127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

94,811 results

Research

Reference-Guided Machine Unlearning

DGX agent

arXiv:2603.11210v2 Announce Type: replace Abstract: Machine unlearning aims to remove the influence of specific training data from a model while preserving its general utility. In vision, many approxi

researcharxiv-cs-lg

30 Sept 2026

Safety

Regime Boundary Alignment for Evidence-Gated Question Answering

DGX agent

arXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence i

All entries

Reference-Guided Machine Unlearning

Regime Boundary Alignment for Evidence-Gated Question Answering

Reimagine Video Dynamics

RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution

Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG

Reliability Testing of Medical Model Performance under Distributed Deployment

Reliable but Design-Sensitive: Instrument Uncertainty in LLM Annotation

Reliable Parallel Decoding in Masked Diffusion Language Models

Relic: From Multi-Agent Collaboration to Persistent Organizational Capability

ReLMem: Learning Recurrent Memory for Longitudinal EHR Modeling

ReLOBGen: Replayable Limit Order Book Message Generation

ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents

Remember What You Did: Action-History Memory with Dual-Expert Denoising for Long-Horizon Vision-Language-Action Policies

Render Before Reading: Visual Rendering as a Prompt Injection Defense

Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech

Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference

Replication Failure and Trivial Baselines in Road-Level Crash Prediction

RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems

Representable but Unlearned: Encoding Rank and the Interaction-Prediction Floor

Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers

Representation Dynamics Reveal Semantic Saliency and Similarity for Visual Token Pruning in MLLMs

Representational and Functional Robustness to Electrode Montages in EEG Foundation Models

Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training

Reprogramming Vision-Language Models via Structured Prompt Reparameterization

ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression

RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning

Resolving the Missing Financial Data Crisis: A Generative AI Pipeline for SEC 10-K Extraction

Rethinking Multimodal Fake News Detection in the Generative AI Era

Rethinking Reasoning Paths as Phase-Structured Trajectories

Rethinking Representations for World-Action Modeling

Rethinking Soft Tokens for Parallel Decoding in Diffusion Language Models

Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation

Retrieval Capacity of Self-Attention Under Competition

Retrieval Sensitivity to Identity Signals in Queries

Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection

Reverberation: Learning the Latencies Before Forecasting Trajectories

REVO: Rollout-Efficient Off-Policy Distillation via Variance-Guided Reuse

Reward-rate Policy Gradient for Efficient Machine Learning Engineering Agents

ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking

Rho: A Foundation for Efficiently Adaptable VLA Models

Riemannian Splat Regression Models for Learning Time Fields on Arbitrary Riemannian Manifolds

Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT

Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees

Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning

Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks

RL-PaO: Prediction as Action in Decision Making under Uncertainty

RLTL;DR: Self-improvement by Internalizing Self-generated Feedback

RLX: A Unified Multi-Backend Tensor Compiler and Distributed Runtime in Rust