Search: “applications”

An `Inverse' Experimental Framework to Estimate Market Efficiency

arXiv:2604.18130v1 Announce Type: new Abstract: Digital marketplaces processing billions of dollars annually represent critical infrastructure in sociotechnical ecosystems, yet their performance optim

safetyarxiv-cs-lg

Aspect Ratios & Resolution in ChatGPT Images 2.0, demonstrated by @dibyayB

DGX agent

ChatGPT Images 2.0 supports multiple aspect ratios and resolutions for image generation, allowing users greater flexibility in creating images tailored to different use cases and display formats. The

model-releasesopenai--x

21 Apr 2026

Auditing Support Strategies in LLMs through Grounded Multi-Turn Social Simulation

arXiv:2604.17079v1 Announce Type: new Abstract: When users seek social support from chatbots, they disclose their situation gradually, yet most evaluations of supportive LLMs rely on single-turn, full

Local Ai

Automated Road Crack Localization to Guide Highway Maintenance

arXiv:2601.16737v2 Announce Type: replace Abstract: Highway networks are crucial for economic prosperity. Climate change-induced temperature fluctuations are exacerbating stress on road pavements, res

local-aiarxiv-cs-cv

Autonomous Unmanned Aircraft Systems for Enhanced Search and Rescue of Drowning Swimmers: Image-Based Localization and Mission Simulation

arXiv:2604.18088v1 Announce Type: new Abstract: Drowning is an omnipresent risk associated with any activity on or in the water, and rescuing a drowning person is particularly challenging because of t

agentsarxiv-cs-cv

Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation

model-releasesarxiv-cs-lg

arXiv:2604.16615v1 Announce Type: new Abstract: We introduce CoCo-LoRA, a multimodal, uncertainty-aware parameter-efficient fine-tuning method for text prediction tasks accompanied by audio context. E

Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text

arXiv:2604.17108v1 Announce Type: new Abstract: Coreference Resolution (CR) is a fundamental NLP task critical for long-form tasks as information extraction, summarization, and many business applicati

Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative Computation

arXiv:2604.17221v1 Announce Type: cross Abstract: Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capa

Tutorials

Block-encodings as programming abstractions: The Eclipse Qrisp BlockEncoding Interface

arXiv:2604.18276v1 Announce Type: cross Abstract: Block-encoding is a foundational technique in modern quantum algorithms, enabling the implementation of non-unitary operations by embedding them into

tutorialsarxiv-cs-lg

BOIL: Learning Environment Personalized Information

arXiv:2604.17137v1 Announce Type: new Abstract: Navigating complex environments poses challenges for multi-agent systems, requiring efficient extraction of insights from limited information. In this p

agentsarxiv-cs-lg

BOP-ASK: Object-Interaction Reasoning for Vision-Language Models

model-releasesarxiv-cs-cv

arXiv:2511.16857v3 Announce Type: replace Abstract: Vision Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses i

Bridging Coarse and Fine Recognition: A Hybrid Approach for Open-Ended Multi-Granularity Object Recognition in Interactive Educational Games

arXiv:2604.16785v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have enabled open-ended object recognition, yet they struggle with fine-grained tasks. In co

Calibrating Model-Based Evaluation Metrics for Summarization

arXiv:2604.17200v1 Announce Type: new Abstract: Recent advances in summary evaluation are based on model-based metrics to assess quality dimensions, such as completeness, conciseness, and faithfulness

CAPO: Counterfactual Credit Assignment in Sequential Cooperative Teams

arXiv:2604.17693v1 Announce Type: new Abstract: In cooperative teams where agents act in a fixed order and share a single team reward, it is hard to know how much each agent contributed, and harder st

safetyarxiv-cs-lg

Local Ai

Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection

arXiv:2604.17998v1 Announce Type: new Abstract: Anomaly detection in multivariate time series is a central challenge in industrial monitoring, as failures frequently arise from complex temporal dynami

local-aiarxiv-cs-lg

CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation

arXiv:2505.20779v5 Announce Type: replace Abstract: A hallmark of human innovation is recombination -- the creation of novel ideas by integrating elements from existing concepts and mechanisms. In thi

CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora

arXiv:2604.18027v1 Announce Type: cross Abstract: Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream ap

Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation

arXiv:2604.17178v1 Announce Type: new Abstract: Emotional Support Conversation (ESC) plays a critical role in mental health assistance by providing accessible psychological support in real-world appli

safetyarxiv-cs-cl

ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented Companionship

arXiv:2604.18356v1 Announce Type: new Abstract: Developing compassionate interactive systems requires agents to not only understand user emotions but also provide diverse, substantive support. While r

Hardware

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

arXiv:2412.00069v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) has garnered significant attention for its ability to scale up neural networks while utilizing the same or even fewer

hardwarearxiv-cs-cl

Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks

arXiv:2604.17761v1 Announce Type: cross Abstract: Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or t

CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit

arXiv:2510.06133v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms

CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks

arXiv:2505.11314v2 Announce Type: replace-cross Abstract: The assessment of evaluation metrics (meta-evaluation) is crucial for determining the suitability of existing metrics in text-to-image (T2I) g

Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM

arXiv:2604.16368v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by using a small draft model to propose k candidate tokens for a target model to verify. While effective

Industry

Democrats in Virginia today are voting to strip democracy from the process, eliminating Republican voices from congress They are fascists an…

Democrats in Virginia today are voting to strip democracy from the process, eliminating Republican voices from congress They are fascists and unrepentant The actions of Texas or any other state are im

industryelon-musk--x

Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network

arXiv:2510.01801v2 Announce Type: replace Abstract: The rise of large language models (LLMs) has enabled the generation of highly persuasive spam reviews that closely mimic human writing. These review

Distributional Off-Policy Evaluation with Deep Quantile Process Regression

arXiv:2604.18143v1 Announce Type: cross Abstract: This paper investigates the off-policy evaluation (OPE) problem from a distributional perspective. Rather than focusing solely on the expectation of t

safetyarxiv-cs-lg

Dual-End Consistency Model

arXiv:2602.10764v2 Announce Type: replace Abstract: The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While cons

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models

arXiv:2604.16481v1 Announce Type: new Abstract: Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable

safetyarxiv-cs-cv

Every docs team I've been on ends up punting on the same project: making code samples in docs testable in CI. We know it's important but the…

Every docs team I've been on ends up punting on the same project: making code samples in docs testable in CI. We know it's important but the implementation cost is too great. Skills + deep agents fina

agentsharrison-chase--x

FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation

arXiv:2604.17149v1 Announce Type: cross Abstract: Accurate autoregressive prediction of 3D turbulent flows remains challenging for neural PDE solvers, as small errors in fine-scale structures can accu

fun off-the-cuff harness + agent engineering sesh with @dexhorthy @vaibcode @GeoffreyHuntley - a lot of good harness/agent design we’re doin…

fun off-the-cuff harness + agent engineering sesh with @dexhorthy @vaibcode @GeoffreyHuntley - a lot of good harness/agent design we’re doing today is still good context engineering, remember tool cal

agentsharrison-chase--x

GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting

arXiv:2604.18047v1 Announce Type: new Abstract: Continuous Spatio-Temporal Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial resolution and frame rate of videos by arbitrary

safetyarxiv-cs-cv

HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval

arXiv:2604.18037v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) is a flexible image retrieval paradigm that enables users to accurately locate the target image through a multimodal quer

How Much Data is Enough? The Zeta Law of Discoverability in Biomedical Data, featuring the enigmatic Riemann zeta function

arXiv:2604.17581v1 Announce Type: new Abstract: How much data is enough to make a scientific discovery? As biomedical datasets scale to millions of samples and AI models grow in capacity, progress inc

Tutorials

How to Approximate Inference with Subtractive Mixture Models

arXiv:2604.16714v1 Announce Type: new Abstract: Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance

tutorialsarxiv-cs-lg

How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas

This article explains how to ground Korean AI agents in realistic demographic data by utilizing synthetic personas, likely leveraging NVIDIA's Nemotron models available on Hugging Face. The approach e

agentshugging-face

Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context

arXiv:2506.10779v2 Announce Type: replace Abstract: Classroom speech and lectures often contain named entities (NEs) such as names of people and special terminology. While automatic speech recognition

Inertia in Moral and Value Judgments of Large Language Models

arXiv:2408.09049v3 Announce Type: replace Abstract: Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy i

safetyarxiv-cs-cl

Inference-Time Temporal Probability Smoothing for Stable Video Segmentation with SAM2 under Weak Prompts

arXiv:2604.17115v1 Announce Type: new Abstract: Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user super

InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

model-releasesarxiv-cs-cv

arXiv:2509.10813v3 Announce Type: replace Abstract: The advancement of Embodied AI heavily relies on large-scale, simulatable 3D scene datasets characterized by scene diversity and realistic layouts.

Is Agentic RAG worth it? An experimental comparison of RAG approaches

arXiv:2601.07711v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems are usually defined by the combination of a generator and a retrieval component that extracts textual c

agentsarxiv-cs-cl

J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively in Inverse Kinematic Control of Serial Manipulators

arXiv:2505.00306v5 Announce Type: replace Abstract: J-PARSE is an algorithm for smooth first-order inverse kinematic control of a serial manipulator near kinematic singularities. The commanded end-eff

safetyarxiv-cs-ro

KaLDeX: Kalman Filter based Linear Deformable Cross Attention for Retina Vessel Segmentation

arXiv:2410.21160v2 Announce Type: replace-cross Abstract: Background and Objective: In the realm of ophthalmic imaging, accurate vascular segmentation is paramount for diagnosing and managing various

Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact

model-releasesarxiv-cs-lg

arXiv:2603.00883v2 Announce Type: replace Abstract: LLMs increasingly excel on AI benchmarks, but doing so does not guarantee validity for downstream tasks. This study contrasts LLM alignment on bench

🏆LangChain was just named 2026 @googlecloud Partner of the Year Award in the Marketplace: Agent Platform category. ☁️ @gcloudpartners #Goog…

LangChain received Google Cloud's 2026 Partner of the Year Award in the Marketplace: Agent Platform category, recognizing its contributions to the cloud ecosystem. The award highlights LangChain's pro

agentsharrison-chase--x

Learning the Riccati solution operator for time-varying LQR via Deep Operator Networks

arXiv:2604.18507v1 Announce Type: cross Abstract: We propose a computational framework for replacing the repeated numerical solution of differential Riccati equations in finite-horizon Linear Quadrati

Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection

arXiv:2506.00955v2 Announce Type: replace Abstract: Sarcasm fundamentally alters meaning through tone and context, yet detecting it in speech remains a challenge due to data scarcity. In addition, exi