This paper proposes AD-Mamba, a multi-stage knowledge distillation framework that improves the performance of state space models in audio classification tasks.

Introduces U$^2$Mamba, a U-structured network for salient object detection with improved local feature extraction and contextual information.

This study systematically evaluates Vision Mamba models for detecting AI-generated images, finding that while they show promise, their current strengths and limitations must be understood relative to…

Zamba2-VL is a new suite of vision-language models built on the Zamba2 hybrid architecture, achieving state-of-the-art performance and significantly improved inference efficiency compared to leading T…

The paper demonstrates that in Mamba-2, single-bucket probes can detect a large functional signature (detection layer) that is not fully responsible for the actual computation (execution layer), chall…

This paper presents MAMO, a multi-agent reinforcement learning approach to tackle the problem of balancing cost minimization and constraint satisfaction in dynamic environments.

The paper proposes PC-MambaSDE, a physically-constrained continuous-time framework that accurately predicts Remaining Useful Life (RUL) despite irregular sensor observations and ensures physically pla…

This paper tests the assumption that small open-weight language models fail at agentic database work by running them on a production system.

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

The paper presents a framework for model selection and parameter estimation using large language models and neural simulation-based inference.

The paper introduces RSPM, a memory management technique for agents that improves performance by pruning and forgetting unnecessary information.

MambaNetBurst introduces a compact, tokenizer-free byte-level classifier using a Mamba-2 backbone to achieve strong network traffic classification without requiring pre-training or complex data prepro…

EnergyMamba proposes an uncertainty-aware, graph-enhanced selective state space model to significantly improve both the accuracy and reliability of energy consumption prediction by explicitly modeling…

The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto l…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.

This paper introduces FurnitureVLA, a systematic study of real-scale bimanual furniture assembly using Vision-Language-Action models, improving simulation success from 48% to 80% and reducing errors.