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

Resolution-Aware Experimental Design under Partial Identifiability taaft Experimental design is commonly framed as choosing the experiment expected to provide the most info… 2026-09-03 published
Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignment taaft Multimodal regression suffers from the mean-collapse pathology: under squared loss, an unconstraine… 2026-08-26 published
Responsible Integration of AI in Cancer Genomics: Barriers, Risks, and Pathways to Trustworthy Clinical Translation taaft Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract… 2026-08-31 published
REST: Receding Horizon Explorative Steiner Tree for Zero-Shot Object-Goal Navigation taaft Zero-shot object-goal navigation (ZSON) requires navigating unknown environments to find a target o… 2026-03-19 published
RestoreBench: Can AI Agents Restore Power Flow Convergence? taaft Large Language Model (LLM) agents increasingly automate multi-step engineering workflows through to… 2026-08-31 published
Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation taaft Global welfare often depends on the correct interpretation of aerial and satellite imagery. Acting… 2026-09-01 published
Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations taaft 3D scene representations like NeRF and 3D Gaussian Splatting (3DGS) suffer severe artifacts in spar… 2026-09-03 published
Rethinking On-Policy Distillation of Large Language Models II: One Training Example taaft On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision… 2026-09-03 published
Rethinking Personalized Ranking at Pinterest: An End-to-End Approach Pinterest In this work, we present our journey to revolutionize the personalized recommendation engine throug… 2022-09-18 published
Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection taaft Real-world deployment of traffic surveillance systems is bottlenecked by geographic domain shift, i… 2026-08-25 published
Rethinking SAR ATR: A Target-Aware Frequency-Spatial Enhancement Framework with Noise-Resilient Knowledge Guidance taaft Synthetic aperture radar automatic target recognition (SAR ATR) is severely challenged by coherent… 2026-03-23 published
Rethinking the Teacher-Student Framework for Test-Time Adaptation taaft Test-Time Adaptation (TTA) has recently emerged as a promising strategy that allows the adaptation… 2026-09-02 published
Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration taaft Test-time prompt tuning (TPT) has emerged as a powerful paradigm, refining prompts for each test sa… 2026-08-31 published
Retinal OCTA Phenotyping with LLM Reporting for Alzheimer's Disease taaft Early identification of Alzheimer's disease (AD) remains challenging because established assessment… 2026-09-04 published
ReToolSQL: Agentic Reinforcement Learning for Robust Text-to-SQL taaft Recent work has shown that reinforcement learning from execution feedback can substantially improve… 2026-08-28 published
ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding taaft Speculative decoding accelerates autoregressive language model inference by having a lightweight dr… 2026-08-30 published
Retrieval Augmented Generation for Domain-specific Question Answering Adobe Question answering (QA) has become an important application in the advanced development of large la… 2024-04-23 published
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information taaft Vision-language models (VLMs) can locate an image region referred to by a text prompt and route the… 2026-08-27 published
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA taaft Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy docume… 2026-03-25 published
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks taaft Large pre-trained language models have been shown to store factual knowledge in their parameters, a… 2020-05-22 published
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation taaft Large language models (LLMs) are increasingly used as rerankers in conversational recommender syste… 2026-08-31 published
RetrievalFormer: A Dual-Encoder Transformer for Efficient Approximate Nearest Neighbor Retrieval and Cold-Item Recommendation taaft A shared search-and-recommendation index must score new items from features alone because search ha… 2026-08-25 published
RetrievalRouter: Joint Modality and Architecture Selection for Document Retrieval taaft Document retrieval increasingly supports high-stakes information access in finance, healthcare, and… 2026-08-26 published
Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories taaft We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retriev… 2026-09-01 published
Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing taaft Augmenting the surface of 3D objects with capacitive sensing is challenging when their volumes cann… 2026-07-18 published
Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics taaft With the rapid proliferation of generative models on Machine Learning as a Service (MLaaS) platform… 2026-09-02 published
Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning taaft Autoregressive rollout generation is a major computational cost in reinforcement learning for large… 2026-08-02 published
Revealing the influence of participant failures on model quality in cross-silo Federated Learning taaft Federated Learning (FL) is a paradigm for training machine learning (ML) models in collaborative se… 2026-03-26 published
Revenge of Monosemanticity: Specialized Neurons Improve Data Efficiency in MLPs taaft Understanding how neural networks learn and organize features is central to understanding their beh… 2026-08-25 published
ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction taaft Vision Language Models (VLMs) have shown great success in general visual tasks, yet they still stru… 2026-08-27 published
Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison taaft Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co… 2026-09-01 published
Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction taaft Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene… 2026-08-27 published
Revisiting Quantum Code Generation: Where Should Domain Knowledge Live? taaft Recent advances in large language models (LLMs) have enabled the automation of an increasing number… 2026-03-23 published
Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable Reasoning taaft Neural tree search is a powerful decision-making algorithm widely used in complex domains such as g… 2026-03-22 published
ReWOO: Decoupling Reasoning from Observation for Efficient LLM Reasoning Microsoft Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) w… 2023-05-23 published
RGB-to-IR image translation for infrared vehicle detection in unseen UAV domains taaft Synthetic training data is crucial for developing vision AI when real-world data is scarce, as in t… 2026-09-02 published