Search: “models”

arXiv:2410.21582v4 Announce Type: replace-cross Abstract: Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintai

Disclosure: This unit was provided free of charge by Orange Pi for testing. No editorial review, no preconditions, no script. All data, bottlenecks, and thermal behavior are reported directly from har

arXiv:2609.35805v1 Announce Type: cross Abstract: Training a language model on data with a narrow flaw can sometimes make the model broadly misaligned. Inspecting the data at face value often does not

arXiv:2603.02790v2 Announce Type: replace Abstract: Foundation models are changing the way we develop medical artificial intelligence. By learning broadly generalizable features across diverse data mo

Overview llama.cpp 0.4.0 adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml update to 0.23.0 with

arXiv:2609.01404v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends into acting: dropping an MLLM di

In the past, I have use llama.cpp, but I read that the exl3 quantization format should give better precision, so I have tried exllamav3/tabbyAPI. It was able to write the shown simple HTML game withou

The post describes some experiments I had while trying to desperately run deepseek-v4-flash-0731 4 bit+ quants on my machine which is supposed to support only q2 quants of the model, a or 2.xx bpw qua

Whoa, Meta released a new open-weight LLM yesterday, something that hasn't happened since the good old Llama days. Their Meta Muse Glimmer model is a 30B multimodal reasoning model with a Gemma-like a

arXiv:2607.22585v1 Announce Type: new Abstract: Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools,

arXiv:2607.12545v1 Announce Type: cross Abstract: Adversarial robustness research has produced hundreds of defended models over the past decade, yet the literature almost universally reports robustnes

arXiv:2606.12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific for

I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow,

LLMs have become more powerful at smaller sizes, but deploying them to edge devices like smartphones remains a massive challenge. Today, developers have to optimize across a sprawling combination of a

arXiv:2605.08873v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has emerged as a powerful algorithm for improving the reasoning capabilities of language models, but often fai

arXiv:2604.18566v1 Announce Type: cross Abstract: We present a systematic evaluation of large language model families -- spanning both proprietary cloud APIs and locally-hosted open-source models -- o

arXiv:2509.23542v2 Announce Type: replace Abstract: The LLM-as-a-judge paradigm is widely used in both evaluating free-text model responses and reward modeling for model alignment and fine-tuning. Rec

arXiv:2604.06796v1 Announce Type: cross Abstract: Latent variable models, including variational autoencoders (VAE), remain a central tool in modern deep generative modeling due to their scalability an

On October 17, 2026, Ollama (via its Twitter account @ollama) announced that it was rolling out an updated model to customers currently using the DeepSeek‑v4.1‑Flash language model. The update is avai

America’s next top model, Reflection’s Beam, is now live on Together AI. Trained on Together GPU Clusters, Beam is Reflection’s first open-weight model. • ~501B-parameter MoE, 23B active • Built for c

arXiv:2609.33465v3 Announce Type: replace Abstract: Improving language model efficiency requires not only cheaper operations but also eliminating redundant computation. We argue that effective modelin

arXiv:2610.20753v1 Announce Type: cross Abstract: Large language models (LLMs) trained on vast amounts of data have demonstrated impressive performance over a range of tasks, but future performance ga

arXiv:2610.15882v1 Announce Type: new Abstract: A stored fact may stop being valid when a user changes a preference or an event replaces an earlier one. We study whether a language model can learn the

arXiv:2610.19654v1 Announce Type: new Abstract: Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduc

arXiv:2610.19822v1 Announce Type: cross Abstract: LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weig

arXiv:2609.31937v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents built on the ReAct pattern concentrate four responsibilities in one model: selecting a strategy, choosing ea

arXiv:2510.21974v3 Announce Type: replace Abstract: We introduce Deep Jump Gaussian Processes (DJGP), a novel method for surrogate modeling of a piecewise continuous function on a high-dimensional dom

arXiv:2603.00466v2 Announce Type: replace Abstract: Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified unders

arXiv:2610.17621v1 Announce Type: new Abstract: We propose FedLoRD, a personalized federated learning (PFL) method based on the low-rank structure of the differences between the global and personalize

arXiv:2610.18774v1 Announce Type: new Abstract: A robot needs a world model that predicts how its actions will change the scene and a policy that chooses those actions. Models are usually built and ev

arXiv:2603.07815v2 Announce Type: replace Abstract: Iterative diffusion generation requires different amounts of model capacity at different token positions. Prior model combinations allocate capacity

arXiv:2511.17366v2 Announce Type: replace-cross Abstract: Building a generalist robot that can perceive, reason, and act across diverse tasks remains an open challenge, especially for dexterous manipu

arXiv:2610.14162v1 Announce Type: cross Abstract: Diffusion language models (DLMs) offer parallel sampling for faster generation than autoregressive models, an increasingly important advantage as infe

arXiv:2610.15721v1 Announce Type: new Abstract: Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generated by a related sender model. Exi

We just shipped web search in Private Mind, our open source app for running LLMs locally on iOS and Android. The video is the whole pitch: Qwen 3 1.7B with web off makes up Apple's September event, wi

I set up a dedicated workstation for local AI experimentation with various models and tools. But every single one of them wants all the available VRAM. To fix this, I built a request dispatching layer

A lot of projects have come up recently consisting of specific hardware config specialized forks of existing conferencing engines, but they all seem to be made using Claude or OpenAI's biggest frontie

I’ve wanted this for a long time: a Krea-2 model that gives you a magazine page in one shot. Flash-lit gravure sets, film grain, multi-photo layouts on white paper, big headlines, covers and back cove

arXiv:2610.13285v1 Announce Type: new Abstract: Distilling long-chain reasoning trajectories from large teacher models provides an effective way to improve the reasoning ability of small language mode

arXiv:2610.12818v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically tra

Finetuned Qwen3.5-4B into a decision model like Jev using @UnslothAI. - 4-bit QLoRA, bf16, single A100, 15 min. - Train/val loss flatten after 2 epochs so most of the learning happens fast. - Trained

arXiv:2610.11430v1 Announce Type: new Abstract: While domain-specific Large Language Models (LLMs) have encoded vast biomedical knowledge, their limited context windows often hinder a deep understandi

arXiv:2610.11694v1 Announce Type: cross Abstract: Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic

Rachel Metz / Bloomberg: Arena, which develops the popular AI model leaderboard, raised 200M at a 3.1B valuation, up from 1.7B in January, and launches an Alignment Index — Arena Intelligence Inc., th

arXiv:2610.09476v1 Announce Type: cross Abstract: Geometric and Spectral Alignment (GSA) characterizes trained networks through spectral concentration, physical-channel alignment, support structure, a

arXiv:2610.10304v1 Announce Type: cross Abstract: We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference. We int