127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “benchmark”

30,250 results

Research

Parallel Recursive LSTM

DGX agent

arXiv:2605.17108v1 Announce Type: new Abstract: Transformers have become the dominant architecture for sequence modeling by using self-attention to enable expressive and highly parallel processing. Ho

researcharxiv-cs-lg

19 May 2026

Research

Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation

DGX agent

Search: “benchmark”

Parallel Recursive LSTM

Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation

Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Sign

Perception-based Image Denoising via Generative Compression

PERL: Parameter Efficient Reasoning in CLIP Latent Space

PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoning

PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting

PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics

Physics-Guided Geometric Diffusion for Macro Placement Generation

Position: Age Estimation Models Do Not Process Biometric Data

Position: AI Evaluations Should be Grounded on a Theory of Capability

Position: Universal Time Series Foundation Models Rest on a Category Error

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Predictive Prefetching for Retrieval-Augmented Generation

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders

Prefix-Adaptive Block Diffusion for Efficient Document Recognition

Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs

ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow

PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting

QLIF-CAST: Quantum Leaky-Integrate-and-Fire for Time-Series Weather Forecasting

QuChaTeR: A Hybrid Quantum-Chaotic Temporal Framework for Earthquake Prediction

QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation

Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models

Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis

Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning

RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture

Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation

Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning

RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification

RAVE: Re-Allocating Visual Attention in Large Multimodal Models

Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification

ReBaR: Reference-Based Reasoning for Robust Pose Estimation from Monocular Images

REC-RL: Referring expression counting via Gaussian and range-based reward optimization

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift

Residual Semantic Decomposition of Word Embeddings

Responsible Agentic AI Requires Explicit Provenance

Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution

Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping

RIE-Greedy: Regularization-Induced Exploration for Contextual Bandits

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening

SAM 2++: Tracking Anything at Any Granularity

SC3D: Dynamic and Differentiable Causal Discovery for Temporal and Instantaneous Graphs

Scalable Environments Drive Generalizable Agents

Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework

scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement

Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics