KVM is a novel block-recurrent compressed memory for attention that unifies expandable transformer context with linear RNN efficiency, enabling competitive long-context performance with released code and models.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
background 1polarities
background 1representative citing papers
GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
Spherical vMF flows reduce the continuity equation on the sphere to a scalar ODE in cosine similarity, enabling posterior-weighted sampling of categorical sequences via cross-entropy trained posteriors.
LLMs contain identifiable COCO neurons that enable implicit self-correction against stereotypes; targeted editing of these neurons improves fairness and robustness to jailbreaks while preserving generation quality.
Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, delivering higher efficiency, information capacity, and throughput than other linear-complexity models.
Poetic jailbreaks succeed because they induce distinct attention patterns in LLMs that are independent of harmful-content detection, not because models fail to recognize literary formatting.
FCP shards sequences at block level with flexible P2P communication and bin-packing to achieve near-linear scaling up to 256 GPUs and 1.13x-2.21x higher attention MFU in foundation model pre-training.
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.
citing papers explorer
-
Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
KVM is a novel block-recurrent compressed memory for attention that unifies expandable transformer context with linear RNN efficiency, enabling competitive long-context performance with released code and models.
-
GravityGraphSAGE: Link Prediction in Directed Attributed Graphs
GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
-
From Mechanistic to Compositional Interpretability
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
-
Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
-
Spherical Flows for Sampling Categorical Data
Spherical vMF flows reduce the continuity equation on the sphere to a scalar ODE in cosine similarity, enabling posterior-weighted sampling of categorical sequences via cross-entropy trained posteriors.
-
Modeling Implicit Conflict Monitoring Mechanisms against Stereotypes in LLMs
LLMs contain identifiable COCO neurons that enable implicit self-correction against stereotypes; targeted editing of these neurons improves fairness and robustness to jailbreaks while preserving generation quality.
-
Structured Recurrent Mixers for Massively Parallelized Sequence Generation
Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, delivering higher efficiency, information capacity, and throughput than other linear-complexity models.
-
Metaphor Is Not All Attention Needs
Poetic jailbreaks succeed because they induce distinct attention patterns in LLMs that are independent of harmful-content detection, not because models fail to recognize literary formatting.
-
Unleashing Scalable Context Parallelism for Foundation Models Pre-Training via FCP
FCP shards sequences at block level with flexible P2P communication and bin-packing to achieve near-linear scaling up to 256 GPUs and 1.13x-2.21x higher attention MFU in foundation model pre-training.
-
Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.