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…

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…

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…

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…

This paper compares the performance of recurrent decoders and selective state-space models (Mamba) in intracortical brain-to-text systems, and investigates the impact of output targets (phonetic vs. c…

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…

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 introduces 5WBENCH, a new benchmark for causal unlearning, and proposes MAAT, a novel three-phase framework that achieves high forgetting and high retention specifically on complex 'Why'-typ…

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.

The paper demonstrates that jointly training a single lightweight neural reranker on multiple diverse environments significantly improves action selection performance and achieves positive cross-domai…

The paper introduces ERGeoBench, a comprehensive diagnostic benchmark designed to evaluate the fine-grained capabilities of multimodal large language models (MLLMs) for embodied geo-localization acros…

The paper presents CONTACTMIMIC, a learning framework that tracks explicit part-level binary contact commands alongside keypoint trajectories for object interaction tasks.

The paper proposes 2FFS, a two-fidelity tree-search algorithm that efficiently identifies the best action in stochastic minimax trees by adaptively combining cheap, biased heuristic evaluations with e…

The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.

This paper introduces MECoBench, a multimodal embodied cooperation benchmark, and explores the benefits and limitations of collaboration in multimodal large language models through extensive experimen…

The paper introduces memorywire, a vendor-neutral JSON-Schema wire format and reference implementation designed to standardize and govern memory operations across disparate agent-memory frameworks.

The paper introduces BilliardPhys-Bench, a new benchmark that demonstrates that current multimodal LLMs struggle with complex physical reasoning and predicting object dynamics in simulated environment…

The paper introduces PortBERT, a family of RoBERTa-based language models for Portuguese, which achieves competitive performance while explicitly balancing efficiency and accuracy.