Creates the BGTD benchmark and mmTraffic architecture to enable explainable multimodal interpretation of encrypted network traffic using LLMs.
Mamba: Linear-time sequence modeling with selective state spaces
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
ECO combines a Mamba encoder-decoder with two-stage batched DPO and LS-aware preference construction, claiming the best reported neural performance and near-linear memory scaling on TSP up to 5000 nodes and CVRP up to 1000 nodes.
FG²-GDN replaces the scalar beta in the delta update with a channel-wise vector and decouples key/value scaling to improve recall over prior GDN and KDA models.
MedMamba introduces a principle-guided bidirectional multi-scale Mamba model that outperforms prior methods on EEG, ECG, and activity classification benchmarks while delivering 4.6x inference speedup.
FMMVCC combines Mamba-based encoders with multi-view contrastive learning and fuzzy clustering to achieve state-of-the-art univariate time series clustering with linear computational complexity.
ADM-Fusion proposes an end-to-end adaptive multi-sensor fusion network using mixture-of-experts routing and cross-task attention for robust ego-motion estimation, trained on simulation then fine-tuned on real data.
StableHLO serves as a viable unified representation for cross-architecture performance modeling of distributed ML workloads, preserving relative trends while exposing fidelity trade-offs.
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
citing papers explorer
-
Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A Benchmark
Creates the BGTD benchmark and mmTraffic architecture to enable explainable multimodal interpretation of encrypted network traffic using LLMs.
-
Rethinking Efficiency in Neural Combinatorial Optimization: Batched Preference Optimization with Mamba
ECO combines a Mamba encoder-decoder with two-stage batched DPO and LS-aware preference construction, claiming the best reported neural performance and near-linear memory scaling on TSP up to 5000 nodes and CVRP up to 1000 nodes.
-
FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control
FG²-GDN replaces the scalar beta in the delta update with a channel-wise vector and decouples key/value scaling to improve recall over prior GDN and KDA models.
-
MedMamba: Recasting Mamba for Medical Time Series Classification
MedMamba introduces a principle-guided bidirectional multi-scale Mamba model that outperforms prior methods on EEG, ECG, and activity classification benchmarks while delivering 4.6x inference speedup.
-
FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Series
FMMVCC combines Mamba-based encoders with multi-view contrastive learning and fuzzy clustering to achieve state-of-the-art univariate time series clustering with linear computational complexity.
-
ADM-Fusion: Adaptive Deep Multi-Sensor Fusion for Robust Ego-Motion Estimation in Diverse Conditions
ADM-Fusion proposes an end-to-end adaptive multi-sensor fusion network using mixture-of-experts routing and cross-task attention for robust ego-motion estimation, trained on simulation then fine-tuned on real data.
-
Evaluating Cross-Architecture Performance Modeling of Distributed ML Workloads Using StableHLO
StableHLO serves as a viable unified representation for cross-architecture performance modeling of distributed ML workloads, preserving relative trends while exposing fidelity trade-offs.
-
From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.