Search: “models”

arXiv:2607.22954v1 Announce Type: new Abstract: Objective: To characterize the kinds of internal documentation inconsistencies a general-domain large language model (LLM) can surface from real-world d

arXiv:2607.23333v1 Announce Type: cross Abstract: We revisit the regret loss framework introduced in Park et al. (2025), which uses decision-theoretic regret as a direct loss function for training mod

arXiv:2607.23970v1 Announce Type: cross Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss la

arXiv:2607.23740v1 Announce Type: new Abstract: As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability t

arXiv:2607.21722v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs) exhibit strong perceptual capabilities, they remain vulnerable in visual reasoning tasks. Existing benchmarks

I got tired of my Ollama server sitting idle between chat experiments, so I pointed it at my Navidrome library and made it run a radio station. The DJ is an agent, not a shuffler. Each turn it gets to

arXiv:2607.21672v1 Announce Type: cross Abstract: Long source-code contexts consume many text tokens, motivating the proposal to render code as images for vision-language models. Recent work asks whet

The performance of AI agents depends not only on the underlying models but also heavily on their “harness”—the surrounding architecture that supplies context, state management, action execution, and t

audio.cpp again :) Release 0.4 is out. The headline this time is new high-quality TTS coverage plus GGUF becoming a first-class across the project. What’s new: Added Higgs Audio v3 TTS 4B, Fish Audio

arXiv:2607.20434v1 Announce Type: cross Abstract: As the parameter size of language models continues to grow, effective model compression is required to reduce their computational and memory overhead.

arXiv:2607.21412v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially i

arXiv:2607.21561v1 Announce Type: new Abstract: Molecular property prediction from structure often uses a single representative conformation, even though many molecules exist as conformational ensembl

arXiv:2607.20533v1 Announce Type: cross Abstract: Portfolio construction under the Black-Litterman model requires investors to specify views on asset returns alongside explicit uncertainty estimates -

arXiv:2607.21332v1 Announce Type: cross Abstract: Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language va

arXiv:2512.19178v2 Announce Type: replace-cross Abstract: Bridging the gap between natural language commands and autonomous execution in unstructured environments remains an open challenge for robotic

So, i have been building some apps that should run on the local every user system, tried gemma4 although its fast and great at reasoning its not as good in instructions following and tool calling. tri

AI9Stars has released G9v3-3B an open weights language model designed to deliver strong reasoning capabilities within a lightweight 3 billion parameter size. It is released under the Apache 2.0 licens

LLaDA2.2-flash is an agent-oriented diffusion language model in the LLaDA2 series. By introducing Levenshtein Editing (with DELETE and INSERT control tokens) to diffusion language modeling, it represe

arXiv:2607.19750v1 Announce Type: cross Abstract: In HEP data analyses, finding an adequate function to model binned data has largely relied on a manual process: guess a functional form by intuition,

The math behind reinforcement learning (RL) post-training for large language models (LLMs) is notoriously unforgiving. As frontier AI labs push the boundaries of reasoning and coding models using RL p

arXiv:2607.19406v1 Announce Type: new Abstract: Structural elucidation from Nuclear Magnetic Resonance (NMR) data remains a fundamental bottleneck across chemistry, materials science, and biology. We

arXiv:2607.20230v1 Announce Type: new Abstract: Accurate modeling of environmental systems is fundamental to scientific understanding and decision-making, yet remains challenging because observations

arXiv:2606.17471v3 Announce Type: replace Abstract: Traditional CPU, GPU, and NPU architectures are increasingly limited by the von Neumann bottleneck. While In-Memory Computing (IMC) using ReRAM cros

A senior White House official has accused Chinese artificial intelligence startup Moonshot AI of using so-called “distillation” techniques to essentially pirate the capabilities of Anthropic PBC’s mos

arXiv:2607.20082v1 Announce Type: new Abstract: Language models are increasingly asked to self-report, informing safety evaluations, public understanding, and model-welfare debates. Yet their reports

World Modeling with JEPA has recently gained traction thanks to a novel anti-collapse mechanism called 'SIGReg' (by @ylecun and @randall_balestr). The math is clean, but it is rarely explained from fi

U.S. Treasury Secretary Scott Bessent said today that the White House is going to examine some of the highest profile “open-weight” models from China to see if their creators have stolen the intellect

As adversarial AI threats accelerate attacks on code, security teams must counter them with machine-speed defenses that can automate code remediation and fight AI with AI. CodeMender is our managed co

NVIDIA AI has released Cosmos 3 Edge, a 4‑billion‑parameter open‑source world model designed for on‑device inference. It enables robots to learn and act, autonomous vehicles to interpret road scenes a

arXiv:2607.13927v1 Announce Type: new Abstract: Reliable perception under diverse weather conditions remains a major challenge for autonomous driving systems. A common strategy to improve robustness i

arXiv:2607.13103v1 Announce Type: cross Abstract: Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions. Existing

arXiv:2607.13573v1 Announce Type: cross Abstract: Maneuvering target tracking in three-dimensional space remains a challenging problem due to complex motion dynamics and model mismatch. To address thi

arXiv:2607.13660v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyp

arXiv:2607.13046v1 Announce Type: new Abstract: We develop a framework for the information discarded by machine learning models whose inputs carry a Lie group action. Given a representation pi of a Li

arXiv:2607.11943v1 Announce Type: cross Abstract: Long-horizon physics-based simulations of battery degradation provide mechanistic insight but remain computationally expensive, limiting their use for

Below Upstream Status sections are from https://github.com/PrismML-Eng/Bonsai-demo Upstream Status for Binary Q1_0 is supported out of the box in upstream llama.cpp across many backends: CPU (generic,

arXiv:2607.12349v1 Announce Type: new Abstract: Drug discovery and development is time-consuming and resource-intensive, motivating computational approaches such as diffusion models for de novo drug d

arXiv:2607.12696v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depe

arXiv:2512.04144v3 Announce Type: replace Abstract: Targeted interventions on language models, such as unlearning or model editing, aim to modify specific information, but their effects often propagat

Introduction RxBrain (Hy-Embodied-RxBrain-1.0) is a unified multimodal foundation model for embodied cognition — a single model that couples language reasoning with visual imagination to deliver three

This AI recursive self improvement (RSI) paper shows no sign of fast takeoff. The AI model advances at about [Intelligence]^0.075, or the the 13th root of input intelligence [1,2]. That means the inte

arXiv:2607.08643v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly constrained by memory capacity, weight bandwidth, and checkpoint storage during deployment. Existing low-b

arXiv:2607.08490v1 Announce Type: new Abstract: Biomedical language evolves rapidly as new discoveries emerge, causing traditional text models to lose semantic fidelity over time. Static embeddings an

arXiv:2607.08127v1 Announce Type: new Abstract: Generative video foundation models exhibit strong compositional priors, yet world-action models (WAMs) and video-action models (VAMs) often lose these p

arXiv:2606.15346v2 Announce Type: replace Abstract: Spatio-temporal prediction supports radar/satellite nowcasting and city-scale traffic monitoring, but modern models are often too expensive for real

arXiv:2508.21556v3 Announce Type: replace Abstract: Modeling human-object interactions (HOI) from an egocentric perspective is a critical yet challenging task, particularly when relying on sparse sign