127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

94,811 results

Hardware

Probabilistic Programs of Thought

DGX agent

arXiv:2604.17290v1 Announce Type: new Abstract: LLMs are widely used for code generation and mathematical reasoning tasks where they are required to generate structured output. They either need to rea

hardwarearxiv-cs-cl

21 Apr 2026

Tutorials

Procedural Knowledge at Scale Improves Reasoning

DGX agent

arXiv:2604.01348v2 Announce Type: replace Abstract: Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat ea

All entries

Probabilistic Programs of Thought

Procedural Knowledge at Scale Improves Reasoning

Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards

ProfVLM: A lightweight video-language model for multi-view proficiency estimation

Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics

Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions

Projected Coupled Diffusion for Test-Time Constrained Joint Generation

Prompt Sensitivity in Vision-Language Grounding: How Small Changes in Wording Affect Object Detection

Prompting Foundation Models for Zero-Shot Ship Instance Segmentation in SAR Imagery

ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification

ProTrain: Efficient LLM Training via Memory-Aware Techniques

Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition

PTLD: Sim-to-real Privileged Tactile Latent Distillation for Dexterous Manipulation

Pulse Shape Discrimination Algorithms: Survey and Benchmark

Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability

PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming

Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement

Q-SINDy: Quantum-Kernel Sparse Identification of Nonlinear Dynamics with Provable Coefficient Debiasing

QU-NLP at QIAS 2026: Multi-Stage QLoRA Fine-Tuning for Arabic Islamic Inheritance Reasoning

QuadSync: Quadrifocal Tensor Synchronization via Tucker Decomposition

Quantifying how AI Panels improve precision

QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks

R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detection

R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation

RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction

RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts

RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation

RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention

Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario

Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning

Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus

Ranking Abuse via Strategic Pairwise Data Perturbations

RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments

Rate-Distortion Optimization for Transformer Inference

RAYEN: Imposition of Hard Convex Constraints on Neural Networks

Re^2MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement

Real-Time Cellist Postural Evaluation With On-Device Computer Vision

Real-Time Structural Detection for Indoor Navigation from 3D LiDAR Using Bird's-Eye-View Images

Real-Time Visual Attribution Streaming in Thinking Model

REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations

ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval

Reasoning Models Know What's Important, and Encode It in Their Activations

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

ReCap: Lightweight Referential Grounding for Coherent Story Visualization

Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning

ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control

ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering