All entries

Trainable Nonexpansive Denoisers for Contractive Image Reconstruction

arXiv:2607.23347v1 Announce Type: cross Abstract: Trainable denoisers with Lipschitz control have become central to convergent image reconstruction. However, training neural networks that simultaneous

Local Ai

Training Language Models to Cooperate with Inference-Time Controllers

DGX agent

arXiv:2607.23771v1 Announce Type: new Abstract: Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reaso

local-aiarxiv-cs-ai

28 Jul 2026

Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex

arXiv:2607.23333v1 Announce Type: cross Abstract: We revisit the regret loss framework introduced in Park et al. (2025), which uses decision-theoretic regret as a direct loss function for training mod

safetyarxiv-cs-ai

Transfer Learning Architectures for Scalable Multi-Fidelity Bayesian Optimization

arXiv:2607.23404v1 Announce Type: new Abstract: Self-driving laboratories increasingly rely on multi-fidelity Bayesian optimization (MFBO) to balance cheap, approximate evaluations against scarce, exp

Transfer learning for conflict and duplicate detection in software requirement pairs

arXiv:2301.03709v3 Announce Type: replace-cross Abstract: Consistent and holistic expression of software requirements is important for the success of software projects. In this study, we aim to enhanc

researcharxiv-cs-lg

TRE: Training-Free Hallucination Detection for Diffusion Language Models

arXiv:2607.22661v1 Announce Type: new Abstract: Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination

TreeAdapter: Hierarchical Taxonomy-Guided Adapter Composition for Fine-Grained Species Image Generation

arXiv:2607.24215v1 Announce Type: new Abstract: Although general text-to-image models excel in open-domain generation, their performance degrades significantly in specialized downstream domains, parti

TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law

model-releasesarxiv-cs-cl

arXiv:2507.21134v2 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their d

TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation

arXiv:2607.23838v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) lets a large language model answer questions using documents retrieved from an external knowledge base at query t

TriSP: Tri-Signal Structured Pruning for Large Language Models

arXiv:2607.22587v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their

Agents

TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs

arXiv:2607.23734v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs) have emerged as a key enabler of next-generation Internet of Things (IoT) ecosystems, offering flexible aerial relayin

agentsarxiv-cs-lg

Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation

model-releasesarxiv-cs-cv

arXiv:2607.22727v1 Announce Type: new Abstract: Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can

Try Once, Then Optimal: De-Redundified Procedure Memory for Cross-Episode Exploration Amortization

model-releasesarxiv-cs-ro

arXiv:2607.23702v1 Announce Type: new Abstract: Manipulating objects with hidden internal state, such as a latched microwave, forces a robot to probe before it can act. Yet a robot that has solved an

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong

model-releasesarxiv-cs-cl

arXiv:2607.23458v1 Announce Type: new Abstract: Chain-of-thought (CoT) explanations support oversight only if they are faithful: the stated reasoning must actually produce the answer. Auditing black-b

Two-Timescale Hierarchical Reinforcement Learning for Resilient Operations

arXiv:2607.23434v1 Announce Type: cross Abstract: Unexpected shocks recur in global operations, requiring decision rules that adapt as market and operating conditions change. Many operational systems

UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agents

model-releasesarxiv-cs-cv

arXiv:2508.00288v5 Announce Type: replace-cross Abstract: Aerial navigation is a fundamental yet underexplored capability in embodied intelligence, enabling agents to operate in large-scale, unstructu

Industry

UK startup Dwelly, which buys real estate businesses and adds AI to handle maintenance, contracts, and other tasks, raised 95M in equity and 75M in debt (Yazhou Sun/Bloomberg)

Yazhou Sun / Bloomberg: UK startup Dwelly, which buys real estate businesses and adds AI to handle maintenance, contracts, and other tasks, raised 95M in equity and 75M in debt — British startup Dwell

industrytechmeme

Local Ai

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

arXiv:2607.23373v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deployment on resource-constrained edge d

local-aiarxiv-cs-cv

UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing

arXiv:2607.24298v1 Announce Type: new Abstract: Recent 3D foundation models can generate high-quality assets from a single image, but degrade markedly on unconstrained multi-image inputs, often produc

Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search

arXiv:2607.23854v1 Announce Type: new Abstract: Humans often find good solutions to combinatorial optimization problems that are computationally hard even for advanced computer algorithms. In the Eucl

researcharxiv-cs-ai

Understanding Machine Unlearning Through the Lens of Mode Connectivity

arXiv:2607.23970v1 Announce Type: cross Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss la

Understanding Tone-Dependent Inference Cost in Large Language Models

arXiv:2607.23915v1 Announce Type: cross Abstract: We examine how prompt tone affects both accuracy of the LLM answers and inference cost as reflected in output-token consumption. Experiments were perf

Unequal Trips, Unequal Places: Diagnosing and Mitigating Delay Inequity in Autonomous Vehicle Fleet Coordination

arXiv:2607.24336v1 Announce Type: new Abstract: City-scale autonomous vehicle fleet coordinators are typically optimized for aggregate travel time, yet fleet averages conceal how delay is distributed

safetyarxiv-cs-ai

UNet: A Generic and Reliable Multi-UAV Communication and Networking Architecture for Heterogeneous Applications

arXiv:2411.03048v2 Announce Type: replace-cross Abstract: The rapid growth of UAV applications necessitates a robust communication and networking system architecture capable of addressing the diverse

researcharxiv-cs-ro

Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training

arXiv:2512.24125v3 Announce Type: replace-cross Abstract: General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action executio

UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

arXiv:2607.24507v1 Announce Type: cross Abstract: Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diff

Unifying Complementarity Constraints and Control Barrier Functions for Safe Whole-Body Robot Control

arXiv:2504.17647v2 Announce Type: replace Abstract: Safety-critical whole-body robot control demands reactive methods that ensure collision avoidance in real-time. Complementarity constraints and cont

safetyarxiv-cs-ro

UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling

arXiv:2607.24157v1 Announce Type: new Abstract: Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled

Unsupervised Graph Representation Learning with Complementary View Alignment

arXiv:2607.24338v1 Announce Type: new Abstract: Unsupervised graph representation learning aims to derive meaningful node embeddings by capturing both structural and attribute information without rely

UP-Fuse: Uncertainty-guided LiDAR-Camera Fusion for 3D Panoptic Segmentation

arXiv:2602.19349v2 Announce Type: replace-cross Abstract: LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a c

Update your chat template for dsv4 if you're using llama.cpp

model-releasesr-localllama

Following some recent commits in llama.cpp, preserve_thinking behavior for chat templates included in older DSV4 ggufs got broken. This makes the model pretty dumb in a coding agent context. Adding kw

URHead: A Unified UV-Space Representation for Joint Mesh-3DGS Optimization in Head Avatars

arXiv:2607.22673v1 Announce Type: cross Abstract: We present URHead, a unified representation for high-fidelity and animatable head avatars that fundamentally redefines mesh-Gaussian integration. Whil

Using Reinforcement Learning to Optimize the Global and Local Crossing Number

arXiv:2509.06108v3 Announce Type: replace-cross Abstract: Graph drawing concerns the algorithmic visualization of graphs. A good drawing of a graph is easy to read and facilitates solving tasks on the

Variable Importance Identification Through Lazy Training for Binary Classification

arXiv:2607.22979v1 Announce Type: cross Abstract: Deep neural networks have been widely used in many applications (e.g., computer vision and natural language processing); however, understanding their

researcharxiv-cs-lg

Variance-Preserving Orthogonal Selection (VPOS): Greedy Feature Selection via Orthogonal Deflation in PCA Loading Space

arXiv:2607.23198v1 Announce Type: new Abstract: We propose Variance-Preserving Orthogonal Selection (VPOS), a greedy framework for unsupervised feature selection that operates in the weighted PCA load

researcharxiv-cs-lg

Variational Boosting for Physics-Informed Neural Networks

arXiv:2607.23940v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) solve differential equations by minimizing the residual of a nonlinear operator over a neural parameterization

safetyarxiv-cs-lg

Variational-Ising-Attention (VIA):TailoredAttentionMattersfor Science

arXiv:2607.23634v1 Announce Type: cross Abstract: Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research ha

researcharxiv-cs-ai

Variational Quantum Conditional Boltzmann Machines for Time-Series Forecasting: Architectures, Symmetric Hyperparameter Evaluation, and a Nonlinear Benchmark

arXiv:2607.24065v1 Announce Type: cross Abstract: In this study, we developed and evaluated four conditional energy-based forecasting architectures: a classical Gaussian-Bernoulli CRBM, a hybrid quant

Local Ai

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy

arXiv:2607.23006v1 Announce Type: cross Abstract: Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the suppo

local-aiarxiv-cs-ai

Applications

VEMamba: Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral Consistent Mamba

arXiv:2603.00887v2 Announce Type: replace Abstract: Volume Electron Microscopy (VEM) is crucial for 3D tissue imaging but often produces anisotropic data with poor axial resolution, hindering visualiz

applicationsarxiv-cs-cv

Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses

model-releasesarxiv-cs-cl

arXiv:2607.22961v1 Announce Type: cross Abstract: Verbalized Machine Learning (VML) parameterizes a model as a natural-language prompt that an LLM evaluates as f(x; theta). The framework is interpreta

Verification-Notebook Learning for Source-Aware Multimodal Misinformation Detection

arXiv:2607.23581v1 Announce Type: new Abstract: Multimodal misinformation verification is challenging because misleading signals may come from different parts of a post and require different forms of

researcharxiv-cs-ai

Tutorials

Very interesting paper on LLM reasoning. They find that frontier models can exhibit invisible reasoning by leveraging semantically irrelevan…

Very interesting paper on LLM reasoning. They find that frontier models can exhibit invisible reasoning by leveraging semantically irrelevant filler tokens. In other words, invisible reasoning can ser

tutorialsdair-ai--x

ViDS: Video Diffusion Shader using 3D Face Tracking

arXiv:2607.24124v1 Announce Type: new Abstract: We introduce ViDS, a Video Diffusion Shader that leverages 3D face tracking for expressive and identity-preserving portrait animation. We first reconstr

VIP: Finding Important People in Images

arXiv:1502.05678v3 Announce Type: replace Abstract: People preserve memories of events such as birthdays, weddings, or vacations by capturing photos, often depicting groups of people. Invariably, some

Tutorials

VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation

arXiv:2607.23472v1 Announce Type: new Abstract: Modern video generation models can synthesize visually compelling and temporally coherent clips, yet controlling their physical behavior remains difficu

tutorialsarxiv-cs-cv

Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model

arXiv:2607.22704v1 Announce Type: cross Abstract: Nuclear fusion has made significant progress in recent years and is expected to become one of the most important pathways to addressing global energy

Applications

Visible to the Court: How AI Is (and Isn't) Litigated in U.S. Federal Court Opinions

arXiv:2607.23888v1 Announce Type: cross Abstract: In the United States, artificial intelligence (AI) is rapidly deployed amid limited federal regulation. With courts become a recurring forum in which

applicationsarxiv-cs-ai