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

Extremely Sparse Supervision Incentivizes Reasoning Ability taaft Large language models demonstrate increasingly strong reasoning capabilities through effective post… 2026-09-03 published
Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study taaft To address this gap, we conduct a Virtual Reality experiment in which pedestrians interact with aut… 2026-03-20 published
Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation taaft Real-world robotic assembly at sub-millimeter tolerances demands spatial precision, compliant inter… 2026-09-01 published
Factors Influencing the Quality of AI-Generated Code: A Synthesis of Empirical Evidence taaft Context: The rapid adoption of AI-assisted code generation tools, such as large language models (LL… 2026-03-26 published
Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory taaft Large language models increasingly serve as persistent knowledge workers, with in-context memory -… 2026-03-18 published
FailBench: How Reliable are VLMs at Judging Robot Task Success? taaft Vision-Language Models (VLMs) are increasingly used to evaluate robot manipulation outcomes, but ex… 2026-09-03 published
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories taaft Large language model (LLM) coding agents are increasingly deployed to autonomously perform software… 2026-07-10 published
FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication taaft Recent dataset deduplication techniques have demonstrated that content-aware dataset pruning can dr… 2024-04-24 published
FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making taaft Vision-language models (VLMs) are increasingly used to make decisions from visual inputs. We introd… 2026-09-01 published
Fairness in multi-class multi-group classification problems via contextial coherent risk measures taaft We propose a new design of fair classifiers for multi-class classification problems in the presence… 2026-08-31 published
Fast Gauss Sums via Flash Attention taaft Gaussian kernel sums are the computational core of maximum mean discrepancies (MMDs), kernel gradie… 2026-09-04 published
Fast Inference from Transformers via Speculative Decoding Google Research Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K se… 2022-11-30 published
Fast rates in Bayesian online learning with approximate posteriors taaft Exact Bayes prediction enjoys fast predictive regret guarantees, but exact posterior updating or re… 2026-08-26 published
Fast Surrogate Modeling of Excitable and Oscillatory FitzHugh-Nagumo Dynamics with Parametric Neural Operators taaft The FitzHugh-Nagumo (FHN) system serves as a simplified model of neuronal voltage dynamics, capturi… 2026-09-03 published
Fast Weight Attention for Continual Learning taaft Recurrent fast-weight memories and selective state-space models compress an expanding context into… 2026-08-27 published
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Microsoft State-of-the-art object detection networks depend on region proposal algorithms to hypothesize obje… 2015-06-04 published
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding taaft The development of long-context Large Language Models (LLMs) is constrained by the memory bandwidth… 2026-08-31 published
FaVOR: LLM-Based Agentic Framework for Factor Mining via Empirical Validation taaft Traditional finance relies on experts to hand-craft factors through a principled process grounded i… 2026-08-31 published
FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning taaft Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guid… 2026-03-24 published
Feasible but Not Safe: Constraint Violations and Report-Channel Attacks in Learned Cell-Free ISAC Association taaft Learning-based schedulers have been proposed to provide real-time user, target, and access point (A… 2026-09-02 published
Feature Encoding in Quantum Machine Learning: A Survey and Practical Guidelines taaft The encoding of classical data into quantum states constitutes the primary performance bottleneck i… 2026-06-03 published
Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation taaft Lesion segmentation in medical images plays a critical role in clinical diagnosis and treatment pla… 2026-09-03 published
Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection taaft In recent years, graph anomaly detection (GAD) based on frequency-domain filtering have achieved pr… 2026-08-27 published
FedDRAW: Federated Dual Reputation Annealing Weighting for Heterogeneous Multi-Institutional Chest Radiograph Classification taaft Artificial intelligence models are promising for medical diagnosis, but they require large numbers… 2026-09-04 published
FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling taaft Recent advances in large language models are enabling autonomous clinical agents to perform increas… 2026-08-28 published
Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates taaft Detecting orchestrated cyberattack campaigns that span multiple organizations traditionally require… 2026-09-04 published
Federated Causal Discovery via Regression-Directed Cumulants taaft In this paper we study linear non-Gaussian acyclic models (LiNGAM) when used in federated environme… 2026-09-03 published
Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications Apple We describe the design of our federated task processing system. Originally, the system was created… 2021-02-16 published
Federated LoRA Adaptation of BiomedCLIP Across Four International Chest X-Ray Cohorts taaft Federated learning (FL) lets institutions train a shared model without exchanging data, and Low-Ran… 2026-09-02 published
FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access Selection taaft Reliable access selection in dynamic and heterogeneous indoor-outdoor environments is challenging b… 2026-08-26 published
FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs taaft Real-world data for knowledge graph question answering is often distributed across different organi… 2026-08-25 published
Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation taaft Multi-view human reconstruction has been extensively studied under simplified settings, yet robust… 2026-09-01 published
Fermionic Neural Network with Effective Core Potential taaft Deep learning techniques have opened a new venue for electronic structure theory in recent years. I… 2021-08-26 published
Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning taaft We consider the task of building a dialogue system that can motivate users to adopt positive lifest… 2024-03-23 published
Few-Shot Generative Model Adaption via Identity Injection and Preservation taaft Training generative models with limited data presents severe challenges of mode collapse. A common… 2026-03-24 published
Few-Shot Video Recognition via Hierarchical Metric Learning taaft Few-shot action recognition (FSAR) aims to recognize unseen action categories with only a small num… 2026-09-04 published