Search: “models”

Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery

arXiv:2605.17976v1 Announce Type: new Abstract: Scientific discovery is increasingly constrained by costly experiments and limited resources, underscoring the need for efficient optimization in AI for

Research

Unleashing Vision Transformer Potential In Image Quality Assessment via Global-Local Adaptive Interaction

DGX agent

arXiv:2605.17748v1 Announce Type: new Abstract: In the field of Blind Image Quality Assessment (BIQA), accurately predicting the perceptual quality of authentically distorted images remains highly cha

researcharxiv-cs-cv

19 May 2026

Vector RAG vs LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research

arXiv:2605.18490v1 Announce Type: new Abstract: We preregistered a comparison of two ways to help an LLM answer questions over a small research corpus: a single-round Vector RAG system and an LLM-comp

researcharxiv-cs-cl

Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation

arXiv:2605.16393v1 Announce Type: cross Abstract: Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (Vi

VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers

arXiv:2605.17312v1 Announce Type: new Abstract: Video style transfer aims to render videos in a target artistic style while preserving content, structure, and motion. While image stylization has advan

Voice ''Cloning'' is Style Transfer

arXiv:2605.16578v1 Announce Type: cross Abstract: Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity preservation

Voices in the Loop: Mapping Participatory AI

arXiv:2605.16827v1 Announce Type: new Abstract: Participatory approaches to artificial intelligence are increasingly documented across public, civic, and humanitarian settings, but evidence about how

Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy

arXiv:2605.16796v1 Announce Type: cross Abstract: Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property.

Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation

arXiv:2605.18507v1 Announce Type: new Abstract: Due to the difficulty of obtaining ground-truth data for 4D radar scene flow estimation, previous methods typically rely on either self-supervised losse

applicationsarxiv-cs-cv

When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering

arXiv:2605.17658v1 Announce Type: new Abstract: Different age-related regulations have been proposed to protect minors from harmful content and interactions online. Automated age estimation is central

Tutorials

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

arXiv:2509.17680v2 Announce Type: replace Abstract: Table question answering (TableQA) is a fundamental task in natural language processing (NLP). The strong reasoning capabilities of large language m

tutorialsarxiv-cs-cl

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations

arXiv:2511.06516v3 Announce Type: replace Abstract: Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering

researcharxiv-cs-cl

A look at a new class of jobs created by AI companies, including AI storytellers or 'evangelists', forward deployed engineers, AI chiefs, and AI gig workers (Brent D. Griffiths/Business Insider)

Brent D. Griffiths / Business Insider: A look at a new class of jobs created by AI companies, including AI storytellers or “evangelists”, forward deployed engineers, AI chiefs, and AI gig workers — -

industrytechmeme

A QUBO Formulation Framework for Kinematic Structure-Based Robot Design Optimization: A Robotic Hand Case Study

arXiv:2605.15510v1 Announce Type: new Abstract: This paper presents a quadratic unconstrained binary optimization-based formulation framework for robot design optimization using kinematic structure-le

applicationsarxiv-cs-ro

A Retrieval-Enhanced Transformer for Multi-Step Port-of-Call Sequence Prediction in Global Liner Shipping

arXiv:2605.15937v1 Announce Type: new Abstract: Accurate multi-step port-of-call sequence prediction is vital for tactical resource orchestration and logistical efficiency. However, existing methods s

Hardware

A Unified Non-Parametric and Interpretable Point Cloud Analysis via t-FCW Graph Representation

arXiv:2605.15475v1 Announce Type: new Abstract: We introduce an empowered transposed Fully Connected Weighted (t-FCW) graph representation to embed point clouds into a metric space. While original t-F

hardwarearxiv-cs-cv

AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression

arXiv:2605.15921v1 Announce Type: new Abstract: Object removal aims to eliminate specified objects from images while plausibly inpainting the affected regions with background content. Current training

ADAPT: A Self-Calibrating Proactive Autoscaler for Container Orchestration

arXiv:2605.15788v1 Announce Type: cross Abstract: Proactive autoscaling for containerized workloads depends on knowing the provisioning delay, i.e., the time between a scaling decision and the moment

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking

arXiv:2510.13842v2 Announce Type: replace-cross Abstract: Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge ba

An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendations

arXiv:2605.15213v1 Announce Type: cross Abstract: Diet quality is a leading determinant of chronic disease risk. Advances in artificial intelligence (AI) have enabled food recommendation systems to ad

Announcing the Databricks analytics engineer learning pathway

Databricks announced a new learning pathway designed to help professionals develop skills in analytics engineering. The program likely covers essential competencies such as data transformation, SQL, d

industrydatabricks

b9213

local-aillama-cpp-releases

I was unable to find specific details about the b9213 release in the search results. Based on the context from the llama.cpp project, b9213 is an intermediate build release of llama.cpp, the C/C++ imp

Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues

arXiv:2605.15984v1 Announce Type: cross Abstract: Toxic speech detection has become a crucial challenge in maintaining safe online communication environments. However, existing approaches to toxic spe

BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction

arXiv:2510.01632v3 Announce Type: replace-cross Abstract: Protein function is driven by cohesive substructures, such as catalytic triads, binding pockets, and structural motifs, that occupy only a sma

Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling

arXiv:2507.01679v3 Announce Type: replace-cross Abstract: Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each par

BMW sends off the 6th-gen M3 CS with a manual gearbox, rear-wheel drive

BMW M marks the close of the sixth-generation M3 with the limited-edition M3 CS Handschalter, pairing lightweight construction with a 6-speed manual transmission and rear-wheel drive. The twin-turbo 3

industryars-technica

Hardware

Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory 'VaCoAl' as a Substrate for Vector-HaSH and TEM

arXiv:2605.15652v1 Announce Type: cross Abstract: Vector-HaSH and the Tolman-Eichenbaum Machine (TEM) propose that the hippocampal-entorhinal circuit factorizes content from a prestructured grid-cell

hardwarearxiv-cs-ai

chatgpt has gotten soooo much better with the latest update. really proud of the team for this one.

Sam Altman, CEO of OpenAI, posted on X praising the latest ChatGPT update, expressing satisfaction with improvements made by the development team. The post indicates significant performance or capabil

industrysam-altman--x

CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

arXiv:2605.15888v1 Announce Type: cross Abstract: Heterogeneous Graph Prompt Learning (HGPL)has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation m

Agents

CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents

arXiv:2512.01089v2 Announce Type: replace Abstract: Automated Scientific Discovery (ASD) systems can help automatically generate and run code-based experiments, but their capabilities are limited by t

agentsarxiv-cs-ai

Constrained MPC-Based Motion Planning for Morphing Quadrotors in Ultra-Narrow Passages under Limited Perception

arXiv:2605.15999v1 Announce Type: new Abstract: This paper introduces a motion planning framework to plan morphology and trajectory for morphing quadrotors under extremely constrained environments. We

safetyarxiv-cs-ro

DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer

arXiv:2605.15681v1 Announce Type: cross Abstract: Recently, diffusion-based material transfer methods rely on image fine-tuning or complex architectures with auxiliary networks but face challenges suc

Designing Datacenter Power Delivery Hierarchies for the AI Era

arXiv:2605.16255v1 Announce Type: cross Abstract: Demand for AI accelerators is rapidly increasing rack power density, with projections approaching 1MW per deployment by 2027. This poses a major chall

Agents

Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis

arXiv:2605.15569v1 Announce Type: cross Abstract: Microservices are widely adopted in modern cloud systems due to their scalability and fault tolerance. However, microservice architectures introduce s

agentsarxiv-cs-ai

Diffusion Policy for Coordinated Control of a Nonholonomic Mobile Base and Dual Arms in Door Opening and Passing

arXiv:2605.15352v1 Announce Type: new Abstract: Opening heavy, self closing doors, especially those that require pulling remains a long standing challenge in robotics. Humans naturally employ both arm

safetyarxiv-cs-ro

Domain-Independent Game Abstraction using Word Embedding Techniques

arXiv:2605.15543v1 Announce Type: cross Abstract: Many games of interest in the real world are often intractably large, thereby necessitating the use of game abstraction to shrink them in size, typica

Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics

arXiv:2605.15459v1 Announce Type: new Abstract: The minima of modern neural network loss functions are typically not isolated, rather they form connected components of reparameterization invariant sol

local-aiarxiv-cs-lg

Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power

arXiv:2512.09673v3 Announce Type: replace-cross Abstract: Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide doma

Efficient Image Synthesis with Sphere Latent Encoder

arXiv:2605.15592v1 Announce Type: new Abstract: Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Desp

Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking

arXiv:2510.04930v2 Announce Type: replace Abstract: Grokking is the phenomenon whereby, unlike the training performance, which peaks early in the training process, the test/generalization performance

Tutorials

EMFusion: An Uncertainty-Aware Conditional Diffusion Framework for Frequency-Selective EMF Forecasting in Wireless Networks

arXiv:2512.15067v3 Announce Type: replace-cross Abstract: The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to e

tutorialsarxiv-cs-ai

EndoGSim: Physics-Aware 4D Dynamic Endoscopic Scene Simulations via MLLM-Guided Gaussian Splatting

arXiv:2605.16022v1 Announce Type: new Abstract: In robot-assisted minimally invasive surgery, high-fidelity dynamic endoscopic scene reconstruction and simulation are crucial to enhancing downstream t

Fast Expanding Safe Circular Regions for Efficient Local Path Planning

arXiv:2605.16009v1 Announce Type: new Abstract: Local navigation is one of the fundamental problems in robot navigation, and numerous approaches have been proposed over the years, including methods su

local-aiarxiv-cs-ro

FedOptima: Optimizing Resource Utilization in Federated Learning

arXiv:2504.13850v2 Announce Type: replace-cross Abstract: Federated learning (FL) systems facilitate distributed machine learning across a server and multiple devices. However, FL systems have low res

applicationsarxiv-cs-lg

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

arXiv:2604.04539v2 Announce Type: replace Abstract: Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Poli

safetyarxiv-cs-lg

Flatness-based trajectory planning for 3D overhead cranes with friction compensation and collision avoidance

arXiv:2510.24457v2 Announce Type: replace Abstract: This paper presents an optimal trajectory generation method for 3D overhead cranes by leveraging differential flatness. This framework enables the d

researcharxiv-cs-ro

FlipAttack: Jailbreak LLMs via Flipping

arXiv:2410.02832v2 Announce Type: replace-cross Abstract: This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we

🧬 flux-genotype: A self-evolving AI kernel that runs on CPU with Ollama — mutates its own architecture

Flux-genotype is a self-evolving AI kernel designed to run on CPU hardware using Ollama, featuring the capability to mutate and adapt its own architecture dynamically. This project demonstrates an app

local-air-ollama