Search: “applications”

arXiv:2606.02326v1 Announce Type: new Abstract: Hard constraints are usually treated as terminal vetoes: once a candidate violates a requirement, the learned rule rejects it and any repair is handled

tutorialsarxiv-cs-ai

Model Releases

Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation

DGX agent

arXiv:2602.07083v2 Announce Type: replace-cross Abstract: Structural modeling is a fundamental component of computational engineering science, in which even minor physical inconsistencies or specifica

model-releasesarxiv-cs-ai

2 Jun 2026

RobustModelMaker: Coupling Bootstrap Stability Selection with Leakage-Safe Nested Cross-Validation for Scientific Machine Learning

arXiv:2606.01566v1 Announce Type: new Abstract: Small-to-medium scientific datasets place machine learning pipelines under two compounding pressures. Single-run feature selection produces feature sets

Scalable Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantee: A Constrained Mean-Field Reinforcement Learning Approach

arXiv:2503.24183v3 Announce Type: replace Abstract: The expansion of ride-sourcing services such as Uber and Lyft has reshaped urban transportation by offering flexible, on-demand mobility via mobile

safetyarxiv-cs-lg

Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation

arXiv:2510.24870v2 Announce Type: replace Abstract: We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a preval

researcharxiv-cs-cl

Series-Parallel Integrated Nonlinear Elastic Actuator applied to the lean motion of a bicycle simulator

arXiv:2606.00201v1 Announce Type: new Abstract: Designing robots for high-torque, high-fidelity haptic interaction is challenging. Parallel Elastic Actuators (PEAs) use elastic elements in parallel to

researcharxiv-cs-ro

Tools

Serving MiniMax-M3 for efficient inference: Unlocking 1M-Token Context and Multimodality Without Regrets

MiniMax-M3 is a large language model capable of handling 1 million token contexts and multimodal inputs while maintaining efficient inference performance. Together AI's blog post discusses techniques

toolstogether-ai-blog

ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models

arXiv:2502.08884v3 Announce Type: replace-cross Abstract: We present ShapeLib, the first method that uses the priors of Large Language Models (LLMs) to design libraries of programmatic 3D shape abstra

researcharxiv-cs-ai

ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation

arXiv:2606.02247v1 Announce Type: cross Abstract: Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially wi

SORA: Free Second-Order Attacks in Fast Adversarial Training

arXiv:2606.00738v1 Announce Type: cross Abstract: Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-s

source: https://easternherald.com/2026/06/01/ai-trillion-dollar-frenzy-venture-capital-reality-check/

Gary Marcus discusses the disconnect between venture capital hype surrounding AI's trillion-dollar potential and the practical realities of AI development and market viability. The article likely exam

safetygary-marcus--x

SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL

arXiv:2512.04069v2 Announce Type: replace Abstract: Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required f

agentsarxiv-cs-cv

Statistical Testing on Directed Graphs by Surrogate Data Generation

arXiv:2606.00758v1 Announce Type: cross Abstract: In recent years, graph signal processing has emerged as a powerful framework at the intersection of signal processing and graph theory, providing tool

Industry

Step-3.7-Flash from @StepFun_ai is a silent winner. Super impressive results, the best model under 500B params on HF leaderboards.. All whil…

Step-3.7-Flash is a compact language model from StepFun AI that reportedly achieves top-tier performance among models under 500 billion parameters on Hugging Face leaderboards, despite receiving limit

industryclem-delangue--x

Stochastic Rounding Increases Small Singular Values

arXiv:2606.00312v1 Announce Type: cross Abstract: Over the past half-dozen years, stochastic rounding (SR) has regained significant attention as a quantization scheme for low-precision floating-point

SWARD: Stochastic Window-Attention-Based Relational Distillation for Cross-Architectural Semantic Segmentation

arXiv:2606.00999v1 Announce Type: new Abstract: Large-scale vision foundation models have driven substantial gains on dense prediction tasks such as semantic segmentation, but their size makes deploym

T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining

arXiv:2606.00673v1 Announce Type: new Abstract: Thermal imaging offers a powerful alternative to visible-spectrum vision under challenging conditions such as low illumination and adverse weather, yet

TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks

model-releasesarxiv-cs-lg

arXiv:2606.02384v1 Announce Type: new Abstract: Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures. At the same time, feature engineering remain

Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models

arXiv:2606.02580v1 Announce Type: new Abstract: Inverse graphics is a longstanding and highly underconstrained problem that seeks to reconstruct images as editable 3D scenes which can be rendered, rel

agentsarxiv-cs-cv

Topological texture analysis of microscopy images of dynamic casein gelation and its relation to rheological properties

arXiv:2606.02048v1 Announce Type: new Abstract: We propose a novel computational toolbox that integrates Topological Data Analysis (TDA), Differential Box Counting (DBC), Multifractal Partition (MFP),

researcharxiv-cs-ai

Toward Responsible and Epistemically Grounded Multilingual LLMs for Computational Social Science and Humanities

arXiv:2606.00596v1 Announce Type: new Abstract: Large language models have rapidly evolved in multilingual competence and reasoning capacity, enabling their integration into Social Sciences and Humani

safetyarxiv-cs-cl

Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection

arXiv:2606.01896v1 Announce Type: cross Abstract: Generated (or synthetic) image data is increasingly used to augment or replace real training datasets when target imagery is scarce, expensive, or bia

TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning

arXiv:2508.12551v2 Announce Type: replace-cross Abstract: Linux kernel tuning is essential for optimizing operating system (OS) performance, yet remains challenging due to the complex kernel space, sp

agentsarxiv-cs-ai

UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations

arXiv:2510.13774v2 Announce Type: replace-cross Abstract: Forecasting urban phenomena such as housing prices and public health indicators requires the effective integration of various geospatial data.

v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound

model-releasesarxiv-cs-ai

arXiv:2509.25773v3 Announce Type: replace-cross Abstract: AI models capable of comprehending humor hold real-world promise -- for example, enhancing engagement in human-machine interactions. To gauge

Value Flows

model-releasesarxiv-cs-ai

arXiv:2510.07650v4 Announce Type: replace-cross Abstract: While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods

Vision Language Models Cannot Reason About Physical Transformation

arXiv:2603.07109v2 Announce Type: replace Abstract: Understanding physical transformations is fundamental for reasoning in dynamic environments. While Vision Language Models (VLMs) show promise in emb

researcharxiv-cs-ai

Vision-language Models for Driver Monitoring Systems: A Driver Activity Description Dataset

model-releasesarxiv-cs-cv

arXiv:2606.02273v1 Announce Type: new Abstract: Understanding subtle driver actions is essential for building reliable driver monitoring systems. Existing visionlanguage models (VLMs) are trained on g

WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

model-releasesarxiv-cs-ai

arXiv:2606.01869v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural lan

Zero-Shot Multi-Animal Tracking in the Wild

arXiv:2511.02591v2 Announce Type: replace Abstract: Multi-animal tracking is crucial for understanding animal ecology and behavior, yet remains challenging due to variations in habitat, motion pattern

A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss

model-releasesarxiv-cs-cv

arXiv:2509.10114v2 Announce Type: replace Abstract: Face image quality assessment (FIQA) plays a critical role in face recognition and verification systems, especially in uncontrolled, real-world envi

AgentOps: Operationalize agentic AI at scale with Amazon Bedrock AgentCore

When you build agentic AI solutions, you face unique operational challenges. Agents make unpredictable decisions, costs spiral unexpectedly, and debugging non-deterministic failures seems impossible.

agentsaws-ml-blog

Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding

arXiv:2605.30742v1 Announce Type: new Abstract: This paper addresses the task of temporal sentence grounding (TSG). Although many respectable works have made decent achievements in this important topi

Tutorials

Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks

arXiv:2605.31152v1 Announce Type: cross Abstract: This paper studies how efficiently deep ReLU neural networks can approximate and learn smooth functions. When the error is measured in L^p([0,1]^d) no

tutorialsarxiv-cs-lg

Asymptotically Optimal Sequential Testing with Markovian Data

arXiv:2602.17587v2 Announce Type: replace-cross Abstract: We study one-sided and alpha-correct sequential hypothesis testing for data generated by an ergodic, finite-state Markov chain. The null hypot

BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation

arXiv:2511.19394v2 Announce Type: replace Abstract: Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architec

Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation

arXiv:2605.30585v1 Announce Type: cross Abstract: Effective prognostics and health management of modern engines relies on accurate turbine gas temperature predictions and robust uncertainty quantifica

Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification

model-releasesarxiv-cs-lg

arXiv:2508.04457v2 Announce Type: replace-cross Abstract: Reliable uncertainty quantification is crucial for trustworthy decision-making and the deployment of AI models in medical imaging. While prior

@bentannyhill @Zach_Kamran Langsmith Engine is the 'Full Self-Driving' moment for AI Engineering

Harrison Chase compares LangSmith Engine to Tesla's 'Full Self-Driving' moment, suggesting it represents a significant advancement in AI engineering capabilities and automation. The post indicates Lan

agentsharrison-chase--x

Clustering Guided Domain-Specific Pretrained Foundation Model Very High-Resolution Arctic Remote Sensing

arXiv:2605.30467v1 Announce Type: new Abstract: This study introduces a novel Arctic-focused remote sensing foundation model (RSFM) by combining diversity-aware regional-scale image curation with mask

Conformal C2ST: Turning weak classifiers into strong two-sample tests

arXiv:2507.17026v2 Announce Type: replace-cross Abstract: The two-sample testing problem, a fundamental task in statistics and machine learning, seeks to determine whether two sets of samples, drawn f

Tutorials

Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design

arXiv:2605.30610v1 Announce Type: new Abstract: Adapting generative foundation models, in particular diffusion and flow models, to optimize given reward functions (e.g., binding affinity) while satisf

tutorialsarxiv-cs-lg

Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion

arXiv:2605.31388v1 Announce Type: new Abstract: Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While

safetyarxiv-cs-lg

Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery

arXiv:2509.20941v2 Announce Type: replace Abstract: As surgical AI transitions from pixel-level detection to complex reasoning, Scene Graphs (SGs) offer the structured, relational representations nece

Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning

arXiv:2605.31174v1 Announce Type: new Abstract: Object detection in real-world scenarios remains challenging due to diverse image degradations and heterogeneous object distributions, which significant

Differentially Private Preference Data Synthesis for Large Language Model Alignment

arXiv:2605.30808v1 Announce Type: cross Abstract: Preference alignment is a crucial post-training step for large language models (LLMs) to ensure their outputs align with human values. However, post-t

Divergence Decoding: Inference-Time Unlearning via Auxiliary Models

arXiv:2605.31293v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently memorize sensitive training data thereby creating significant privacy and copyright risks. Addressing these risk

researcharxiv-cs-cl

Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models

arXiv:2605.30713v1 Announce Type: cross Abstract: Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their applicati