All entries

Time-frequency localization of bird calls in dense soundscapes

arXiv:2606.10407v1 Announce Type: cross Abstract: Passive acoustic monitoring enables large-scale observation of wildlife, but most bioacoustic classifiers only predict species presence in a time wind

local-aiarxiv-cs-cv

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

DGX agent

arXiv:2606.09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open. To bridge the ga

researcharxiv-cs-ai

10 Jun 2026

Time series forecasting from partial observations via Non-negative Matrix Factorization

arXiv:2102.05314v2 Announce Type: replace Abstract: In modern time series problems, one aims at forecasting multiple time series with possible missing and noisy values. In this paper, we introduce the

Tutorials

(To be clear, I don't think we should try to slow down recursive AI self improvement - I think we should open it up and democratize it as …

tutorialsjeremy-howard--x

(To be clear, *I* don't think we should try to slow down recursive AI self improvement - I think we should open it up and democratize it as much as possible. My point is: if *you* claim we should slow

Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was bui…

Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I think the technolog

safetyboris-cherny--x

Tools

Together AI is ISO 27001:2022 certified. A-LIGN (ANAB-accredited) completed a multi-month audit of our ISMS: customer data protection, acces…

Together AI is ISO 27001:2022 certified. A-LIGN (ANAB-accredited) completed a multi-month audit of our ISMS: customer data protection, access controls, secure development, and incident response. Detai

toolstogether-ai--x

Hardware

torch-sla: Differentiable Sparse Linear Algebra with Adjoint Solvers and Sparse Tensor Parallelism for PyTorch

arXiv:2601.13994v3 Announce Type: replace-cross Abstract: Differentiable sparse linear algebra is foundational for scientific machine learning, yet PyTorch lacks a unified library for it: torch.sparse

hardwarearxiv-cs-ai

Toward Calibrated, Fair, and accurate Deepfake Detection

arXiv:2606.09881v1 Announce Type: cross Abstract: Deepfake detectors show large performance gaps across demographic groups. Existing fairness approaches require demographic labels, retraining, or sacr

safetyarxiv-cs-cv

Toward Proactive RF Charging Scheduling: Generative AI for Decision Support

arXiv:2606.10600v1 Announce Type: cross Abstract: Radio frequency wireless power transfer (RF-WPT) is an enabling technology for supporting uninterrupted communications in future Internet of Things sy

applicationsarxiv-cs-lg

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

arXiv:2606.10749v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, a

agentsarxiv-cs-ai

Towards Autonomous Accelerator Design: FPGA Accelerator Generation with SECDA

arXiv:2606.11117v1 Announce Type: cross Abstract: Designing FPGA-based accelerators for modern artificial intelligence workloads requires exploring a large and complex hardware design space that invol

agentsarxiv-cs-ai

Towards Critical Branching Mechanism in Recurrent Neural Networks

arXiv:2606.10384v1 Announce Type: cross Abstract: Criticality has been proposed as a key organizing principle in biological neural systems, yet its origin and relevance in artificial neural networks r

Towards Diverse Scientific Hypothesis Search with Large Language Models

arXiv:2606.10587v1 Announce Type: cross Abstract: Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientifi

Towards Robust Arabic Speech Emotion Recognition with Deep Learning

arXiv:2606.10278v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) aims to identify a speaker's emotional state from audio signals. While recent advances in deep learning have signific

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

arXiv:2606.11119v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. H

safetyarxiv-cs-ai

Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering

arXiv:2606.10921v1 Announce Type: new Abstract: Long-document question answering (QA) requires large language models (LLMs) to reason over evidence scattered across lengthy documents, where answers of

agentsarxiv-cs-cl

Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents

arXiv:2606.10457v1 Announce Type: new Abstract: Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved thr

applicationsarxiv-cs-ai

Tractogram foundation model

arXiv:2606.09893v1 Announce Type: cross Abstract: Diffusion MRI (dMRI) tractography is the only noninvasive approach for mapping white-matter pathways in the living human brain. It represents each bra

local-aiarxiv-cs-ai

Trading Utility for Dynamic Fairness in Multiple Resource Division with Sequential Demand

arXiv:2606.10472v1 Announce Type: cross Abstract: Dynamic multi-resource allocation is a central problem in shared computing environments, where users' demands arrive sequentially and resources must b

safetyarxiv-cs-lg

Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization

arXiv:2606.10179v1 Announce Type: cross Abstract: Quantum Circuit Born Machines (QCBMs) offer a natural approach to generative machine learning by leveraging the Born rule. Recent work has provided a

Trainable Smooth-Rotation Transforms with Learned Channel Scales for LLM Quantization

model-releasesarxiv-cs-ai

arXiv:2606.09927v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is one of the most practical ways to reduce the serving cost of Large Language Models (LLMs), but activation quantiza

Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization

model-releasesarxiv-cs-cl

arXiv:2606.10860v1 Announce Type: cross Abstract: Production LLMs receive instructions from sources with very different levels of trust, yet attend to every token with uniform architectural privilege.

Training Set Augmentation and Biology-Aware Harmonization Improve Radiomic Models for Lung Cancer Prediction in Indeterminate Nodules

arXiv:2412.16758v3 Announce Type: replace-cross Abstract: CT radiomics-based machine learning has potential to predict lung cancer in pulmonary nodules (PNs) earlier than standard-of-care methods. Low

researcharxiv-cs-cv

Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition

arXiv:2606.10718v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a widely adopted technique for monitoring brain activity, offering valuable insights into neurological states due to i

local-aiarxiv-cs-ai

TRAPS: Therapeutic Response Analysis via Pathway-informed Stratification

model-releasesarxiv-cs-lg

arXiv:2606.09898v1 Announce Type: new Abstract: Cancer treatment planning requires decisions across multiple clinical dimensions at once. Clinicians must determine whether a patient should receive tar

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

arXiv:2509.25760v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination a

Try it out in Comfy today!

Try it out in Comfy today! 🎥Bria’s V-RMBG 3.0 is live! A state-of-the-art upgrade to the only end-to-end video background removal suite in production today. Benchmarked against every major competitor.

applicationscomfyui--x

two fun surprises from using activegraph: - the coding agent i was using would query the trace db to debug instead of looking at the logs li…

two fun surprises from using activegraph: - the coding agent i was using would query the trace db to debug instead of looking at the logs like they normally would (i didn't ask it to) - when long eval

agentsyohei-nakajima--x

Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning

arXiv:2606.09866v1 Announce Type: cross Abstract: Fine-tuning safety aligned large language models (LLMs) on downstream data improves adaptation but may erode learned safety behavior. Existing methods

safetyarxiv-cs-ai

U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training

model-releasesarxiv-cs-cv

arXiv:2606.11032v1 Announce Type: new Abstract: Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution

Ugh, I’m completely lost. I can’t get VS Code on Windows to connect to Ollama, it’s installed on a local Ubuntu server and I’m struggling to configure it.

This post discusses troubleshooting steps for connecting Visual Studio Code running on Windows to an Ollama instance installed on a local Ubuntu server, addressing configuration and connectivity issue

local-air-ollama

UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data

model-releasesarxiv-cs-ro

arXiv:2606.10382v1 Announce Type: new Abstract: Real-robot evaluation is essential for understanding whether learned manipulation policies can operate reliably outside curated demonstrations. This nee

Uncertainty-Aware Deep Learning for Wildfire Danger Forecasting

arXiv:2509.25017v2 Announce Type: replace-cross Abstract: Wildfires are among the most severe natural hazards, posing a significant threat to both humans and natural ecosystems. The growing risk of wi

researcharxiv-cs-cv

Uncertainty-Aware Motion Planning for Autonomous Driving in Mixed Traffic Environment

model-releasesarxiv-cs-ai

arXiv:2606.09958v1 Announce Type: cross Abstract: In mixed-traffic environments where autonomous and human-driven vehicles may co-exist, motion planning for autonomous vehicles requires anticipating t

Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows

arXiv:2606.09857v1 Announce Type: new Abstract: Reduced-order models (ROMs) provide an efficient surrogate for complex multiscale systems, but their predictive accuracy is often compromised by truncat

Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults

arXiv:2606.10501v1 Announce Type: new Abstract: Deploying Vision-Language-Action (VLA) models in real robotic systems requires robustness not only to semantic and perceptual variations, but also to em

safetyarxiv-cs-ro

Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill

arXiv:2606.11007v1 Announce Type: cross Abstract: OpenClaw has rapidly emerged as a transformative artificial intelligence (AI) agent framework, and its ability to autonomously execute complex, multi-

agentsarxiv-cs-ai

UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data

arXiv:2606.10683v1 Announce Type: cross Abstract: Dexterous hands are essential for fine-grained manipulation, but their hardware designs vary substantially across embodiments. Differences in kinemati

Hardware

Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey

arXiv:2606.10706v1 Announce Type: cross Abstract: Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often stu

hardwarearxiv-cs-ai

Unifying Local Communications and Local Updates for LLM Pretraining

arXiv:2606.11081v1 Announce Type: cross Abstract: Communication-efficient pre-training of LLMs is increasingly important as training draws on compute distributed across clusters, data centers, and low

local-aiarxiv-cs-ai

UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors

arXiv:2606.11131v1 Announce Type: new Abstract: Most existing deep learning-based PET image denoising methods assume a fixed and known dose reduction factor (DRF) for low-dose PET images. However, the

safetyarxiv-cs-cv

UniSVQ: 2-bit Unified Scalar-Vector Quantization

arXiv:2606.10520v1 Announce Type: new Abstract: Post-training quantization at the 2-bit level enables low-cost deployment and inference acceleration for large language models (LLMs). Scalar quantizati

researcharxiv-cs-cl

Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Images

arXiv:2501.01481v2 Announce Type: replace-cross Abstract: Reconstructing Hyperspectral Images (HSI) from RGB images can yield high spatial resolution HSI at a lower cost, demonstrating significant app

local-aiarxiv-cs-cv

Unsupervised Deep Learning for Limited-Angle STEM-EDX Tomography -- Application to 3D Chemical Analysis of Phase-Change Memory Devices

arXiv:2606.10547v1 Announce Type: cross Abstract: Energy Dispersive X-ray (EDX) tomography in Scanning Transmission Electron Microscopy (STEM) enables 3D compositional and elemental mapping at the nan

Tutorials

Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion

arXiv:2606.10099v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns about misuse such as plagiarism, misinformation, and automated influence ope

tutorialsarxiv-cs-ai

UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

arXiv:2606.10466v1 Announce Type: cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fail

applicationsarxiv-cs-ai

Upper Bounds for Local Learning Coefficients of Three-Layer Neural Networks

arXiv:2603.12785v2 Announce Type: replace Abstract: Three-layer neural networks are known to form singular learning models, and their Bayesian asymptotic behavior is governed by the learning coefficie

Industry

U.S. and China AI development will continue to fluctuate between 3 and 15 months. It's interesting that China is becoming open, and the U.S.…

U.S. and China AI development will continue to fluctuate between 3 and 15 months. It's interesting that China is becoming open, and the U.S. is becoming closed. Great conversation with @alansmurray at

industrykai-fu-lee--x