SPACE framework unifies symmetric and asymmetric VRPs via bidirectional Frechet representations and weight-decomposed decoding for zero-shot generalization across 110 variants.
hub
Attention is all you need.Advances in Neural Information Processing Systems, 30
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
The What-Where Transformer achieves explicit what-where separation in a ViT-style backbone via concurrent token and attention-map streams, yielding emergent object discovery from attention maps and better weakly-supervised localization.
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
A dual-branch contrastive learning framework distills street-view semantics and temporal context into satellite representations, improving monthly carbon emission prediction using only satellite imagery at inference.
The paper derives a characterization of minimax risk for KV cache compression and maps it to practical design principles and an algorithm tested on LongBench.
I²RiMA achieves up to 82.78% balanced accuracy in cross-subject EEG stress detection by mapping frequency-specific covariances to the SPD tangent space, aggregating spectral clusters, and applying intra-inter temporal attention.
The CARM module boosts neural routing solvers by adaptively modulating embeddings with constraint variables, enabling better use of global observations and improved performance on constrained VRPs.
RDKV derives per-token and per-channel weights from attention distortion, then uses reverse water-filling to assign bit-widths from full precision to zero after prefilling, recovering 97.81% accuracy with 2.48% cache retention on LongBench.
M2D distillation augments input graphs with model-derived features and structure, letting simple student GNNs match teacher performance while exposing mechanisms such as attention and fairness directly in the data.
A shared global expert pool in MoE improves validation loss over per-layer experts and allows sublinear expert-parameter growth with depth.
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
X-LogSMask injects per-head powers of the normalized adjacency matrix via a logarithmic transform into Transformer attention, achieving SOTA results on 13 of 20 graph benchmarks while remaining competitive in a one-layer setup.
Aligning the DDIM forward diffusion process with flow-matching manifold evolution enables high-quality generation without time conditioning, and class-conditional synthesis is possible with an unconditional denoiser by using separate time spaces per class.
EgoMotion decouples reasoning from motion synthesis in egocentric vision-language tasks by mapping inputs to motion primitives via VLM then using diffusion to produce grounded and coherent 3D trajectories.
Generative AI should be evaluated through computational hermeneutics using iterative, human-inclusive benchmarks that measure cultural context rather than isolated model outputs.
A novel weakly supervised anomaly detection method for brain MRI that uses discriminative dual prompt tuning for pseudo masks and region-aware spatial attention with location-based random embeddings to achieve SOTA results with under 8 million parameters on BraTS and MSD datasets.
citing papers explorer
-
SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
SPACE framework unifies symmetric and asymmetric VRPs via bidirectional Frechet representations and weight-decomposed decoding for zero-shot generalization across 110 variants.
-
What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization
The What-Where Transformer achieves explicit what-where separation in a ViT-style backbone via concurrent token and attention-map streams, yielding emergent object discovery from attention maps and better weakly-supervised localization.
-
Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
-
CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training
A dual-branch contrastive learning framework distills street-view semantics and temporal context into satellite representations, improving monthly carbon emission prediction using only satellite imagery at inference.
-
The risk of KV cache compression
The paper derives a characterization of minimax risk for KV cache compression and maps it to practical design principles and an algorithm tested on LongBench.
-
I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals
I²RiMA achieves up to 82.78% balanced accuracy in cross-subject EEG stress detection by mapping frequency-specific covariances to the SPD tangent space, aggregating spectral clusters, and applying intra-inter temporal attention.
-
Rethinking Constraint Awareness for Efficient State Embedding of Neural Routing Solver
The CARM module boosts neural routing solvers by adaptively modulating embeddings with constraint variables, enabling better use of global observations and improved performance on constrained VRPs.
-
RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache
RDKV derives per-token and per-channel weights from attention distortion, then uses reverse water-filling to assign bit-widths from full precision to zero after prefilling, recovering 97.81% accuracy with 2.48% cache retention on LongBench.
-
From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning
M2D distillation augments input graphs with model-derived features and structure, letting simple student GNNs match teacher performance while exposing mechanisms such as attention and fairness directly in the data.
-
UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
A shared global expert pool in MoE improves validation loss over per-layer experts and allows sublinear expert-parameter growth with depth.
-
Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
-
X-LogSMask: Expand Transformer for Graph-Structured Data
X-LogSMask injects per-head powers of the normalized adjacency matrix via a logarithmic transform into Transformer attention, achieving SOTA results on 13 of 20 graph benchmarks while remaining competitive in a one-layer setup.
-
Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
Aligning the DDIM forward diffusion process with flow-matching manifold evolution enables high-quality generation without time conditioning, and class-conditional synthesis is possible with an unconditional denoiser by using separate time spaces per class.
-
EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation
EgoMotion decouples reasoning from motion synthesis in egocentric vision-language tasks by mapping inputs to motion primitives via VLM then using diffusion to produce grounded and coherent 3D trajectories.
-
Computational Hermeneutics: Evaluating generative AI as a cultural technology
Generative AI should be evaluated through computational hermeneutics using iterative, human-inclusive benchmarks that measure cultural context rather than isolated model outputs.
-
RASALoRE: Region Aware Spatial Attention with Location-based Random Embeddings for Weakly Supervised Anomaly Detection in Brain MRI Scans
A novel weakly supervised anomaly detection method for brain MRI that uses discriminative dual prompt tuning for pseudo masks and region-aware spatial attention with location-based random embeddings to achieve SOTA results with under 8 million parameters on BraTS and MSD datasets.