PaperPulse - AI/ML Summarization Platform

arXivNov 6, 2025

AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research

Tim Beyer, Jonas Dornbusch et al.

TLDR: AdversariaLLM is a comprehensive toolbox designed to improve the reproducibility and comparability of research on the robustness of Large Language Models (LLMs).

arXivNov 6, 2025

A Hybrid Deep Learning Model for Robust Biometric Authentication from Low-Frame-Rate PPG Signals

Arfina Rahman, Mahesh Banavar

TLDR: This study introduces a hybrid deep learning model for biometric authentication using low-frame-rate PPG signals, achieving 98% accuracy by combining spatial and temporal features.

AI Research Paper Feed

AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research

A Hybrid Deep Learning Model for Robust Biometric Authentication from Low-Frame-Rate PPG Signals

Distributional Multi-objective Black-box Optimization for Diffusion-model Inference-time Multi-Target Generation

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism

GraphCompliance: Aligning Policy and Context Graphs for LLM-Based Regulatory Compliance

Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics

LINK-KG: LLM-Driven Coreference-Resolved Knowledge Graphs for Human Smuggling Networks

AI Mathematician as a Partner in Advancing Mathematical Discovery -- A Case Study in Homogenization Theory

Data-driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems

Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments

InfoFlow: Reinforcing Search Agent Via Reward Density Optimization

Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems

Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings

WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios

Human-in-the-loop Online Rejection Sampling for Robotic Manipulation

Discovering State Equivalences in UCT Search Trees By Action Pruning

Human-AI Complementarity: A Goal for Amplified Oversight

GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?

Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing

The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration