Tootfinder

Unified Scaling Laws for Compressed Representations
Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu, Vage Egiazarian, Mher Safaryan, Dan Alistarh
https://arxiv.org/abs/2506.01863

Unified Scaling Laws for Compressed Representations
Scaling laws have shaped recent advances in machine learning by enabling predictable scaling of model performance based on model size, computation, and data volume. Concurrently, the rise in computational cost for AI has motivated model compression techniques, notably quantization and sparsification, which have emerged to mitigate the steep computational demands associated with large-scale training and inference. This paper investigates the interplay between scaling laws and compression formats…

Hybrid scaling mechanism of critical behavior in the overlapping critical regions of classical and quantum Yang-Lee edge singularities
Yue-Mei Sun, Wen-Jing Yu, Xin-Yu Wang, Liang-Jun Zhai
https://arxiv.org/abs/2506.00919

Hybrid scaling mechanism of critical behavior in the overlapping critical regions of classical and quantum Yang-Lee edge singularities
Recently, the study of scaling behavior in Yang-Lee edge singularities (YLES) has attracted sustained attention. However, the scaling mechanism for the overlapping critical region between classical and quantum YLES remains unclear. In this work, we investigate this question, and a hybrid scaling mechanism is introduced to characterize the scaling behavior in the overlapping regions. The hybrid scaling mechanism asserts that in the overlapping region the scaling behavior can be described by the …

This https://arxiv.org/abs/2505.15304 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control
Deep neural network (DNN)-based policy models, such as vision-language-action (VLA) models, excel at automating complex decision-making from multi-modal inputs. However, scaling these models greatly increases computational overhead, complicating deployment in resource-constrained settings like robot manipulation and autonomous driving. To address this, we propose Saliency-Aware Quantized Imitation Learning (SQIL), which combines quantization-aware training with a selective loss-weighting strate…

On the Scaling of Robustness and Effectiveness in Dense Retrieval
Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng
https://arxiv.org/abs/2505.24279 …

On the Scaling of Robustness and Effectiveness in Dense Retrieval
Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent work has addressed scaling laws of effectiveness in dense retrieval, revealing a power-law relationship between effectiveness and the size of models and data. Does robustness follow scaling laws too? If so, can scaling improve both robustness and effectiveness together, or do they remain locked in a trade-off? To answ…

Control-R: Towards controllable test-time scaling
Di Zhang, Weida Wang, Junxian Li, Xunzhi Wang, Jiatong Li, Jianbo Wu, Jingdi Lei, Haonan He, Peng Ye, Shufei Zhang, Wanli Ouyang, Yuqiang Li, Dongzhan Zhou
https://arxiv.org/abs/2506.00189

Control-R: Towards controllable test-time scaling
This paper target in addressing the challenges of underthinking and overthinking in long chain-of-thought (CoT) reasoning for Large Reasoning Models (LRMs) by introducing Reasoning Control Fields (RCF)--a novel test-time approach that injects structured control signals to guide reasoning from a tree search perspective. RCF enables models to adjust reasoning effort according to given control conditions when solving complex tasks. Additionally, we present the Control-R-4K dataset, which consists …

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
Jennifer Chen, Aidar Myrzakhan, Yaxin Luo, Hassaan Muhammad Khan, Sondos Mahmoud Bsharat, Zhiqiang Shen
https://arxiv.org/abs/2506.01954

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
Retrieval-Augmented Generation (RAG) methods have proven highly effective for tasks requiring factual consistency and robust knowledge retrieval. However, large-scale RAG systems consume significant computational resources and are prone to generating hallucinated content from Humans. In this work, we introduce $\texttt{DRAG}$, a novel framework for distilling RAG knowledge from large-scale Language Models (LLMs) into small LMs (SLMs). Our approach leverages evidence- and knowledge graph-based d…

From Pixels to Camera: Scaling Superconducting Nanowire Single-Photon Detectors for Imaging at the Quantum-Limit
Jun Gao, Jin Chang, Bruno Lopez Rodriguez, Iman Esmaeil Zadeh, Val Zwiller, Ali W. Elshaari
https://arxiv.org/abs/2505.24725

From Pixels to Camera: Scaling Superconducting Nanowire Single-Photon Detectors for Imaging at the Quantum-Limit
Superconducting nanowire single-photon detectors (SNSPDs) have emerged as essential devices that push the boundaries of photon detection with unprecedented sensitivity, ultrahigh timing precision, and broad spectral response. Recent advancements in materials engineering, superconducting electronics integration, and cryogenic system design are enabling the evolution of SNSPDs from single-pixel detectors toward scalable arrays and large-format single-photon time tagging cameras. This perspective …

Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling
Bruce Fang, Danyi Gao
https://arxiv.org/abs/2507.00550 https:/…

Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling
This paper addresses the challenges of rapid resource variation and highly uncertain task loads in cloud computing environments. It proposes an optimization method for elastic cloud resource scaling based on a multi-agent system. The method deploys multiple autonomous agents to perceive resource states in parallel and make local decisions. While maintaining the distributed nature of the system, it introduces a collaborative value function to achieve global coordination. This improves the respon…

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
Dongyi Ding, Tiannan Wang, Chenghao Zhu, Meiling Tao, Yuchen Eleanor Jiang, Wangchunshu Zhou
https://arxiv.org/abs/2507.01887

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
Large language models (LLMs) excel at reasoning tasks requiring long thought sequences for planning, reflection, and refinement. However, their substantial model size and high computational demands are impractical for widespread deployment. Yet, small language models (SLMs) often struggle to learn long-form CoT reasoning due to their limited capacity, a phenomenon we refer to as the "SLMs Learnability Gap". To address this, we introduce \textbf{Mi}d-\textbf{Co}T \textbf{T}eacher \textbf{A}ssist…

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
Yating Wang, Haoyi Zhu, Mingyu Liu, Jiange Yang, Hao-Shu Fang, Tong He
https://arxiv.org/abs/2507.01016

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
In this paper, we introduce an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory dataset to date, leveraging over 100 times more data than previous approaches. This extensive dataset enables our tokenizer to capture rich spatiotemporal dynamics, resulting in a model that not only accelerates inference but also generates smoother and more coherent action outputs. Once trained, the tokenizer can be seamlessly adapted to a wide range of downstream…