Knowledge catalogue
arXiv:2608.23651v1 Announce Type: cross Abstract: Agent harnesses record a failed tool call and its error message in the transcript and ask the model to continue, on the assumption that the error is c
arXiv:2604.01024v2 Announce Type: replace Abstract: We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to lea
arXiv:2608.23841v1 Announce Type: cross Abstract: Single-token autoregressive decode on CPUs is bound by memory bandwidth, not arithmetic: a modern CPU sustains roughly 1 TFLOP/s of compute but only a
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
Today we’re introducing Gemini 3.5 Transcribe, our latest transcription model built for incredibly precise, smart dictation across your favorite apps and devices. Remember when traditional speech-to-t
What's better than an open-weight multimodal model release? Well, the technical report. I just love how these labs like Qwen and DeepSeek continue to drop gem after gem. Qwen3.8-Flash is the latest in
arXiv:2608.22994v1 Announce Type: cross Abstract: Training large language models is costly. How low a loss the same compute can ultimately reach depends on how each step's gradient is converted into a
Building a local AI agent hierarchy on a budget — RAG, quantization, and testing whether fact-grounding pushes small models toward real creativity I don't have a CS background, a GPU, or much of a bud
arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing p
arXiv:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From advers
arXiv:2608.22090v1 Announce Type: cross Abstract: Large language models can produce fluent reasoning traces whose local semantic errors propagate to an incorrect conclusion, while unconstrained self-c
arXiv:2608.22309v1 Announce Type: new Abstract: We benchmark transport-based generative models as well as distillation-based few-step methods for the probabilistic forecasting of stochastic fluid flow
arXiv:2608.20373v1 Announce Type: new Abstract: Objective: To evaluate large language model (LLM) performance on unprocessed electronic medical record (EMR) data for clinical registry abstraction. Met
arXiv:2608.20639v1 Announce Type: new Abstract: Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view map from multi-view images. Recent MVPD methods adopt
arXiv:2608.20807v1 Announce Type: new Abstract: Environmental exposures such as air pollution and greenness have been associated with affective and cognitive outcomes, but EEG and environmental datase
Dan Primack / Axios: Source: robotics startup Generalist, which released its GEN-1 model to complete physical tasks in April, raised ~200M led by 8VC, after raising 400M in June — Generalist has quiet
arXiv:2608.20365v1 Announce Type: cross Abstract: Sri Lankan parliamentary debates (Hansards) constitute a trilingual corpus of speeches in Sinhala, Tamil, and English, including code-mixed content, y
An anonymous provider has been handing out free access to a frontier-class coding model on OpenRouter Inc. since Aug. 20, and no company has admitted to building it. The model is listed as “Ox Alpha”
Im looking to set up a new local llm (probably on unsloth studio as that seemed to be doing pretty well last time I tested it). This one won't need to do agentic coding or app building or anything (no
This is the Qwen3.8-27B setup I actually use every day on one RTX 5090. I wanted to write it down with enough detail that another 5090 owner can reproduce it instead of guessing which memory knobs I u
arXiv:2608.19879v1 Announce Type: cross Abstract: This document describes the application of a first order linearised nonlinear repeated measurements approach to the analysis of battery cell ageing pr
GPT-5.6 Sol is now the most affordable frontier model on Devin Desktop and CLI. Today, OpenAI reduced Sol’s prices by 20% for the next 3 months. Last week's 70% discount still applies, so through Octo
arXiv:2608.19227v1 Announce Type: cross Abstract: Market microstructure simulation aims to model how liquidity, prices, and order flow evolve in electronic financial markets. Since market data reveal
arXiv:2512.06754v2 Announce Type: replace Abstract: Continuum manipulators offer intrinsic dexterity and safe geometric compliance for navigation within confined and obstacle-rich environments. Howeve
Multimodal API support 🔌 🔹 Set model='deepseek-v4-flash-vision-exp' 🔹 Images are tokenized for billing: up to 384 tokens each, at V4-Flash pricing 🔹 Supports Chat Completions, Messages & Responses 🔹 S
I'm introducing Aurora-80K, a small language model with exactly 80 thousand parameters. It uses a factorized 4,096-token vocabulary despite having only 80K parameters. The benchmarks: Wikitext-2 BPB:
arXiv:2608.17917v1 Announce Type: cross Abstract: Automatic Target Detection and Recognition (ATD/R) is critical for military decision support and (semi-)autonomous operations. Recent advances in obje
arXiv:2608.17366v1 Announce Type: new Abstract: Merging finetuned models combines specialized capabilities without joint training or access to the original data. Most methods operate by linear arithme
arXiv:2603.10302v3 Announce Type: replace Abstract: A plethora of protein language models have been released in recent years. Yet comparatively little work has addressed how to best sample from them t
arXiv:2608.18077v1 Announce Type: new Abstract: We introduce Hydra-0, a generalist world model conditioned on action flow, which represents robot actions as pixel motion. This shared visual interface
arXiv:2608.16972v1 Announce Type: new Abstract: Machine learning has become an essential component of modern healthcare, where the integration of heterogeneous data sources offers unprecedented opport
(my own experience) I have a mid-range gaming laptop from 2024 with 4GB VRAM and 16GB RAM. There is nothing that I can run other than small models at humble t/s. I mostly use the models to generate sc
A local 27B model scoring frontier performance! Huge thanks to @cline for the shoutout.🥳 This is just the beginning — Qwen3.8-27B will keep finding its way into more fields.🌱 Artificial Analysis Intel
arXiv:2509.20271v2 Announce Type: replace Abstract: Breast cancer is the most commonly diagnosed cancer and the leading cause of cancer-related mortality in women globally. Mammography is essential fo
arXiv:2608.16268v1 Announce Type: new Abstract: Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as p
arXiv:2509.14104v2 Announce Type: replace Abstract: Self-supervised learning (SSL) through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) foundation model (F
arXiv:2412.19505v3 Announce Type: replace Abstract: Recent successes in autoregressive (AR) generation models, such as the GPT series in natural language processing, have motivated efforts to replicat
arXiv:2608.15004v1 Announce Type: cross Abstract: Lung cancer remains one of the leading causes of cancer-related mortality worldwide, and Computed Tomography (CT) is a primary imaging tool for screen
arXiv:2608.14003v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chain-of-thought generation, but incur substantial computatio
arXiv:2607.15740v2 Announce Type: replace-cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important
arXiv:2602.15572v3 Announce Type: replace Abstract: Agent-based modelling (ABM) is a widespread approach to simulate complex systems. Advancements in computational processing and storage have facilita
Yes, it sucks to waste time waiting on 16K+ reasoning tokens alone. But here's the thing, this is only a 27B model trying to perform on par with 1T+ parameter models. Something has to be sacrificed, a
arXiv:2608.13835v1 Announce Type: new Abstract: Dynamic topic models capture evolving word distributions, but traditional coherence metrics may fail when vocabulary changes while semantic meaning pers
common: support --models-dir loading MTP assistant models (#24431) common: support --models-dir loading MTP assistant models common: preset: check for MTP models with strict prefix common: preset: Tak
Anthropic PBC today revealed that it has developed an artificial intelligence model more capable than Claude Mythos 5. The company detailed the algorithm in the latest edition of its AI alignment repo
arXiv:2608.13455v1 Announce Type: new Abstract: Medical foundation models learn latent representations of clinically meaningful phenotypes, yet their ability to support controllable image generation r
arXiv:2608.13250v1 Announce Type: cross Abstract: Normative datasets are often used to train and align AI systems, but the norms they contain can function as action-guiding patterns rather than neutra
Ollama makes it easy to run a model locally, but the hard part for me starts after the model responds: what keeps an agent from having unclear tool permissions, unbounded loops, silent partial failure
arXiv:2608.12419v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable breakthroughs across various applications. However, their architectures remain inefficient in pret
We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world
arXiv:2608.11216v1 Announce Type: new Abstract: World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe domin
— Google AI Pro and Ultra subscribers can experience 3.7 Flash today via Spark in the @GeminiApp — Access the model in the Gemini Enterprise Agent Platform and Gemini Enterprise app — Build in the Gem
Enterprise content is no longer just something people consume. As organizations increasingly rely on AI to extract and act on information from documents, images, audio, and video, Azure Content Unders
Grok 4.6 is an excellent model. I’ve been using it heavily for the past couple of weeks and it handles everything from simple coding & code review all the way to designing and debugging complex system
arXiv:2608.10947v1 Announce Type: new Abstract: Learned image compression has seen significant progress in recent years with the development of end-to-end learned models that achieve better compressio
Alibaba released the open‑weights Qwen3.8‑2.4T‑A95B (Qwen3.8‑Max), a fine‑grained mixture‑of‑experts model with 2.4 trillion parameters, hybrid full‑ and linear‑attention, a one‑million‑token context
What's Changed Models that don't set a repeat_penalty now default to 1.0 (off) instead of 1.1, matching other engines and speeding up speculative decoding; set a per-model parameter if an older model
arXiv:2608.08319v1 Announce Type: new Abstract: Brain magnetic resonance imaging (MRI) is central to neuroscience and clinical assessment, but models are commonly developed for individual diseases, po
I just heard of this model. Seems to be a competitor to DeepSeek V4 Flash. About the same size and active parameters. Anyone tested it compared to V4 Flash? Link: https://huggingface.co/upstage/Solar-
Back after ~6 months — rebuilding my spiking language model around CPU-first inference Hey everyone. It’s been around six months since I last posted anything about this project here. Some of you might