Search: “models”

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference

arXiv:2605.00392v1 Announce Type: new Abstract: DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundan

Model Releases

Scalable Context-Aware Graph Attention for Unsupervised Anomaly Detection in Large-Scale Mobile Networks

DGX agent

arXiv:2605.00482v1 Announce Type: new Abstract: Mobile network operators must monitor thousands of heterogeneous network elements across the radio access network and the packet core, each exposing hig

model-releasesarxiv-cs-lg

4 May 2026

SCAN: Structured Capability Assessment and Navigation for LLMs

arXiv:2505.06698v4 Announce Type: replace Abstract: Evaluating Large Language Models (LLMs) has become increasingly important, with automatic evaluation benchmarks gaining prominence as alternatives t

researcharxiv-cs-cl

Sentinel: an open-source local-first desktop app for AI coding

Sentinel is a local-first AI coding desktop application built with Rust and Tauri that automatically routes coding tasks to appropriate models based on task complexity. Instead of swapping between mul

local-air-ollama

State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning

model-releasesarxiv-cs-cl

arXiv:2605.00206v1 Announce Type: cross Abstract: Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and lea

Static and Dynamic Graph Alignment Network for Temporal Video Grounding

arXiv:2605.00684v1 Announce Type: new Abstract: Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. R

Temporal Data Requirement for Predicting Unplanned Hospital Readmissions

arXiv:2605.00738v1 Announce Type: new Abstract: With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical dat

Tempus: A Temporally Scalable Resource-Invariant GEMM Streaming Framework for Versal AI Edge

arXiv:2605.00536v1 Announce Type: cross Abstract: Scaling laws for Large Language Models (LLMs) establish that model quality improves with computational scale, yet edge deployment imposes strict const

local-aiarxiv-cs-lg

Thought Graph Traversal for Test-time Scaling in Chest X-ray VLLMs

arXiv:2506.11989v3 Announce Type: replace Abstract: Test-time scaling offers a promising way to improve the reasoning performance of vision-language large models (VLLMs) without additional training. I

TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference

arXiv:2505.11329v5 Announce Type: replace-cross Abstract: Distributed inference of large language models (LLMs) using tensor parallelism can introduce communication overheads of 20% even over GPUs con

local-aiarxiv-cs-lg

Safety

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

arXiv:2605.00658v1 Announce Type: new Abstract: Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often tr

safetyarxiv-cs-cv

Hardware

NVIDIA's New AI Turns One Photo Into A World That Never Breaks

hardwaretwo-minute-papers

NVIDIA's Instant Splat is a breakthrough AI technique that synthesizes missing information from a few images to create immersive 3D models of virtual worlds. The method produces high-quality 3D models

3 May 2026

zit vs zib settings question

local-air-stablediffusion

ZIT (Z-Image Turbo) is a compact, fast distilled model tuned for photorealism that uses 8 inference steps with a fixed CFG of 1, which limits creativity . ZIB (Z-Image Base) is an undistilled model id

3 May 2026

A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion

arXiv:2501.07451v4 Announce Type: replace Abstract: Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g.

Adaptive Nonlinear MPC for Trajectory Tracking of An Overactuated Tiltrotor Hexacopter

arXiv:2211.06762v2 Announce Type: replace Abstract: Omnidirectional micro aerial vehicles (OMAVs) are more capable of doing environmentally interactive tasks due to their ability to exert full wrenche

researcharxiv-cs-ro

Agentic AI for Cybersecurity: A Meta-Cognitive Architecture for Governable Autonomy

arXiv:2602.11897v3 Announce Type: replace-cross Abstract: Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipul

Hardware

All the Doomers and hawks are lining up behind this distillation 'attack' farce because they want to see open source banned. It's really as …

All the Doomers and hawks are lining up behind this distillation 'attack' farce because they want to see open source banned. It's really as simple as that. They want to take away your right to choose,

hardwareyann-lecun--x

Assessing Pancreatic Ductal Adenocarcinoma Vascular Invasion: the PDACVI Benchmark

arXiv:2604.27582v1 Announce Type: new Abstract: Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate asse

Autoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Data

model-releasesarxiv-cs-lg

arXiv:2603.01444v2 Announce Type: replace Abstract: Synthetic data generation is an important capability for privacy-preserving data sharing, system benchmarking and test data provisioning. For mixed-

Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces

arXiv:2604.28122v1 Announce Type: new Abstract: Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often f

Contextual Online Uncertainty-Aware Preference Learning for Human Feedback

arXiv:2504.19342v3 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human pr

Tutorials

Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining

arXiv:2509.05291v2 Announce Type: replace-cross Abstract: Large language models (LLMs) learn non-trivial abstractions during pretraining, such as detecting irregular plural noun subjects. However, bec

tutorialsarxiv-cs-ai

Safety

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

arXiv:2604.27977v1 Announce Type: new Abstract: Despite recent progress in language models and agents for scientific data-driven discovery, further advancing their capabilities is held back by the abs

safetyarxiv-cs-ai

Tutorials

Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders

arXiv:2604.28176v1 Announce Type: cross Abstract: Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as b

tutorialsarxiv-cs-lg

Hardware

Efficient Training on Multiple Consumer GPUs with RoundPipe

arXiv:2604.27085v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) on consumer-grade GPUs is highly cost-effective, yet constrained by limited GPU memory and slow PCIe intercon

hardwarearxiv-cs-ai

How do I change temperature parameters and all that?

This discussion thread covers how to adjust temperature parameters in Ollama, the local language model platform. The post likely addresses configuration methods for controlling model sampling temperat

local-air-ollama

Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization

arXiv:2604.27335v1 Announce Type: new Abstract: Web filtering systems rely on accurate web content classification to block cyber threats, prevent data exfiltration, and ensure compliance. However, cla

Man, Machine, and Mathematics

arXiv:2604.27052v1 Announce Type: cross Abstract: Nonlinear models and optimization methods have successfully tackled a rapidly growing set of problems in recent years. Indeed, a relatively small tool

Measurement Risk in Supervised Financial NLP: Rubric and Metric Sensitivity on JF-ICR

arXiv:2604.27374v1 Announce Type: new Abstract: As LLMs become credible readers of earnings calls, investor-relations Q&A, guidance, and disclosure language, supervised financial NLP benchmarks increa

OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research

arXiv:2504.15564v3 Announce Type: replace-cross Abstract: Existing class-level code generation datasets are either synthetic (ClassEval: 100 classes) or insufficient in scale for modern training needs

Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation

arXiv:2604.27201v1 Announce Type: cross Abstract: Hybrid-thinking language models expose explicit think and no-think modes, but current designs do not separate them cleanly. Even in no-think mode, mod

Physically-Informed Fuzzy Clustering of Vertical Sounding Ionograms

arXiv:2604.27721v1 Announce Type: cross Abstract: This paper presents a physically-informed fuzzy clustering of vertical sounding ionograms for automatically separating the ionogram into tracks suitab

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains

arXiv:2508.21787v2 Announce Type: replace-cross Abstract: Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate so

Predicting Fetal Birthweight from High Dimensional Data using Advanced Machine Learning

arXiv:2502.14270v3 Announce Type: replace Abstract: Birth weight serves as a fundamental indicator of neonatal health, closely linked to both early medical interventions and long-term developmental ri

Progressive Multi-Agent Reasoning for Biological Perturbation Prediction

arXiv:2602.07408v2 Announce Type: replace Abstract: Predicting gene regulation responses to biological perturbations requires reasoning about underlying biological causalities. While large language mo

Agents

Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning

arXiv:2505.19630v4 Announce Type: replace Abstract: Large language models (LLMs) struggle in real-world clinical consultations. Single-turn consultation systems require patients to describe all sympto

agentsarxiv-cs-cl

RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation

arXiv:2604.27559v1 Announce Type: cross Abstract: Radiology report generation (RRG) has emerged as a promising approach to alleviate radiologists' workload and reduce human errors by automatically gen

SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation

arXiv:2604.27555v1 Announce Type: new Abstract: Automatically generating interactive 3D indoor scenes from natural language is crucial for virtual reality, gaming, and embodied AI. However, existing L

Spectral Dynamic Attention Network for Hyperspectral Image Super-Resolution

arXiv:2604.27326v1 Announce Type: cross Abstract: Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle wi

Safety

Test Before You Deploy: Governing Updates in the LLM Supply Chain

arXiv:2604.27789v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously thro

safetyarxiv-cs-ai

Toward Personalized Digital Twins for Cognitive Decline Assessment: A Multimodal, Uncertainty-Aware Framework

arXiv:2604.27217v1 Announce Type: new Abstract: Cognitive decline is highly heterogeneous across individuals, which complicates prognosis, trial design, and treatment planning. We present the Personal

Towards single-shot coherent imaging via overlap-free ptychography

arXiv:2602.21361v3 Announce Type: replace-cross Abstract: Ptychographic imaging at synchrotron and XFEL sources requires dense overlapping scans, limiting throughput and increasing dose. Extending coh

Applications

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning

arXiv:2604.27861v1 Announce Type: cross Abstract: Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a seq

applicationsarxiv-cs-cl

Uni-HOI:A Unified framework for Learning the Joint distribution of Text and Human-Object Interaction

arXiv:2604.27491v1 Announce Type: new Abstract: Modeling 4D human-object interaction (HOI) is a compelling challenge in computer vision and an essential technology powering virtual and mixed-reality a

VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checking

arXiv:2601.08611v2 Announce Type: replace-cross Abstract: The growing scale of online misinformation urgently demands Automated Fact-Checking (AFC). Existing benchmarks for evaluating AFC systems, how

VerteNet -- A Multi-Context Hybrid CNN Transformer for Accurate Vertebral Landmark Localization in Lateral Spine DXA Images

arXiv:2502.02097v3 Announce Type: replace Abstract: This aims to develop and validate a deep learning model that can accurately locate vertebral landmarks in lateral spine Dual energy X-ray Absorptiom

local-aiarxiv-cs-cv

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

arXiv:2602.23163v3 Announce Type: replace Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanis

30 Apr 2026

Assessing the Utility of Volumetric Motion Fields for Radar-based Precipitation Nowcasting with Physics-informed Deep Learning

arXiv:2603.13589v2 Announce Type: replace-cross Abstract: Estimating motion from spatiotemporal geoscientific data is a fundamental component of many environmental modeling and forecasting tasks. In t