All entries

arXiv:2609.01832v1 Announce Type: cross Abstract: Patients with depression present with diverse symptom profiles, yet clinical practice routinely reduces this variation to a single severity score. Lar

Introducing K2 Horizon: a connected fleet of six foundation models ranging from 0.9 billion to 375 billion parameters. - Frontier performance: Across coding and agentic tasks, K2 Horizon delivers top-

It started as a fork of llama-swap, but I have been building it out for myself since then as a convenient tool for all my local AI needs, and by now it has drifted far enough to be its own thing. The

Introducing WeatherNext 3️⃣— our most advanced global weather AI model yet from @GoogleDeepmind and @GoogleResearch With prediction capabilities that are up to 5x sharper than WeatherNext 2, the model

It is inevitable that all AI will converge towards symbolic learning (i.e. modeling data by finding the shortest symbolic program that explains it), since that is the optimally efficient form of AI. B

I've watched a lot of good tools die in production. Not because they didn't work. Because the two people who understood them rolled off the show, and what was left was a graph nobody could read. So th

Jörg Schad is the VP of Engineering at @pinecone. He joins @kbal11 to discuss moving beyond RAG with precomputed context, context artifacts, semantic layers, and AI retrieval. @joerg_schad https://sof

Just because someone puts the word AGI in their benchmark doesn't make it even remotely a reflection of what the general public understands by this term. As a layman, I define AGI as a virtual charact

On September 3, 2026 NVIDIA announced a $12.93‑billion acquisition of Hugging Face. The purchase price contains an easter egg: the digits 129,303 are the decimal representation of Unicode code point U

arXiv:2609.01823v1 Announce Type: new Abstract: Understanding animal motion is fundamental to modeling animal behavior and biomechanics, yet progress in this area lags far behind human motion research

arXiv:2609.01976v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded in organizational work, yet their errors often pass human review. Prior research locates such f

arXiv:2609.02079v1 Announce Type: new Abstract: Intermittent state measurements pose fundamental challenges to model predictive control of constrained nonlinear systems because prediction uncertainty

Krea 2 Turbo — 4-Step Distillation LoRA (work in progress) A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4. ⚡ Half the steps — 8 → 4, on Turbo's own deployment sigmas. ⏱

arXiv:2609.02077v1 Announce Type: new Abstract: Accurate 3D ship detection in maritime environments is critical for autonomous navigation, yet remains challenging due to large-scale vessel variations,

arXiv:2603.18593v2 Announce Type: replace Abstract: We propose a method that represents language models by log-likelihood vectors over prompt-response pairs and constructs model maps for comparing the

arXiv:2609.02737v1 Announce Type: cross Abstract: Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If

arXiv:2609.02805v1 Announce Type: new Abstract: Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G network

arXiv:2609.02063v1 Announce Type: new Abstract: Single-image super-resolution (SISR) requires global context modeling for structurally consistent reconstruction. Fourier operators are increasingly ado

arXiv:2609.02634v1 Announce Type: new Abstract: Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal

arXiv:2609.01871v1 Announce Type: cross Abstract: We describe a neural network architecture and training procedure designed to model electronic ground and excited states of arbitrary molecular systems

arXiv:2609.02207v1 Announce Type: cross Abstract: Real-world personally identifiable information (PII) redaction often operates on document images---scans, screenshots, and PDF renderings---where OCR

arXiv:2609.02548v1 Announce Type: cross Abstract: Modern large language models (LLMs) rely on reinforcement learning to build strong capabilities in individual domains, but integrating those capabilit

arXiv:2601.14810v3 Announce Type: replace-cross Abstract: Machine Learning (ML) has deeply changed some fields recently, like Language and Vision and we may expect it to be relevant also to the analys

arXiv:2609.02568v1 Announce Type: cross Abstract: Volumetric video based on point cloud representations enables immersive virtual and augmented reality applications but introduces significant challeng

arXiv:2609.01687v1 Announce Type: new Abstract: Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult be

arXiv:2609.02833v1 Announce Type: cross Abstract: Meshfree methods such as smoothed particle hydrodynamics (SPH) with kernel corrections, radial basis function-generated finite differences (RBF-FD), a

arXiv:2609.02194v1 Announce Type: new Abstract: Classical constitutive modeling of path-dependent inelastic materials relies on internal state variables whose evolution equations must be postulated ba

arXiv:2609.02644v1 Announce Type: new Abstract: Face recognition in unconstrained environments remains highly challenging due to diverse and extreme variations encountered in real-world scenarios. To

arXiv:2609.02473v1 Announce Type: new Abstract: Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to matched patient phenotypes. Large language models (LLM

arXiv:2609.02471v1 Announce Type: new Abstract: Target templates define what a visual tracker searches for, yet the templates available at inference trade off localization certainty with appearance fr

arXiv:2609.01928v1 Announce Type: new Abstract: Higher-order interaction components are important for signal, image, and video modeling, but explicit high-order operators often suffer from rapidly inc

arXiv:2609.02187v1 Announce Type: new Abstract: General-purpose vision-language models (VLMs) now support strong visual recognition, instruction following, and generation. However, most pretrained vis

arXiv:2609.01997v1 Announce Type: new Abstract: We propose LF-MultiDiffusion, a training-free panorama generation method that extends MultiDiffusion to support linear projections between target and re

arXiv:2609.02246v1 Announce Type: new Abstract: Self-improving agent pipelines have a problem at their center. An optimizer rewrites prompts to score higher, and the score comes from a judge that is i

arXiv:2607.10103v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become widely deployed, their outputs can be copied, transformed, and redistributed at scale without reliable

arXiv:2609.02676v1 Announce Type: cross Abstract: Ultra-low-field MRI makes neonatal brain imaging deploy- able in low-resource settings, but its low SNR, lack of shielding, and long scan duration mak

I might be missing something obvious, but when I open any cloud model, by default I'm dealing with the 200k version and the first thing I need to do is /model to change it to the 1M version. Is there

Looking forward to this ecosystem with open models continuing to flourish and grow with NVIDIA and Hugging Face, and the continued partnership. Congrats @JensenHuang and @ClementDelangue! Exciting day

arXiv:2609.02350v1 Announce Type: new Abstract: Vision-Language Navigation (VLN) requires an embodied agent to follow natural-language instructions in unseen environments. Recent progress has been lar

arXiv:2609.02649v1 Announce Type: new Abstract: Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challenge when deploying NLP systems in real-world industri

arXiv:2609.01924v1 Announce Type: new Abstract: Recent work identifies a mid-depth band of verbalisable, causally potent representations in a standard feedforward transformer --- a functional analogue

arXiv:2609.02734v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geo

arXiv:2609.01961v1 Announce Type: new Abstract: Augmenting the dexterity of human surgeons has the potential to free them from tedious subtasks. We consider debridement (removal of diseased or dead ti

arXiv:2609.02266v1 Announce Type: new Abstract: Fine-grained defect severity grading is essential for industrial inspection, yet remains challenging due to the ordinal nature of severity labels, the s

arXiv:2609.01628v1 Announce Type: cross Abstract: E-commerce search ranking must balance multiple objectives--relevance, user engagement, and platform revenue--when allocating impression slots to comp

arXiv:2609.02565v1 Announce Type: new Abstract: Text-video retrieval requires representations that can distinguish videos with similar scenes, actions, and temporal patterns. Recent multimodal large l