Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced

Cross-Domain Tracker Adaptation Without Target-Domain Labels via Vision-Language Agents taaft We present a system that uses a Vision-Language Model (VLM) as a diagnostic agent for adapting a de… 2026-09-04 published
Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations? taaft Cross-lingual alignment in multilingual language models is typically attributed to joint training:… 2026-08-27 published
Cross-lingual Functional Vectors for Emotion Detection in Large Language Models taaft Function vectors (FVs) have recently emerged as a promising mechanism for steering the behavior of… 2026-08-30 published
Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition taaft As large language models are increasingly deployed across diverse real-world applications, extendin… 2026-03-19 published
Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation taaft Spontaneous movement is one of the earliest windows onto an infant's neuromotor health, and structu… 2026-09-01 published
Cross-Spectral Dense Correspondence for Multimodal Spectral Medical Imaging taaft Precise dense correspondence is a fundamental prerequisite for multimodal spectral imaging systems… 2026-08-28 published
CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth Estimation taaft Reliable 3D understanding of the surrounding environment is a core requirement for autonomous drivi… 2026-09-04 published
CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents taaft Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly… 2026-09-04 published
CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning taaft Multimodal language models achieve near-ceiling scores on food recognition benchmarks, yet it remai… 2026-09-03 published
CURA: Certified Runtime Alarms for Computer-Use Agents taaft Self-report is the cheapest oversight channel a deployer has, and on capable computer-use agents (C… 2026-08-28 published
Curvature-aware Expected Free Energy as an Acquisition Function for Bayesian Optimization taaft We propose an Expected Free Energy-based acquisition function for Bayesian optimization to solve th… 2026-03-27 published
Curved Inference II: Sleeper Agent Geometry - Extending Interpretability Beyond Probes taaft This paper extends Anthropic's Sleeper Agents research [1], which showed artificial backdoors persi… 2026-08-25 published
CVPD at QIAS 2026: RAG-Guided LLM Reasoning for Al-Mawarith Share Computation and Heir Allocation taaft Islamic inheritance (Ilm al-Mawarith) is a multi-stage legal reasoning task requiring the identific… 2026-03-25 published
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models taaft Continual Pre-Training (CPT) on Large Language Models (LLMs) has been widely used to expand the mod… 2024-06-03 published
D-FROST: Decentralized Federated pRompt-tuning via Optimal tranSporT for Non-IID and Imbalanced Data taaft Prompt tuning provides a parameter-efficient way to adapt foundation models (FMs) by freezing the p… 2026-09-01 published
D-TAIA: Domain-Aware LLM Adaptation for Multi-Task Predictive Process Monitoring taaft Predictive Process Monitoring (PPM) enables organizations to forecast future process behavior, such… 2026-08-28 published
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features Microsoft In this work we address the problem of finding reliable pixel-level correspondences under difficult… 2019-05-09 published
D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection taaft AI-generated text detection is commonly framed as a binary document-level judgment about whether a… 2026-08-27 published
DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection taaft Domain Adaptive Object Detection (DAOD) aims to transfer detectors from a labeled source domain to… 2026-03-19 published
DAMO-YOLO : A Report on Real-Time Object Detection Design Alibaba In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achi… 2022-11-23 published
DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge IBM Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail… 2026-03-18 published
DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models taaft Vision foundation models (VFMs) are valuable in data-scarce domains such as surgery, where a single… 2026-09-03 published
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories taaft Data tells stories that shape society; the data journalist's job is to turn raw information into st… 2026-06-09 published
Data Leakage Inflates Generalizability of Power Outage Prediction Models taaft Power outage prediction models are increasingly used in assessments of climate-driven infrastructur… 2026-08-25 published
Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance taaft Pretraining data of large language models composes multiple domains (e.g., web texts, academic pape… 2024-03-25 published
Data Pruning via Moving-one-Sample-out taaft In this paper, we propose a novel data-pruning approach called moving-one-sample-out (MoSo), which… 2023-10-23 published
Data Selection for Language Models via Importance Resampling taaft Selecting a suitable pretraining dataset is crucial for both general-domain (e.g., GPT-3) and domai… 2023-02-06 published
Data-Driven Design Optimization of Streaming-Potential-Mediated Electrokinetic Transport of Viscoelastic Fluids in Microchannels taaft Streaming-potential-mediated transport of viscoelastic fluids has attracted research attention owin… 2026-08-30 published
Data-driven Koopman mode approximation: A neural power iteration algorithm taaft This paper proposes a novel data-driven algorithm to approximate the dominant eigenfunctions (aka.~… 2026-08-27 published
Data-Driven Persona-Conditioned Agents for A/B Test Simulation taaft A/B testing is the gold standard for evaluating product changes, but each experiment requires real… 2026-09-01 published
Data-efficient crack quantification in lithium-ion cathodes using foundation model transfer taaft Battery lifetime is central to sustainable electrification, yet the particle cracking that drives l… 2026-08-27 published
Data-efficient Fine-tuning for LLM-based Recommendation taaft Leveraging Large Language Models (LLMs) for recommendation has recently garnered considerable atten… 2024-01-30 published
Data-Efficient Networks for Multi-Contrast MRI Reconstruction based on a Generalized Content/Style Prior taaft Multi-contrast MR scans contain redundant structural information that can be leveraged during recon… 2026-09-02 published
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language Meta Platforms While the general idea of self-supervised learning is identical across modalities, the actual algor… 2022-02-07 published
DataComp: In search of the next generation of multimodal datasets taaft Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and G… 2023-04-27 published
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum taaft Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequ… 2024-05-21 published