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

ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance taaft Despite decades of work, surveillance still struggles in searching and reasoning about specific tar… 2026-03-24 published
FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers taaft Vision models deployed on microcontrollers (MCUs) are quantized to integer-only arithmetic and run… 2026-09-01 published
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents taaft Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plai… 2026-09-04 published
Formal, Executable and Explainable Runtime Monitoring of Spoken Air Traffic Control Operational Procedures taaft Air traffic control procedures are executed through spoken exchanges between controllers and pilots… 2026-08-26 published
Forward-Deployed Full-Stack Engineering for Autonomous Cloud MLOps taaft Across industries, machine-learning systems support applications ranging from prediction and anomal… 2026-08-30 published
Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models? taaft Foundation models promise accurate forecasts with little or no task-specific training, but whether… 2026-08-31 published
Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks taaft Symmetry is everywhere in nature and society. Geometric deep learning builds architectures respecti… 2026-07-04 published
FoundYou: A Unified Model for Personalized Segmentation and Retrieval taaft Personalized segmentation and personalized retrieval both aim to identify the same physical object… 2026-08-30 published
FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators NVIDIA FourCastNet, short for Fourier Forecasting Neural Network, is a global data-driven weather forecast… 2022-02-22 published
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation taaft Score-based generative models (SGMs) learn a family of noise-conditional score functions correspond… 2022-10-09 published
FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models taaft Vision-language models (VLMs) are increasingly deployed in multi-turn settings where users may desc… 2026-09-03 published
Fractal dimension predicts quantum kernel collapse in angle-encoded data taaft Angle-encoded quantum kernels on tabular data collapse when the feature map is wider than the intri… 2026-08-31 published
FrameBench:A Language Understanding Benchmark Based on Frame Semantics taaft In frame semantics, sentence comprehension is assumed to proceed by relating lexical meaning to bac… 2026-09-03 published
FRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production taaft Modern video generators excel at synthesizing individual clips, but complete video production requi… 2026-08-30 published
frb100-40 After Two Decades: An Optimality Certificate and a Preregistered Search Study taaft For more than 20 years, the Model-RB benchmark frb100-40 remained an open challenge; since 2014, it… 2026-09-02 published
Free Pause Tokens taaft State--prediction separation (SPS) relieves a language model's hidden state of two competing burden… 2026-09-03 published
Frequency Switching Mechanism for Parameter-E!cient Multi-Task Learning taaft Multi-task learning (MTL) aims to enable a single model to solve multiple tasks efficiently; howeve… 2026-03-22 published
Frequency-aware forecasting for short-term typhoon gust prediction taaft Accurate gust forecasting under typhoon conditions remains challenging due to the highly non-statio… 2026-08-26 published
Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory taaft A large language model (LLM) agent that inherits a plan through shared memory can hold the latest r… 2026-09-03 published
FrOGS: Discrete Neural Sampler for Independent Alloy Configurations Across Chemical Conditions taaft Predicting the thermodynamic properties of an alloy requires sampling its configurations across man… 2026-09-01 published
From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline taaft Comparisons between GPU implementations are usually asymmetric: one side is tuned by its author, th… 2026-09-04 published
From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs taaft A key challenge in reliable LLM deployment is recognizing when uncertainty reflects irreducible var… 2026-09-03 published
From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities taaft Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to inte… 2026-08-27 published
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification taaft Large language models (LLMs) struggle to classify text into taxonomies with many semantically simil… 2026-09-01 published
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research taaft Research and news coverage of language-model deception increasingly attributes human-like mental-st… 2026-09-03 published
From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X taaft Ragebait refers to online content intentionally designed to provoke anger or outrage and thereby in… 2026-09-02 published
From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images taaft The rapid advancement of generative models has significantly worsened the problem of manipulated im… 2026-09-02 published
From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs taaft Autonomous flight in cluttered environments requires a robot to build a geometric map of its surrou… 2026-07-21 published
From Documents to Reasoning: A Validated Synthetic Data Pipeline and Semantic-Aware Fine-Tuning for Financial Numerical Reasoning taaft Financial question answering (QA) has emerged as a key benchmark for evaluating the performance of… 2026-08-28 published
From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning taaft The conventional approach to machine learning, that is, collecting data, training models, and perfo… 2026-09-02 published
From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models taaft Unified recommendation models aim to jointly model non-sequential multi-field features and sequenti… 2026-08-31 published
From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation taaft Trajectory data is getting more vital for training large language models for boosting the agentic a… 2026-08-31 published
From Fleet to Lab: Revisiting the Security and Complexity of Industrial Rowhammer Mitigation taaft This paper studies efficient and secure Rowhammer mitigation at the Memory-Controller (MC). Rowhamm… 2026-08-26 published
From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis taaft Automated root cause analysis (RCA) with large language models (LLMs) has drawn growing attention.… 2026-08-26 published
From Habits to Discovery: Deploying LLMs for Personalized Generative Recommendations at Spotify Spotify This is a Spotify paper, "From Habits to Discovery: Deploying LLMs for Personalized Generative Reco… Spotify
From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality taaft Code review helps maintain software quality before code integration, but it also imposes a substant… 2026-07-14 published