Ranking
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
arXiv:2606.08382v1 Announce Type: new Abstract: Low-rank projection has emerged as a promising approach for compressing the KV cache by exploiting hidden-dimension redundancy. However, prior methods rely on fixed or heuristic rank selection and struggle to achieve aggressive compression with minimal accuracy degradation. We propose STAR-KV, an adaptive low-rank KV cache compression framework with fine-grained rank control.
Logarithmic Density of Rank $\geq 1$ and Rank $\geq 2$ Genus-2 Jacobians and Applications to Hyperelliptic Curve Cryptography
Announce Type: replace-cross Abstract: In this work we study quantitative existence results for genus-$2$ curves over $\mathbb{Q}$ whose Jacobians have Mordell--Weil rank at least $1$ or $2$, ordering the curves by the naive height of their integral Weierstrass models. We use geometric techniques to show that asymptotically the Jacobians of almost all integral models with two rational points at infinity have rank $r \geq Since there are $\asymp X^{\frac{13}{2}}$ such models among the $X^7$...
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
arXiv:2505.16014v5 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems deployed in sensitive domains must provide interpretable evidence selection and robust safeguards against data poisoning, yet current approaches rely on opaque similarity-based retrieval with arbitrary top-k cutoffs that offer no explanation for their selections and remain vulnerable to adversarial manipulation. METEORA replaces re-ranking with rationale-driven selection via three components: a...
Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization
new Abstract: Visual Prompting (VP) has emerged as an efficient paradigm for adapting large-scale pre-trained vision models to downstream tasks by incorporating learnable prompts at the input level. However, existing VP methods typically employ dense pixel-level prompts, which often suffer from redundant perturbations, limited generalization and energy inefficiency. To overcome these limitations, we propose to integrate brain-inspired spiking learning into visual prompt learning tasks.
Parameter-Efficient Fine-Tuning with Learnable Rank
new Abstract: Low-Rank Adaptation (LoRA) is a popular parameter-efficient fine-tuning (PEFT) method that restricts weight updates to low-rank adapters, introducing a fixed low-rank inductive bias by optimizing in a low-dimensional subspace. In this work, we question whether a fixed-rank constraint is the most effective inductive bias for parameter-efficient fine-tuning. We introduce *Learnable Rank LoRA (LR-LoRA)*, a PEFT method in which the adapter rank is learned during the training process.
Asymptotic tensor rank is characterized by polynomials
arXiv:2411.15789v2 Announce Type: replace Abstract: Asymptotic tensor rank is notoriously difficult to determine. Indeed, determining its value for the $2\times 2$ matrix multiplication tensor would determine the matrix multiplication exponent, a long-standing open problem. On the other hand, Strassen's asymptotic rank conjecture makes the bold claim that asymptotic tensor rank equals the largest dimension of the tensor and is thus as easy to compute as matrix rank.
Approximating $f$-Divergences with Rank Statistics
arXiv:2601.22784v2 Announce Type: replace-cross Abstract: We introduce a rank-statistic approximation of $f$-divergences that avoids explicit density-ratio estimation by working directly with the distribution of ranks. For a resolution parameter $K$, we map the mismatch between two univariate distributions $\mu$ and $\nu$ to a rank histogram on $\{ 0, \ldots, K\}$ and measure its deviation from uniformity via a discrete $f$-divergence, yielding a rank-statistic divergence estimator. We prove...
Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
arXiv:2606.03723v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) enables parameter-efficient specialization of foundation models, but the proliferation of task-specific adapters fragments capabilities across many adapters, complicating reuse and deployment. We study the problem of merging $T$ LoRAs into a single rank-$r$ LoRA, thereby preserving the benefits of low-rank structure.
Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation
arXiv:2606.08679v1 Announce Type: cross Abstract: Pretrained models are often evaluated on multi-task leaderboards to measure their applicability in diverse contexts. However, current methods for aggregating performance across tasks into leaderboard-level rankings do not address the uncertainty and variability at the task level. While recent works have proposed interval-based model rankings, the principled aggregation of uncertainty from individual tasks to leaderboard-level rankings remains...
Maine’s race for governor heads to ranked choice tallies in both primaries
The Democratic and Republican primaries for governor of Maine are both up in the air, with a broad field of candidates competing and Maine’s ranked choice voting system adding another layer of complexity. No candidate in either primary will get majority support, NBC News projects, meaning the contests will both go to ranked choice tabulations to determine the nominees. In 2016, Maine was the first state in the country to implement ranked choice voting for statewide and federal elections.