Spectra defines and controls effective capacity in graph embeddings via the Shannon effective rank of a trace-normalized kernel spectrum, making capacity a post-fit property rather than a pre-training hyperparameter.
F oundations and Trends in Machine Learning , 5(2–3):123–286
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
ContextualJailbreak uses evolutionary search over simulated primed dialogues with novel mutations to reach 90-100% attack success on open LLMs and transfers to some closed frontier models at 15-90% rates.
The observability and controllability Gramians parameterized by sensor and actuator node subsets are determinantal point processes.
HyperX is the first end-to-end FPGA accelerator for Nyström-based HDC graph classification, delivering 6.85× speedup and 169× energy efficiency over CPU baselines plus 3.4% average accuracy gain on TUDataset benchmarks.
LDDR proposes a linear DPP-based dynamic-resolution frame sampler that achieves 3x speedup and up to 2.5-point gains on video MLLM benchmarks by selecting non-redundant frames and allocating tokens accordingly.
Exact sampling algorithm for Pfaffian point processes via skew-symmetric Cholesky factorization, together with a symplectic Arnoldi method for constructing skew-orthogonal polynomial kernels.
A question-adaptive greedy frame selector combines SigLIP relevance and DINOv2 coverage under a submodular objective with a text classifier routing to preset trade-offs, yielding accuracy gains on MLVU especially at low frame budgets.
Proposes a minimum measurement standard for LLM-as-a-judge in multi-hop RAG that fixes budgets and requires cluster-aware inference, showing it alters which baseline comparisons remain significant.
RCD balances relevance, coverage, and diversity in a knapsack-constrained selection framework, with experiments showing that selector choice and budget level determine optimal unitization strategies on clinical datasets.
Generalizing two DPP-based Monte Carlo estimators to continuous domains provides variance rates of O(N^{-(1+1/d)}) for a fixed DPP method and O(1/N) for a tailored DPP method, along with new sampling algorithms.
citing papers explorer
-
Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models
Spectra defines and controls effective capacity in graph embeddings via the Shannon effective rank of a trace-normalized kernel spectrum, making capacity a post-fit property rather than a pre-training hyperparameter.
-
ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming
ContextualJailbreak uses evolutionary search over simulated primed dialogues with novel mutations to reach 90-100% attack success on open LLMs and transfers to some closed frontier models at 15-90% rates.
-
Connections Between Determinantal Point Processes and Gramians in Control
The observability and controllability Gramians parameterized by sensor and actuator node subsets are determinantal point processes.
-
LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs
LDDR proposes a linear DPP-based dynamic-resolution frame sampler that achieves 3x speedup and up to 2.5-point gains on video MLLM benchmarks by selecting non-redundant frames and allocating tokens accordingly.
-
Sampling Pfaffian point processes and the symplectic Arnoldi method
Exact sampling algorithm for Pfaffian point processes via skew-symmetric Cholesky factorization, together with a symplectic Arnoldi method for constructing skew-orthogonal polynomial kernels.
-
Adaptive Greedy Frame Selection for Long Video Understanding
A question-adaptive greedy frame selector combines SigLIP relevance and DINOv2 coverage under a submodular objective with a text classifier routing to preset trade-offs, yielding accuracy gains on MLVU especially at low frame budgets.
-
A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test
Proposes a minimum measurement standard for LLM-as-a-judge in multi-hop RAG that fixes budgets and requires cluster-aware inference, showing it alters which baseline comparisons remain significant.
-
Budget-Aware Routing for Long Clinical Text
RCD balances relevance, coverage, and diversity in a knapsack-constrained selection framework, with experiments showing that selector choice and budget level determine optimal unitization strategies on clinical datasets.
-
On two ways to use determinantal point processes for Monte Carlo integration
Generalizing two DPP-based Monte Carlo estimators to continuous domains provides variance rates of O(N^{-(1+1/d)}) for a fixed DPP method and O(1/N) for a tailored DPP method, along with new sampling algorithms.