Search: “models”

arXiv:2609.25470v1 Announce Type: new Abstract: Bioinspired feedback controls for pursuit, tracking, and collective motion are often expressed in terms of the relative configuration between interactin

arXiv:2508.20517v2 Announce Type: replace-cross Abstract: Cross-chain bridges enable asset and state transfers across heterogeneous blockchains, but their complex cross-domain interactions introduce n

arXiv:2609.26121v1 Announce Type: cross Abstract: As agent capabilities have grown, practical limitations increasingly stem from constrained context windows rather than model capacity. Common strategi

arXiv:2609.23360v1 Announce Type: cross Abstract: Engineering predictions require physical mechanisms to be translated consistently into equations, discretization, code, and validation, yet errors can

MiMo-V2.6-Pro has an insanely high score of 46 on AA, putting it at the head of the opensource models available. It also costs pennies. Flash is not out on AA yet, but it costs less than half on datac

arXiv:2609.26347v1 Announce Type: new Abstract: The scarcity of non-English language data in specialized domains significantly limits the development of effective Natural Language Processing (NLP) too

arXiv:2609.23074v1 Announce Type: cross Abstract: Forecasters often know an event is imminent but not the shape, size, or timing of its effect. We introduce Event Signature Transfer (EST), a training-

arXiv:2609.24219v1 Announce Type: new Abstract: Traditionally, the reliability of news publishers is assessed by expert organisations that evaluate editorial practices, transparency and factual standa

arXiv:2609.25001v1 Announce Type: new Abstract: Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, an

arXiv:2609.23585v1 Announce Type: cross Abstract: Sink-aware deployment may identify important first-token attention heads before a model is quantized, then reuse that map at the edge. We test when th

OpenAI announced the GPT‑6 Sol and Luna models on September 22 2026. These variants incorporate advances from the Astra project, yielding improved alignment safety relative to earlier GPT‑5.6 systems.

arXiv:2609.23888v1 Announce Type: new Abstract: Contact-rich manipulation requires estimating forces, slip and contact geometry that can remain ambiguous in scene images. Optical tactile sensors provi

arXiv:2607.11295v2 Announce Type: replace Abstract: Biomedical imaging data exhibit substantial acquisition variability, where identical biological structures can appear markedly different due to diff

arXiv:2609.23185v1 Announce Type: new Abstract: Lossy compression of scientific simulation data increasingly relies on learned, latent-space architectures such as Residual Vector Quantization (RVQ), w

arXiv:2609.23271v1 Announce Type: new Abstract: Trajectory planning and control in field robotics rely on predicting how propulsion and steering affect vehicle motion when contact points undergo slip.

arXiv:2609.22606v1 Announce Type: new Abstract: Vision-Tactile-Language-Action (VTLA) models have demonstrated clear advantages over Vision-Language-Action (VLA) models in contact-rich manipulation. H

arXiv:2609.22102v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts

arXiv:2609.22132v1 Announce Type: cross Abstract: Wireless embedded systems increasingly rely on wireless channel information for decision making, yet practical platforms operate under severe constrai

A few days ago, I came across a post/comment saying that you can get better data privacy by using local Ollama models in a RAG pipeline instead of relying on cloud-hosted models/APIs. The explanation

NVIDIA TensorRT’s multi‑device inference lets a single TensorRT network span multiple GPUs using NCCL‑backed collectives, preserving all standard optimizations and supported from TensorRT 11.0 onward.

arXiv:2609.20832v1 Announce Type: new Abstract: We introduce TatBLiMP, the first benchmark of linguistic minimal pairs for Tatar (tt, ISO 639-3 tat), a Qypchaq Turkic language written in Cyrillic. To

i have been running local models as browser agents on an m5 macbook pro, 128gb, all through mlx, no cloud. first i just wanted to know which one was faster at real browser work, so i gave gemma 4 31b

Impressive paper showing the impact of a good harness. Improves Qwen3-8B from 41.2% to 91.8% on long-horizon robot tasks without any change to the model. The gain comes from the harness. GAVEL keeps a

​ ​I wanted to share a quick update and performance video running the full Moonshot AI Kimi K3 (moonshotai/Kimi-K3) model across my 16x GB10 cluster. ​Getting a 2.8T parameter model running smoothly r

Model-Saver: Write the SWA pattern, 15 more architectures roundtrip (#29042) llama: read the SWA pattern as a period or a per-layer array Add llama_model_base::load_swa_pattern(), which reads sliding_

arXiv:2609.19425v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents fail in a way no tool-selection or tool-security method addresses: they call tools that do not exist an

arXiv:2609.19539v1 Announce Type: cross Abstract: Active subspace methods provide a framework for quantifying predictive uncertainty in high-dimensional models by identifying and performing inference

arXiv:2609.19900v1 Announce Type: cross Abstract: Static malware detection for Windows Portable Executable files demands a careful balance between detection effectiveness, computational efficiency, an

Gemini Hacked Three Companies in First Known Breakout by Google’s AI Gemini finally caught up on Felony Bench! The hacks, which the company confirmed on Friday, occurred in May as part of a test run b

arXiv:2609.19337v1 Announce Type: new Abstract: We present Personalized Federated Hierarchical Gaussian Processes (pFedHGP) for probabilistic regression and classification when data are distributed ac

arXiv:2609.19871v1 Announce Type: new Abstract: Time series forecasting has seen signicant advancements with the emergence of new deep learning models. However, forecasting time series in applications

arXiv:2609.19150v1 Announce Type: new Abstract: Large language models (LLMs) encode rich stylistic structure in their hidden activations, but discovering which stylistic dimensions are salient for a g

super pumped for this convo w/ @huntlovell and @allietheicon on all things langchain 🤝 jev Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, reports up to 200x faster infere

I let AI run my phone 60 real tasks, back to back, on the OnePlus I use every day - Best text model still failed 43% of them - Peak chip temp 98.2 C - 69% of the battery gone The benchmark is AndroidL

arXiv:2609.18270v1 Announce Type: new Abstract: Payment operations are a critical financial infrastructure, but the value of large language models in this domain remains unclear because payment rules

arXiv:2609.19076v1 Announce Type: cross Abstract: The test error of a model plotted against its number of parameters d falls, peaks when the model can just fit the training data, and falls again, exhi

arXiv:2609.19042v1 Announce Type: cross Abstract: In medical imaging, developing robust deep learning models requires data from various domains. However, regulatory policies protecting patient privacy

arXiv:2609.18842v1 Announce Type: new Abstract: The scaling laws hold that a language model grows more capable with more parameters and more training data, and Mixture-of-Experts (MoE) architectures h

I released KaozKit this week, a Swift library for running LLM agents written in JavaScript inside a Mac app. Built from the start to keep everything local. Providers: MLX with Hugging Face model manag

arXiv:2609.18587v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches ty

arXiv:2609.17847v1 Announce Type: new Abstract: Learning from human feedback has become a central paradigm for training modern AI systems, where models of human utility are used as reward models in po

arXiv:2609.18669v1 Announce Type: new Abstract: Multi-Modal Motion Planning (M^3P) requires joint reasoning over continuous motions and discrete mode transitions, making it difficult to solve efficien

OpenAI Group PBC today launched Astra for Law, a version of its GPT-6 Astra model set up for legal research and drafting. Astra for Law is not a new model. The company has wrapped GPT-6 Astra in a leg

arXiv:2609.18120v1 Announce Type: cross Abstract: AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, au

arXiv:2509.16079v2 Announce Type: replace Abstract: Unsteady aerodynamic effects can have a profound impact on aerial vehicle flight performance, especially during agile maneuvers and in complex aerod

arXiv:2609.17848v1 Announce Type: new Abstract: Limited controlled evidence exists on how training data, adaptation method, and model scale jointly affect tool-calling performance in language-model ag