All entries

Poolside AI’s co‑CEO Eiso Kant explains that a small, top‑research team built a model‑factory capable of training Laguna S, a 118‑billion‑parameter mixture‑of‑experts model that outperforms the ~1 tri

toolslatent-space

Tutorials

Instance Hardness-Based Relevance for Imbalanced Regression

arXiv:2607.20173v1 Announce Type: new Abstract: Imbalanced regression problems arise when the target variable has an asymmetric distribution, resulting in underrepresented value ranges in the dataset.

tutorialsarxiv-cs-lg

23 Jul 2026

Hardware

InstantSfM: Towards GPU-Native SfM for the Deep Learning Era

arXiv:2510.13310v3 Announce Type: replace Abstract: Structure-from-Motion (SfM) is a fundamental technique for recovering camera poses and scene structure from multi-view imagery, serving as a critica

hardwarearxiv-cs-cv

InstructMixup: Instruction-Guided Salient Patch Editing for Robust Data Augmentation

arXiv:2607.19324v1 Announce Type: new Abstract: In image and video technologies, data augmentation is widely used to improve the generalization of deep visual models, and mixup-based strategies that i

Integrity of peer-to-peer distributed LLM inference under malicious nodes

arXiv:2607.19490v1 Announce Type: cross Abstract: Peer-to-peer distributed inference executes a Large Language Model (LLM) on pooled consumer hardware by spreading its layers across many nodes. Every

Interactive Medical-SAM2 GUI: A Napari-based semi-automatic annotation tool for medical images

model-releasesarxiv-cs-cv

arXiv:2602.22649v2 Announce Type: replace Abstract: Interactive Medical-SAM2 GUI is an open-source desktop application for semi-automatic annotation of 2D and 3D medical images. Built on the Napari mu

Interesting reasoning by phi4-mini-reasoning

https://preview.redd.it/joxxvyzhf1fh1.png?width=2386&format=png&auto=webp&s=a55c09d11eb080b83d3b66b59013a09118913c9d Freshly installed, just asked it 'who are you'. Why does this happen? 😄 submitted b

local-air-ollama

Internet-of-Things Architectures for Secure Cyber-Physical Spaces: the VISOR Experience Report

arXiv:2204.01531v2 Announce Type: replace-cross Abstract: Internet of things (IoT) technologies are becoming a more and more widespread part of civilian life in common urban spaces, which are rapidly

Interpretable Deep Learning Paradigm for Airborne Transient Electromagnetic Inversion

model-releasesarxiv-cs-lg

arXiv:2503.22214v2 Announce Type: replace Abstract: The extraction of geoelectric structural information from airborne transient electromagnetic (ATEM) data primarily involves data processing and inve

Interpretable Fuzzy Rule-Based Regression Extension for Ex-Fuzzy Library

arXiv:2607.20277v1 Announce Type: new Abstract: Machine learning models achieve high predictive accuracy in regression tasks, but their deployment in safety-critical and regulated domains requires int

safetyarxiv-cs-lg

Tutorials

Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling

arXiv:2607.20339v1 Announce Type: new Abstract: Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformati

tutorialsarxiv-cs-lg

Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality gen…

Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality generation What's new: • Fine-grained inline tags-steer [whispe

model-releasesqwen--x

Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds

arXiv:2607.18135v1 Announce Type: cross Abstract: Learning-based approaches to locomotion have risen in popularity in recent years, showing the capability for complex legged locomotion and whole-body

safetyarxiv-cs-lg

It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability

model-releasesarxiv-cs-cv

arXiv:2607.16292v2 Announce Type: replace Abstract: Brain-encoding foundation models predict fMRI responses to video, audio, and text well enough to win the Algonauts 2025 challenge. We ask whether th

ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers

arXiv:2607.19407v1 Announce Type: new Abstract: Formal theorem proving has emerged as a frontier challenge for machine learning, yet the ecosystem is fragmented: proofs remain siloed across incompatib

It’s important that outside agencies and independent bodies hold frontier AI companies accountable for the actions of their models. This is …

It’s important that outside agencies and independent bodies hold frontier AI companies accountable for the actions of their models. This is not a “whoops” situation, it’s a deliberate policy choice. W

safetygary-marcus--x

it’s just for your safety

On July 23, 2026, a Polymarket tweet announced that Anthropic donated $20 million to a political nonprofit calling for stricter AI regulation ahead of the U.S. midterm elections. The post, posted at 4

safetyyann-lecun--x

It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief

model-releasesarxiv-cs-cl

arXiv:2607.18232v2 Announce Type: replace Abstract: Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true.

'It's really hard to overstate how crazy it is what happened here.' ControlAI's US Director Connor Leahy (@NPCollapse) speaks with @LindseyR…

'It's really hard to overstate how crazy it is what happened here.' ControlAI's US Director Connor Leahy (@NPCollapse) speaks with @LindseyReiser on CBS News, after OpenAI's own AI autonomously escape

safetyconnor-leahy--x

JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

arXiv:2607.17572v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. Whil

safetyarxiv-cs-lg

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

arXiv:2607.19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unre

JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety

arXiv:2607.19913v1 Announce Type: new Abstract: Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-orient

safetyarxiv-cs-ai

Juxtaposition of Shallow Reservoir-Triggered Seismicity and Deep Tectonic Locking in the Qiaojia-Dongchuan Seismic Gap

arXiv:2607.19606v1 Announce Type: cross Abstract: Identifying the critical state of mature seismic gaps is challenging, especially when anthropogenic stress perturbations, such as reservoir impoundmen

Kernel Ridge Regression Inference

arXiv:2302.06578v4 Announce Type: replace-cross Abstract: We provide uniform confidence bands for kernel ridge regression (KRR), a widely used nonparametric regression estimator for nonstandard data s

researcharxiv-cs-lg

Kimi K3 is coming to Together AI on day zero, July 27. Start building with it the moment it launches, powered by Together AI inference for c…

model-releasestogether-ai--x

Kimi K3 is coming to Together AI on day zero, July 27. Start building with it the moment it launches, powered by Together AI inference for coding, agents, and production workloads. https://www.togethe

KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding

model-releasesarxiv-cs-ro

arXiv:2607.19876v1 Announce Type: new Abstract: Evaluating the physical consistency of embodied world models(EWMs) is a critical open challenge. While closed-loop evaluation via simulator rollouts off

Agents

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

arXiv:2607.19837v1 Announce Type: new Abstract: Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that A

agentsarxiv-cs-ai

Agents

Knowledge-Centric Self-Improvement

arXiv:2607.19592v1 Announce Type: new Abstract: Self-improving AI systems typically treat the agent as the object that improves, by optimizing prompts, workflows, harnesses, or even the agent's own co

agentsarxiv-cs-ai

Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing

arXiv:2510.08532v2 Announce Type: replace Abstract: Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instr

Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination

arXiv:2607.19719v1 Announce Type: new Abstract: Latent world models improve sample efficiency in continuous control by optimizing policies over imagined latent trajectories, but common neural transiti

local-aiarxiv-cs-lg

Kwaipilot/KAT-Coder-V2.5-Dev · Hugging Face

model-releasesr-localllama

from kwaipilot: Following the release of KAT-Coder-V2.5 in July, we are pleased to release the open-weight version KAT-Coder-V2.5-Dev, an MOE model with a total parameter count of 35B and 3B activated

LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

arXiv:2607.19391v1 Announce Type: cross Abstract: Low-Rank Adaptation is widely used for parameter-efficient fine-tuning, yet existing methods typically assign the same adapter rank to every transform

Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields

arXiv:2607.20321v1 Announce Type: cross Abstract: Neural surrogates are widely used in scientific machine learning for fast prediction of three-dimensional (3D) thermo-fluid fields. However, generatin

researcharxiv-cs-lg

LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models

arXiv:2607.16339v2 Announce Type: replace Abstract: Diffusion-based Large Language Models(DLLMs) enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation. However, current

Laguna-S-2.1 'thinking forever' loops seem to be a quantization artifact

model-releasesr-localllama

If you're running Laguna S 2.1 on llama.cpp and hitting thinking loops because it won't close its </think> tags, you might want to look at your quant before you spend too much time tweaking settings.

Language-Specific versus Cross-Lingual Knowledge Graphs for Implicit Aspect Identification in Arabic: A Comparative Study of Reasoning and Adaptation Strategies

arXiv:2607.20056v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Im

LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

arXiv:2407.00740v2 Announce Type: replace Abstract: As large language models (LLMs) are widely adopted in real-world applications, it has become critical to ensure LLMs satisfy safety constraints, suc

local-aiarxiv-cs-cl

Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models

arXiv:2607.19120v1 Announce Type: new Abstract: Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs

arXiv:2602.00462v5 Announce Type: replace-cross Abstract: Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encode

safetyarxiv-cs-ai

LAVIFT: Latent-Action-Guided Vision Fine-Tuning for Surgical Interaction Recognition

arXiv:2607.19889v1 Announce Type: new Abstract: Understanding instrument-tissue interactions is essential for context-aware surgical AI and autonomous robotic surgery. Pretrained vision-language model

local-aiarxiv-cs-cv

LC-SLab -- An object-based deep learning framework for large-scale land cover classification from satellite imagery and sparse in-situ labels

arXiv:2509.15868v2 Announce Type: replace Abstract: Large-scale land cover maps generated using deep learning play a critical role across a wide range of Earth science applications. Open in-situ datas

Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2

arXiv:2607.19811v1 Announce Type: new Abstract: The Segment Anything Model 2 (SAM2) has advanced temporal promptable segmentation, yet its deployment remains hindered by heavy memory cross-attention o

safetyarxiv-cs-cv

Learning About Learning: A Path from Spin Glasses to Artificial Intelligence

arXiv:2601.07635v3 Announce Type: replace-cross Abstract: The Hopfield model, originally inspired by spin glasses, occupies a central place at the intersection of statistical mechanics, neural network

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks

arXiv:2509.23926v4 Announce Type: replace Abstract: Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along dir

safetyarxiv-cs-cv

Learning Explicit Physical Parameter Control and Benchmarking for Video Generation

model-releasesarxiv-cs-cv

arXiv:2607.18924v1 Announce Type: new Abstract: Recent advances in image-to-video generation have improved visual realism, making physically grounded and controllable dynamics an important step toward

Learning Personalized Safety Interventions for Haptic Human-Robot Shared Control

arXiv:2607.19534v1 Announce Type: new Abstract: Haptic feedback provides an implicit channel for communicating safety intentions during human-robot shared control. Existing haptic guidance systems typ

safetyarxiv-cs-ro

Tutorials

Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation

arXiv:2607.19000v1 Announce Type: new Abstract: Change detection aims to identify semantic changes between remote sensing images. However, features from models are easily disturbed by non-semantic var

tutorialsarxiv-cs-cv

Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Speaker Origin Prediction

arXiv:2607.19751v1 Announce Type: cross Abstract: We present a regression-based approach to Arabic dialect geolocation that models dialectal variation as a continuous geographic space rather than disc