Knowledge catalogue
arXiv:2609.22243v1 Announce Type: new Abstract: Input-conditioned neural interventions raise a runtime question: what persists when one behavioral specification admits multiple actions whose validity
arXiv:2609.23372v1 Announce Type: new Abstract: Accurate multi-user localization is challenging in complex urban environments, where wireless measurements can become ambiguous under noise, blockage, a
arXiv:2609.22087v1 Announce Type: cross Abstract: Training under non-stationary but predictable compute availability (satellites under eclipse, duty-cycled edge devices, power-capped datacenters) is o
Grok 4.7 xHigh is now at the top with just ONE point away from Claude Fable 5.1 Max on Artificial Analysis’ AA-Briefcase benchmark Claude Fable 5.1 Max — 59% Grok 4.7 xHigh — 58% Just a 1-point differ
arXiv:2609.21212v1 Announce Type: cross Abstract: Learned navigation policies typically consume observations as a temporally ordered history, with positional encodings tying each observation to when i
arXiv:2601.22488v3 Announce Type: replace Abstract: Modern sequence models are typically trained at a fixed computational capacity, while real-world applications require deployment across platforms wi
Vacations give you time to think and explore. I came across a few things and made a few discoveries of my own. It turns out that, as a programmer, I no longer need the smartest and most expensive AI m
arXiv:2609.17590v1 Announce Type: cross Abstract: Evolutionary Ensemble Search (EES) constructs machine-learning procedures through expert-guided program evolution. A role-specialized council turns ta
As enterprise organizations scale mission-critical applications, storage I/O and memory access can become severe operational bottlenecks. Whether its Oracle databases, in-memory databases like SAP HAN
arXiv:2609.13664v1 Announce Type: new Abstract: Knowledge graphs are increasingly distributed across autonomous organizations that share an entity space but own disjoint subsets of relations, forming
arXiv:2609.15485v1 Announce Type: new Abstract: Avalanche forecasting requires knowledge of snowpack conditions and recent avalanche activity, but field observations are sparse across large mountain r
Some food for thought when designing benchmarks... So, here's a little computer-use (visual) comparison between GPT-5.6 Astra and Qwen3.8 Max. The task here was to recreate the image in the center usi
arXiv:2603.15412v2 Announce Type: replace Abstract: The mammalian brain, most extensively studied in rodents and bats, solves an enormous variety of non-spatial cognitive tasks using neural circuitry,
sycl: rfc: Use radix select for top_k (#28670) sycl: GPU-resident TOP_K for large k, parallelised over the device The SYCL backend refused GGML_OP_TOP_K above k = 32 and let it fall back to the CPU, a
arXiv:2609.12446v1 Announce Type: cross Abstract: Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We p
arXiv:2603.15976v2 Announce Type: replace Abstract: While LLMs have accelerated scientific code generation, comprehensively evaluating generated code remains challenging. Many benchmarks emphasize fun
arXiv:2609.11899v1 Announce Type: new Abstract: Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses te
arXiv:2609.11736v1 Announce Type: cross Abstract: We develop a quantum approach to spectral feature extraction from the density of states (DOS) of a problem-dependent Hamiltonian, and apply it to mach
arXiv:2609.09137v1 Announce Type: new Abstract: Robotic Process Automation (RPA) is widely used to reduce administrative burden in United States hospitals, yet an estimated 30-50% of RPA initiatives u
So I was playingw ith embedding models I saw that when you upgrade from model A to B, you face a very big backfilling cost Ie, suppose you have a 1b vectors from model A, and then you want to use mode
arXiv:2609.09569v1 Announce Type: new Abstract: News articles often contain omitted temporal expressions, such as day-only or month-only mentions, which must be interpreted with reference to the publi
arXiv:2609.09985v1 Announce Type: new Abstract: Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a f
arXiv:2609.06670v1 Announce Type: new Abstract: The In-context learning (ICL) paradigm aids large language models (LLMs) to adapt to new tasks without need for fine-tuning. However, selecting an optim
arXiv:2609.07276v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) depends on dense retrieval: each document is stored as a learned vector, and a query is answered by finding its n
arXiv:2609.07078v1 Announce Type: new Abstract: For learning generalizable motion representations from large-scale unlabeled data, Self-supervised learning (SSL) has become a widely adopted methodolog
TorchServe is no longer maintained, leaving teams to own the entire GPU inference stack. The AWS Ray Serve Deep Learning Container is a supported, pre-tested container with the framework, GPU drivers,
arXiv:2609.05541v1 Announce Type: new Abstract: Implicit Neural Representations (INR) provide a compact and content-adaptive paradigm for video compression, typically representing a video through shar
We’ve been building PipesHub for a while now, and I’d love to get more teams to try it and tell us where it breaks. The problem we kept running into was pretty simple: Building an AI app over company
So I've been messinga round with embedding models for a bit, and I think they are interesting enough to experiment with. They are useful for rag, especially in a localllm sense because you can ground
arXiv:2609.04999v1 Announce Type: new Abstract: This paper describes the participation of the BIT.UA team from the University of Aveiro in the 14th edition of the BioASQ Task B challenge on biomedical
https://preview.redd.it/3p6234jzk2oh1.png?width=900&format=png&auto=webp&s=b9eab3351d6c6dbd4d5b3fd677a6c40b57f18167 https://huggingface.co/tencent/EVIE-8B 🌟 Highlights SOTA Retrieval Performance: 66.7
Loops and graphs. Sam Altman is now the ultimate advocate for (neuro)symbolic AI and he doesn’t even know it. Sam Altman (CEO of OpenAI): 'You don't need to write prompts anymore. You need loops and g
arXiv:2609.01925v1 Announce Type: cross Abstract: The attention prefilling phase of long-context LLM inference scales quadratically, making self-attention a severe computational bottleneck. Traditiona
arXiv:2609.01617v1 Announce Type: cross Abstract: Getting accurate, grounded answers out of large enterprise document repositories is a difficult problem. Dense vector retrieval alone frequently perfo
If you are like me and use Google flow for NB2/NBP there is hope to finally ditch it. Let me start off by saying I’m not very impressed with any of the current local image edit or Image Reference mode
arXiv:2609.02486v1 Announce Type: cross Abstract: Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to
Anthropic publish the system prompts for their Claude consumer applications (Claude.ai and the Claude mobile apps - sadly not for Claude Cowork or Claude Code). I love that they do this, and that they
arXiv:2609.00950v1 Announce Type: new Abstract: Executing long-term tasks in dynamic environments requires embodied agents to maintain robust and adaptive 3D scene representations. However, most exist
arXiv:2609.00638v1 Announce Type: cross Abstract: Retrieval is the first stage of modern search and advertising systems, selecting a candidate set from a large item universe for downstream ranking and
arXiv:2608.30181v1 Announce Type: new Abstract: We introduce A.X K2, a 688B-parameter Mixture-of-Experts (MoE) language model trained from scratch as a high-performance foundation for agentic applicat
arXiv:2608.28968v1 Announce Type: new Abstract: Semantic Search on LinkedIn must retrieve relevant profiles from a corpus of hundreds of millions in response to natural-language queries such as 'a fin
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 matchi
arXiv:2608.27690v1 Announce Type: cross Abstract: Cardiovascular risk prediction remains limited by incomplete clinical data and imaging biomarkers that reduce computed tomography (CT) to a small numb
arXiv:2608.28564v1 Announce Type: cross Abstract: We study kernel ridge regression under anisotropic Gaussian data, where the input covariance decays as a power law with exponent alphageq 0 for polyno
I used the quantized n-gram to INT4, it's 32 GB, memory-mapped from disk. I confirmed that it works great on 150-160k context, and i was watching all the time my VRAM usage while doing single thread l
arXiv:2608.26355v1 Announce Type: new Abstract: While LVLMs rapidly improve, long-video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often f
I built a benchmark called EchoNet. An agent gets a factual question, then searches a syntheic web I made before answering. Some of that web is seeded with misinformation: one fake page, a fake page r
arXiv:2509.07274v4 Announce Type: replace Abstract: Migration has been a core topic in German political debate, from postwar expellee displacement to labor migration and recent refugee movements. Larg
TL;DR: llama.cpp with --load-mode mmap used 21-32 GB of RAM, with ik_llama.cpp using 106-108 GB. -sm tensor killed my prefill, changing to -sm layer went from 36 tps to 135 tps. After that, -ubatch 20
arXiv:2608.26481v1 Announce Type: new Abstract: When a single policy is trained in parallel across multiple environments of the same task, such as procedurally generated levels, randomized dynamics, o
arXiv:2608.27187v1 Announce Type: new Abstract: Peer effects are difficult to estimate when interaction graphs evolve because pre-assignment network history, dynamic peer exposure, and post-assignment
arXiv:2604.03403v2 Announce Type: replace-cross Abstract: Dense retrieval systems increasingly face an asymmetry between complex instruction-like queries and relatively simple, static document collect
Instinct, the developer of an artificial intelligence assistant popular among Silicon Valley tech workers, is reportedly raising 250 million in funding. The company told the Wall Street Journal on Wed
arXiv:2608.24901v1 Announce Type: new Abstract: A decodable 'empathy' direction is routinely read as a causal lever, conflating decodability, automated-metric control, and human-perceived change. We t
Ever since Qwen 3.8 Flash Next dropped, there's a misconception going around that N-gram tables will let people run 1T+ parameter models on a single server with 980B parameters offloaded to SSD. I'm h
Megathread for discussing the release of GLM-5.3-Flash. Quants Fine-Tunes & Abliterations Chat Templates Inference Server Support & Configuration Experiences, Benchmarks & Model Comparisons We'll try
arXiv:2608.23761v1 Announce Type: cross Abstract: Highly overparameterized models often predict well despite interpolating training data in complex domains, challenging the classical bias--variance tr
arXiv:2608.24133v1 Announce Type: cross Abstract: People search for urban outdoor places not only by category or function, but also by what activities a place can support and how it is perceived. Exis
What happens when there are more agents than eyeballs browsing the internet? How will the economics of the internet be reinvented? @paraga thinks Shapley values may hold the answer. Parag built Twitte
arXiv:2608.23421v1 Announce Type: new Abstract: Natural Language Processing (NLP) has grown rapidly over the past decade, driven by digital transformation in the Arab world, social media, and large la