model releases

Ornith does really well. TielCoder (https://llm-bench.io/benchmarks/cmt7kp2zj002r01lcmpchvlko) might be even a bit better in coding. Will give it a try soon. Details of the comparison see here: https:

With vision enabled I am able to run at 150k context on a single RTX 3090 and the results are just amazing. I was even able to write a gmail plugin for DeepSeek harness with locally hosted Qwen 3.8 27

arXiv:2603.11252v2 Announce Type: replace Abstract: Although semantic 3D city models are internationally available and becoming increasingly detailed, the incorporation of material information remains

arXiv:2608.21305v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has demonstrated significant gains in image captioning, yet it is still limited in encouraging Large Vision-Language Model

Thanks to Unsloth Dynamic 3.0 quants coming in slightly leaner and better preserved, I settled on Qwen 3.8 27B (`UD_Q4_K_XL`) at 100K context as my daily driver for Hermes Agent and OpenCode. On an RT

arXiv:2608.20680v1 Announce Type: new Abstract: We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not

arXiv:2608.20389v1 Announce Type: new Abstract: A production agent harness must discover and rank, from a growing library of skills, the one most appropriate for a user's task. At small scale this sel

arXiv:2608.20368v1 Announce Type: new Abstract: Knowledge and innovations are shaped by using the quality and credibility of the scientific research. Yet, distinguishing between impactful, high-qualit

Mark Anderson / Bloomberg: Researchers detail the growing use of AI in cyberattacks across many Chinese state-linked groups, primarily using open-weight models like Kimi K3 and DeepSeek — Chinese hack

arXiv:2608.20812v1 Announce Type: new Abstract: We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many

arXiv:2608.20418v1 Announce Type: cross Abstract: We introduce Malaria-Instruct, a curated instruction-following dataset derived from the ChEMBL Legacy Malaria corpus for Malaria virtual screening, an

arXiv:2608.20656v1 Announce Type: cross Abstract: Traffic sensors commonly record flow, speed, and occupancy, but standard traffic flow forecasting benchmarks and models rarely exploit all three raw m

arXiv:2608.21032v1 Announce Type: new Abstract: Vehicle-to-Everything (V2X) cooperation enables beyond-line-of-sight perception, mitigating occlusions in single-vehicle sensing. However, existing V2X

arXiv:2608.21024v1 Announce Type: new Abstract: Modern neural network training increasingly uses matrix-aware optimizers, yet their conditioned matrix step is typically added directly to the weight, j

arXiv:2608.20359v1 Announce Type: new Abstract: Large language models (LLMs) are deployed for increasingly complex tasks involving planning and multi-step decision making, but high-quality performance

arXiv:2601.09487v2 Announce Type: replace Abstract: The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts

arXiv:2504.05978v4 Announce Type: replace Abstract: Reinforcement learning (RL) is a powerful framework for decision-making in uncertain environments, but it often requires large amounts of data to le

arXiv:2608.21044v1 Announce Type: new Abstract: Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model sequentially adapts to an unbounded stream of sess

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:2608.20754v1 Announce Type: new Abstract: Promptable segmentation models provide a reusable interface, but direct transfer to automatic infrared small-target segmentation (IRSTD) exposes a misma

arXiv:2608.20632v1 Announce Type: new Abstract: Efficient-transformer research often motivates token pruning and adaptive computation with the claim that not all tokens require equal computational eff

arXiv:2608.21208v1 Announce Type: cross Abstract: This paper investigates cross-agent specification portability using Oracle-to-PostgreSQL migration as a controlled software transformation task. The s

arXiv:2608.21175v1 Announce Type: cross Abstract: Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneou

arXiv:2608.20414v1 Announce Type: new Abstract: Vision-language models are increasingly used for multimodal question answering, yet their ability to reconstruct latent spatial structure from a single

arXiv:2608.20477v1 Announce Type: new Abstract: Neural operators have emerged as efficient surrogates for time-dependent physical systems governed by partial differential equations (PDEs), but their f

still more bad news for Anthropic. if they don’t scale back expectations for their IPO, it’s going to be a trainwreck. NEW: Thomson Reuters wanted to rely less on Claude. So it built its own AI model

arXiv:2608.20442v1 Announce Type: new Abstract: Subliminal trait transfer allows a student model to acquire behavioral dispositions from teacher-generated data in which the trait is not semantically e

arXiv:2502.04131v2 Announce Type: replace Abstract: The successful application of modern machine learning for time series classification is often hampered by limitations in quality and quantity of ava

arXiv:2608.21035v1 Announce Type: new Abstract: Long-horizon manipulation tasks are often only partially ordered. For example, when assembling an electronic device, the battery and circuit board may b

arXiv:2608.20485v1 Announce Type: new Abstract: Large language model agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, to

arXiv:2608.20376v1 Announce Type: new Abstract: LLM agents can now generate realistic shilling profiles, fluent reviews, and coherent ratings at scale, systematically defeating recommender-system defe

arXiv:2608.21262v1 Announce Type: cross Abstract: Many machine-learning systems set a threshold at a quantile of a calibration set: conformal predictors that promise 90% coverage by drawing their cuto

arXiv:2501.10573v2 Announce Type: replace Abstract: We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension. Viewing transfo

Hi, Back in late march I begun playing around with Qwen 3.6 27b and found like everyone else that it's notoriously good at tool calls, where every model I tried before just derailed after a few turns

Try it here: https://ocean.blackbeardlabs.dev/ Model: Qwen 3.8 27b Q8_X_KL Unsloth Hardware: 3 x RTX3090 Harness: DeepSeek Harness Prompt: /goal I want you to create a **JavaScript + Node.js WebGL pro

Global content powerhouse Thomson Reuters Corp. today launched Thomson, its first proprietary large language model, combining the company’s trove of legal knowledge with LLMs from outside providers to

Today, we’re announcing a strategic collaboration with @HUMAIN spanning AI infrastructure, advanced model development, and the deployment of AI solutions in Saudi Arabia and across the region. Togethe

arXiv:2608.21180v1 Announce Type: cross Abstract: LGE cardiac MRI is widely used for left atrial fibrosis assessment and ablation planning in atrial fibrillation patients as knowledge of fibrotic tiss

arXiv:2608.20494v1 Announce Type: cross Abstract: Multi-agent LLM systems are an emerging networked workload whose rapid deployment raises questions about the traffic patterns they generate. Compared

arXiv:2608.20809v1 Announce Type: cross Abstract: Breast ultrasound diagnosis relies on clinically meaningful semantic concepts, yet most deep learning methods adopt end-to-end image-to-label paradigm

arXiv:2608.20965v1 Announce Type: new Abstract: We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete occurrence, generated result and rela

arXiv:2608.20777v1 Announce Type: new Abstract: As scientific literature grows and papers increasingly under-report limitations, multi-agent LLMs offer a promising approach to systematically uncover t

arXiv:2608.21008v1 Announce Type: new Abstract: Mobile AR frameworks attach a metric pose prior to every casual phone capture, and turning it into reconstruction-grade poses cheaply on CPU is the step

arXiv:2608.21095v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge, but RAG systems usually trust whatever they ret

arXiv:2608.20378v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) is often superficial, relying on refusal mechanisms that trigger only at the final stages of generation

arXiv:2504.09772v3 Announce Type: replace Abstract: Test-Time Scaling has emerged as a powerful method to extend the reasoning capabilities of Large Language Models. However, single-agent TTS faces si