31546v1 Announce Type: new Abstract: Electrocardiogram (ECG) foundation models typically tokenize the signal into fixed-length patches that ignore cardiac structure, so a patch may split a
arXiv:2609.31306v1 Announce Type: new Abstract: Tabular in-context learners such as TabPFN, Mitra, or ConTextTab rely on alternating row and column attention over 2D sequences of latent embeddings. Th
arXiv:2609.30508v1 Announce Type: new Abstract: The aim of this work is to examine the connectomes of Caenorhabditis elegans through a computational lens using the reservoir computing framework. Conne
arXiv:2609.30550v1 Announce Type: new Abstract: Benchy is a semantic language and execution engine for benchmarking AI programs. A benchmark is completely specified by a program, a scoring function, a
arXiv:2609.30738v1 Announce Type: new Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score, m
arXiv:2609.30489v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated historic breakthroughs in general reasoning with early successes in biomedical science. However, existing
Yesterday I shared our open-source Clash Royale simulator and its recurrent PPO agent here. A training loop is easier to understand when you can watch it, so we put a small interactive version online:
arXiv:2609.31140v1 Announce Type: new Abstract: Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However,
arXiv:2609.30997v1 Announce Type: cross Abstract: Passive image provenance asks whether pixels alone can reveal where an image came from: a human, an aggregate AI class, or a particular generator. Thi
arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr
arXiv:2609.30650v1 Announce Type: cross Abstract: Task performance need not determine which intervention mechanism an agent retains. We study causal retention: whether a frozen learned state answers a
arXiv:2609.30913v1 Announce Type: new Abstract: Vision-language-action (VLA) policies can execute many tasks from standard initial states, yet a new instruction may fail after another task has altered
arXiv:2609.30979v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated excellent performance in visual tasks, but their visual causal reasoning capabilities still lack reliabl
arXiv:2609.31326v1 Announce Type: cross Abstract: Ordinal acne severity grading requires distinguishing visually similar neighboring grades while jointly weighing holistic facial appearance and locali
arXiv:2505.16326v3 Announce Type: replace Abstract: Recent years have seen rapid progress in multimodal large language models (MLLMs) in the field of chemistry. However, chemical MLLMs that can handle
Claude Opus 5.0 identified the IP-sharing route and declined to use it, reading our instruction not to target other external systems as ruling out third-party services. Fable and GPT-6 Astra refused t
Claude Sonnet 5.5 New Sonnet model from Anthropic today. They say it 'runs 30%+ faster, and costs up to 30% less for most work' - it's priced the same as Sonnet 5 but appears to beat it on every bench
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
arXiv:2609.31014v1 Announce Type: new Abstract: Animals such as squirrels and even bears have adapted to rapidly climb up trees and other complex vertical terrain, but achieving comparable agility has
arXiv:2609.30345v1 Announce Type: cross Abstract: Cloud-security investigation is dominated by population tasks: which identities can read a data store, how many resources fail a control, which assets
arXiv:2604.04247v2 Announce Type: replace Abstract: Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without paramete
arXiv:2609.31587v1 Announce Type: cross Abstract: We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it
arXiv:2609.31117v1 Announce Type: new Abstract: Service robots remain difficult to deploy in domestic environments, partly because fully autonomous operation is not yet reliable in unpredictable surro
arXiv:2609.30796v1 Announce Type: new Abstract: Diagnostic consultation is an online sequential decision-making process in which clinicians gather evidence through patient interaction until a diagnosi
arXiv:2609.30546v1 Announce Type: cross Abstract: In this paper, we establish the first asymptotic convergence guarantees for the Muon algorithm through a more accurate proxy for the Newton-Schultz it
arXiv:2609.30275v1 Announce Type: new Abstract: A statistic reported without the quantity needed to interpret it is not evidence. We develop that thesis for a concrete practice in AI safety. Interpret
arXiv:2609.30914v1 Announce Type: cross Abstract: Quantum-inspired algorithms emulate quantum mechanical principles, such as, superposition, interference, and probabilistic amplitude evolution, on cla
arXiv:2609.30395v1 Announce Type: new Abstract: Real-time tiny object detection in aerial imagery is constrained by the weak spatial evidence of very small objects and the loss of high-resolution deta