All entries

Deep Learning Method for Stationary Distribution of Reflected Brownian Motion

arXiv:2607.08091v1 Announce Type: cross Abstract: The stationary distribution of reflected Brownian motion (RBM) plays an important role in the analysis of high-dimensional stochastic systems, yet clo

Applications

DeepPySR -- A Symbolic Regression Framework with Dynamic Pruning, Pareto Selection, and Hierarchical Composition for Real-World Scientific Discovery

DGX agent

arXiv:2607.08150v1 Announce Type: new Abstract: Symbolic regression (SR) discovers analytical equations from data, yielding glass-box models with directly interpretable formulas, unlike black-box meth

applicationsarxiv-cs-lg

10 Jul 2026

Agents

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

arXiv:2607.07820v1 Announce Type: new Abstract: Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajector

agentsarxiv-cs-cl

DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks

model-releasesarxiv-cs-lg

arXiv:2607.07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents. Most public agentic coding benchmarks fo

DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution

arXiv:2511.16920v2 Announce Type: replace Abstract: Anomaly generation is often framed as few-shot fine-tuning with anomalous samples, which contradicts the scarcity that motivates generation and tend

safetyarxiv-cs-cv

DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models

arXiv:2607.08434v1 Announce Type: new Abstract: Current Unified Large Multimodal Models (ULMMs) support interleaved multimodal reasoning through textual reasoning and intermediate visual states, but t

Tutorials

Deploying quantized models on Amazon SageMaker AI with Unsloth

In this post, you will learn four deployment patterns for taking models that have already been quantized with Unsloth and deploying them on AWS infrastructure. The patterns use Amazon Elastic Compute

tutorialsaws-ml-blog

Design optimization and robustness analysis of rigid-link flapping mechanisms

arXiv:2503.21204v3 Announce Type: replace Abstract: Rigid link flapping mechanisms remain the most practical choice for flapping wing micro-aerial vehicles (MAVs) to carry useful payloads and onboard

applicationsarxiv-cs-ro

Detecting Ladder Logic Bombs in IEC 61131-3 PLC Programs using ESBMC-PLC+: A Formal Verification Approach with Trigger Synthesis

arXiv:2607.08417v1 Announce Type: new Abstract: A Ladder Logic Bomb (LLB) is malicious control logic in a Programmable Logic Controller (PLC) program that lies dormant until a trigger activates a payl

safetyarxiv-cs-cl

DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation

model-releasesarxiv-cs-ro

arXiv:2607.08751v1 Announce Type: new Abstract: Building general-purpose dexterous manipulation policies requires benchmarks that go beyond isolated tasks to systematically evaluate policies across di

Diagnosing Corruption-Induced Reliability Failures in Vision-Language Models

arXiv:2511.19032v2 Announce Type: replace Abstract: Visual corruptions can change vision--language model (VLM) behavior in ways that top-1 accuracy does not capture. A model may keep the same answer w

safetyarxiv-cs-cv

Diagnosing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry

model-releasesarxiv-cs-lg

arXiv:2606.17093v2 Announce Type: replace Abstract: Learning-based single-shot fringe projection profilometry (FPP) has been studied almost entirely at close range, and the networks used are evaluated

Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech

arXiv:2607.08208v1 Announce Type: new Abstract: This paper describes our self-designed system for Task 1 of the MLC-SLM 2026 Challenge for multilingual two-speaker conversational speech. The system co

Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment

model-releasesarxiv-cs-ai

arXiv:2607.08268v1 Announce Type: new Abstract: High-volume structured extraction pays a large model's latency on every item, so distilling the task into a small on-device model is attractive: compara

Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph

arXiv:2607.08746v1 Announce Type: cross Abstract: While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the ric

Industry

Disable auto-play and infinite scroll or risk massive fines, EU tells Meta

The European Union ordered Meta to disable 'addictive design' elements like infinite scroll and autoplay videos on Facebook and Instagram, or face large fines under the Digital Services Act. The Commi

industryars-technica

Distributed Sketching on Data Partitions for OLS Regression

arXiv:2607.07888v1 Announce Type: new Abstract: This paper studies distributed sketching for ordinary least squares (OLS) regression, an approach that distributes small sketches of a large data set ov

Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation

arXiv:2607.07767v1 Announce Type: cross Abstract: Missing values undermine statistical inference and machine learning pipelines, yet most imputation methods rely on heuristics or restrictive parametri

applicationsarxiv-cs-lg

Dive Into the Implicit Biases of Low-rank Vision-language Alignment

arXiv:2607.08194v1 Announce Type: new Abstract: Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requi

DKDNet: Dual Knowledge and Data-Driven Network for Cross-Domain Automatic Modulation Classification

arXiv:2607.08031v1 Announce Type: cross Abstract: The dynamics of communication environments induce significant distribution shifts across domains, challenging the generalization of deep learning-base

Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?

arXiv:2607.08514v1 Announce Type: new Abstract: Hand-object interaction (HOI) recognition requires capturing both hand manipulations and object transformations. However, existing video-language models

researcharxiv-cs-cv

Do Transformations Reveal the Truth? Generative Residual Learning for Generalized AI-Generated Image Detection

arXiv:2607.08674v1 Announce Type: new Abstract: The rapid advancement of generative AI has enabled the creation of highly realistic deepfake media, posing significant threats, including misinformation

Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution

arXiv:2607.08700v1 Announce Type: new Abstract: Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Befo

DocMaster: A Hierarchical Structure-Aware System for Document Analysis

arXiv:2607.08539v1 Announce Type: cross Abstract: Leveraging large language models (LLMs) to analyze complex documents -- such as academic papers, technical manuals, and financial reports -- has emerg

DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding

arXiv:2607.08642v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting several tokens and verifying them in parallel. Block-diffusion drafters such as DFlash produc

Douglas-Rachford Splitting for Group-Sparse Feedback Linear-Quadratic Control

arXiv:2507.19895v4 Announce Type: replace-cross Abstract: In this paper, we study the distributed linear quadratic problem with fixed communication topology (DFT-LQ) and the sparse feedback linear qua

DR-Arena: an Automated Evaluation Framework for Deep Research Agents

arXiv:2601.10504v2 Announce Type: replace Abstract: As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, rel

safetyarxiv-cs-cl

DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation

arXiv:2607.07817v1 Announce Type: cross Abstract: We present DreamCharacter-1, a lightweight post-adaptation framework that calibrates pretrained 3D foundation models toward high-fidelity, production-

applicationsarxiv-cs-ai

Drift-Aware Temporal Graph Rewiring (DATGR) for Adaptive Semantic Modeling in Biomedical Text

arXiv:2607.08490v1 Announce Type: new Abstract: Biomedical language evolves rapidly as new discoveries emerge, causing traditional text models to lose semantic fidelity over time. Static embeddings an

Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings

arXiv:2508.11847v4 Announce Type: replace-cross Abstract: We propose a method for evaluating the robustness of widely used LLM ranking systems -- variants of a Bradley--Terry model -- to dropping a wo

DrugGen 2: A disease-aware language model for enhancing drug discovery

arXiv:2607.08404v1 Announce Type: cross Abstract: Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properti

Dual-Correlation Hypergraph Network for Unaligned RGBT Video Object Detection and A Large-scale Benchmark

arXiv:2607.08191v1 Announce Type: new Abstract: RGB-Thermal (RGBT) Video Object Detection (VOD) has gained significant traction due to its ability to overcome the limitations of conventional RGB-based

Dual-Difficulty Curriculum Learning for Direct Preference Optimization

arXiv:2504.07856v4 Announce Type: replace Abstract: Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dime

Dynamics of Gradient Descent with Large Step Size Near a Manifold of Flat Minima

arXiv:2607.08380v1 Announce Type: new Abstract: An important quantity in the theory of gradient descent (GD) is the sharpness, defined as the largest eigenvalue of the objective Hessian. Classical ana

Early to Share, Late to Save: Synchronisation-Driven Communication Gating in Bandwidth-Constrained Cooperative VLN

arXiv:2607.08504v1 Announce Type: cross Abstract: Most cooperative Vision-Language Navigation (VLN) methods assume unlimited communication, not considering real-world applications where bandwidth is r

safetyarxiv-cs-ro

Echoes: A semantically-aligned music deepfake detection dataset

arXiv:2603.23667v2 Announce Type: replace-cross Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-

Echoes Across Vietnam's Highlands, Delta, and Coast: A Multilingual Corpus for Cham, Khmer, and Tay-Nung

arXiv:2607.08362v1 Announce Type: new Abstract: Vietnam's ethnic minority languages are almost absent from the field of Natural Language Processing (NLP), and the challenge goes beyond data scarcity:

EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy

arXiv:2607.08659v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains di

Effective Gaussian Management for High-fidelity Scene Reconstruction

arXiv:2509.12742v4 Announce Type: replace Abstract: This paper proposes an effective Gaussian management framework for high-fidelity scene reconstruction of both appearance and geometry. Unlike recent

researcharxiv-cs-cv

Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraints

arXiv:2306.12857v3 Announce Type: replace Abstract: The storage, management, and application of massive spatio-temporal data are widely used in practical scenarios, including public safety. However, d

safetyarxiv-cs-lg

Efficient Safety Alignment of Language Models via Latent Personality Traits

arXiv:2607.07918v1 Announce Type: cross Abstract: Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Late

EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data

arXiv:2607.08436v1 Announce Type: cross Abstract: Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scene

Eigenvalue Calibration for Semantic Embeddings of Large Language Models

arXiv:2607.08377v1 Announce Type: new Abstract: Uncertainty quantification is central to the reliable deployment of large language models (LLMs), and eigenvalues of semantic embeddings have recently e

applicationsarxiv-cs-lg

Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding

arXiv:2512.14236v2 Announce Type: replace Abstract: The growing demand for immersive 3D content calls for automated monocular-to-stereo video conversion. We present Elastic3D, a controllable, direct e

applicationsarxiv-cs-cv

Industry

End of an era: Decommissioning the original Model S & X assembly line in just 46 days

Tesla decommissioned the original Model S and Model X assembly line in 46 days, marking the end of an era for these vehicles that launched the company's expansion beyond the Roadster. This rapid trans

industryelon-musk--x

Tutorials

Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

arXiv:2607.08765v1 Announce Type: new Abstract: In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream t

tutorialsarxiv-cs-cv

Enhancing the KidSat Model: Integrating Geographical Encoding and Data Quality Assessment for Childhood Poverty Prediction

arXiv:2607.08281v1 Announce Type: new Abstract: Accurate poverty mapping using satellite imagery is often hindered by (i) noisy and sparse survey-derived supervision, (ii) image quality issues such as

researcharxiv-cs-cv

Ensemble Diversity Optimization for Subjective Supervision

arXiv:2607.08493v1 Announce Type: cross Abstract: Subjective NLP tasks often exhibit systematic annotator disagreement, requiring models that represent uncertainty rather than collapse it. We introduc

safetyarxiv-cs-cl