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

Poisoning Attacks on the PGM-index taaft The PGM-index (Ferragina and Vinciguerra, VLDB'20) is one of the most practical learned indexes, ow… 2026-09-02 published
PolERo: Studying Political Evasion in Romanian taaft Political evasion refers to responses that engage with a question while withholding the requested i… 2026-09-02 published
Politics of Questions in News: A Mixed-Methods Study of Interrogative Stances as Markers of Voice and Power taaft Interrogatives in news discourse have been examined in linguistics and conversation analysis, but m… 2026-03-23 published
PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning taaft Long Narrative Reasoning is an essential capability for processing and reasoning over complex narra… 2026-08-26 published
Pooling and Drift in Delayed Bandits taaft A system often has to act long before it learns whether the act worked: a recommender sees a click… 2026-09-01 published
Position: Synthetic Persona Needs Explicit Grounding and Standardized Reporting MatrAIx Argues vivid synthetic personas often outstrip actual representativeness. Categorizes construction… MatrAIx
Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning taaft This position paper argues that the absence of labels does not imply the absence of human supervisi… 2026-09-02 published
Post-Edit Re-Verification in Simulator-Backed Engineering Agents: A Controlled Comparison of Verification-Cadence Guidance taaft Engineering agents that interact with external simulators may need to coordinate design modificatio… 2026-08-28 published
Post-Training Language Models for Gold-Medal Performance in Coding Competitions taaft Competitive programming has become a key test of large language model reasoning, with international… 2026-09-02 published
Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment taaft Ultra-low-bit language models can reduce storage and memory bandwidth, but a nominal "1.58-bit" lab… 2026-09-02 published
Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling taaft We study a variant of the Thompson Sampling (TS) algorithm, called $α$-TS, for solving stochastic g… 2026-09-02 published
PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation taaft We present PosterIQ, a design-driven benchmark for poster understanding and generation, annotated a… 2026-03-25 published
PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing taaft With the rapid development of the Internet of Things, computation intensive directed acyclic graph… 2026-09-03 published
PQuantML: A Tool for End-to-End Hardware-aware Model Compression taaft PQuantML is a new open-source, hardware-aware neural network model compression library tailored to… 2026-03-27 published
PRACTICE: From Experience to Expertise in Self-Evolving Embodied Agents taaft Recent studies have shown that multimodal large language models (MLLMs) can serve as embodied agent… 2026-08-31 published
PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation taaft Synthetic dialogue generation can support research in privacy-restricted service settings, but gene… 2026-09-02 published
Praxist: From Experimental Artifacts to Solution Lineages taaft Autonomous R\&D agents now write, run, and improve executable artifacts under automated evaluation-… 2026-08-26 published
Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models taaft Diffusion language models (DLMs) have emerged as a promising alternative to the auto-regressive par… 2026-09-02 published
Predicting Program Exit Code with LLMs and Programming Language Semantics taaft Large language models (LLMs) have shown proficiency in various software engineering tasks, such as… 2026-09-01 published
Predicting Radiologist Expertise from 3D Gaze Patterns During CT Interpretation taaft Accurate interpretation of volumetric CT requires efficient navigation of 3D image volumes and atte… 2026-08-24 published
Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network taaft Urban air quality can vary significantly along transit corridors, necessitating high-resolution mon… 2026-09-04 published
Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness taaft Smooth speaker transitions are fundamental to effective conversation and rely on an interlocutor's… 2026-08-28 published
Predictors of Loneliness in Older Adults Using Multimodal Analysis of Speech and Language taaft Loneliness is a critical public health issue among older adults, linked to higher risks of depressi… 2026-09-02 published
Preference Data Selection for Mitigating the Alignment Tax in Large Language Models taaft Aligning large language models to human preferences is crucial for real-world deployment but freque… 2026-08-25 published
Preference Optimization for Non-Verbal Vocalization Synthesis taaft Non-verbal vocalizations (NVs), such as laughter, coughs, and sighs, are essential for expressive T… 2026-08-25 published
PreferRec: Learning and Transferring Pareto Preferences for Multi-objective Re-ranking taaft Multi-objective re-ranking has become a critical component of modern multi-stage recommender system… 2026-03-23 published
Prefix Sliding for efficient test-time scaling taaft Test-time scaling uses extra test-time compute to improve performance, such as letting language mod… 2026-08-26 published
Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models taaft Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive… 2026-08-26 published
Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems taaft Preprocessing-based defenses are the standard first-line response to adversarial attacks on edge vi… 2026-09-03 published
Preserving Knowledge across Space and Time for Continual Video Deepfake Detection taaft The continuous emergence of high-quality video deepfakes requires detectors that continually adapt… 2026-09-03 published
Pretrained, Curriculum-Tuned, and Ensembled: A Tracer-Aware Interactive Segmentation Pipeline for AutoPET V taaft Interactive lesion segmentation in whole-body PET/CT requires a model to provide a strong initial p… 2026-08-31 published
Preventing Oversmoothing in VAE via Generalized Variance Parameterization taaft Variational autoencoders (VAEs) often suffer from posterior collapse, which is a phenomenon in whic… 2021-02-17 published
PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting taaft Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conven… 2026-09-04 published
PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert taaft Click-through rate (CTR) models vary in feature-interaction design, yet their top networks usually… 2026-08-31 published
Principia: Relational Physics Tests for Video Models taaft Evaluating physical reasoning in video models is difficult because absolute motion measurements dep… 2026-09-03 published
Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models taaft As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be eas… 2026-03-23 published