Hasil untuk "Speculative philosophy"

Zhenwei Tang, Arun Verma, Zijian Zhou et al.

Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model. However, the performance of standard SD is often limited by the strictly sequential execution of these drafting and verification stages. To address this, this paper proposes MineDraft, a batch parallel speculative decoding (PSD) framework designed to effectively hide drafting latency by overlapping it with verification. Our theoretical analysis shows that PSD is substantially more efficient than standard SD. MineDraft realizes the PSD through a novel batch-parallel design that maintains two batches of requests, overlapping drafting for one batch with verification for the other. Our experimental results show significant improvements of MineDraft in both throughput (up to 75%) and end-to-end latency (up to 39%) over standard SD. Furthermore, we have implemented MineDraft as a plugin for vLLM, demonstrating its practicality for production-ready inference systems.

Sebastian De Haro, Jeremy Butterfield

This monograph discusses dualities in physics: what dualities are, their main examples--from quantum mechanics and electrodynamics to statistical mechanics, quantum field theory and string theory--and the philosophical questions they raise. Part I first conceptualises dualities and discusses their main roles and themes, including how they are related to familiar notions like symmetry and interpretation. It also discusses the main simple examples of dualities: position-momentum, wave-particle, electric-magnetic, and Kramers-Wannier dualities. Part II discusses advanced examples and their inter-relations: particle-soliton dualities, electric-magnetic dualities in quantum field theories, dualities in string theory, and gauge-gravity duality. This Part ends with discussions of the hole argument, and how string theory counts the microstates of a black hole. Part III is an in-depth discussion of general philosophical issues on which dualities bear: theoretical equivalence (two theories 'saying the same thing, in different words'), scientific realism and the under-determination of theories by data, theory succession and the M-theory programme, explanation, and scientific understanding. It proposes a view of scientific theories that it dubs 'the geometric view of theories'. The book's treatment of the examples is at the advanced undergraduate and graduate level, starting from elementary and progressing to more advanced examples. The discussions of philosophical topics, such as referential semantics, theoretical equivalence, scientific realism and scientific understanding, are both self-contained and in-depth. Thus the book is aimed at students and researchers with an interest in the physical examples and philosophical questions about dualities, and also in how physics and philosophy can fruitfully interact with each other.

Heming Xia, Cunxiao Du, Yongqi Li et al.

This tutorial presents a comprehensive introduction to Speculative Decoding (SD), an advanced technique for LLM inference acceleration that has garnered significant research interest in recent years. SD is introduced as an innovative decoding paradigm to mitigate the high inference latency stemming from autoregressive decoding in LLMs. At each decoding step, SD efficiently drafts several future tokens and then verifies them in parallel. This approach, unlike traditional autoregressive decoding, facilitates the simultaneous decoding of multiple tokens per step, thereby achieving promising 2x-4x speedups in LLM inference while maintaining original distributions. This tutorial delves into the latest techniques in SD, including draft model architectures and verification strategies. Additionally, it explores the acceleration potential and future research directions in this promising field. We aim for this tutorial to elucidate the current research landscape and offer insights for researchers interested in Speculative Decoding, ultimately contributing to more efficient LLM inference.

Xuekang Wang, Shengyu Zhu, Xueqi Cheng

Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with additional safety properties to defend against these attacks. However, tuning large models has become increasingly resource intensive and may have difficulty ensuring consistent performance. We introduce Speculative Safety-Aware Decoding (SSD), a lightweight decoding-time approach that equips LLMs with the desired safety property while accelerating inference. We assume that there exists a small language model that possesses this desired property. SSD integrates speculative sampling during decoding and leverages the match ratio between the small and composite models to quantify jailbreak risks. This enables SSD to dynamically switch between decoding schemes to prioritize utility or safety, to handle the challenge of different model capacities. The output token is then sampled from a new distribution that combines the distributions of the original and the small models. Experimental results show that SSD successfully equips the large model with the desired safety property, and also allows the model to remain helpful to benign queries. Furthermore, SSD accelerates the inference time, thanks to the speculative sampling design.

Hong Joo Ryoo

Modern physics proposals present deep tensions between seemingly contradictory descriptions of reality. Views of wave-particle duality, black hole complementarity, and the Unruh effect demand explanations that shift depending on how a system is observed. However, traditional models of scientific explanation impose a fixed structure that fails to account for varying observational contexts. This paper introduces context-dependent mapping, a framework that reorganizes physical laws into self-consistent subsets structured around what can actually be observed in a given context. By doing so, it provides a principled way to integrate complementarity into the philosophy of explanation.

Louis Vervoort, Vitaly Nikolaev

We propose a test for abstract causal reasoning in AI, based on scholarship in the philosophy of causation, in particular on the neuron diagrams popularized by D. Lewis. We illustrate the test on advanced Large Language Models (ChatGPT, DeepSeek and Gemini). Remarkably, these chatbots are already capable of correctly identifying causes in cases that are hotly debated in the literature. In order to assess the results of these LLMs and future dedicated AI, we propose a definition of cause in neuron diagrams with a wider validity than published hitherto, which challenges the widespread view that such a definition is elusive. We submit that these results are an illustration of how future philosophical research might evolve: as an interplay between human and artificial expertise.

Marcelo Viktor Gilge

Ernst Haeckel (1834-1919) foi um renomado pesquisador alemão da segunda metade do século XIX e início do século XX. Parte de sua produção científica foi devotada a defender e divulgar as ideias darwinianas de modificação das espécies em seu país. Entre as ideias de Haeckel, destaca-se a Lei Biogenética Fundamental, na qual ele afirmava que os estágios de desenvolvimento pelos quais passam os embriões recapitulam a história evolutiva do filo. Para explicar essa ideia, na obra Natürliche Schöpfungsgeschichte (História Natural da Criação) de 1868, Haeckel utilizou ilustrações de embriões que foram alvo de críticas e acusações de fraude e plágio. Este artigo tem por objetivos analisar o uso que Ernst Haeckel fez dessas ilustrações, relatando algumas das críticas de cientistas contemporâneas e posteriores e proporcionar um material para atividades pedagógicas voltadas ao ensino de evolução biológica e desenvolvimento embrionário. Em aproximação a análises realizadas por alguns historiadores da ciência, conclui-se que Haeckel se defendeu razoavelmente e que a motivação maior das críticas era o ataque ao darwinismo.

P. J. E. Peebles

I argue that research in physics operates under an implicit community philosophy, and I offer a definition I think physicists would accept, by and large. I compare this definition to what philosophers, sociologists, and historians of science, with physicists, say we are doing.

Christine Reeh Peters

This article considers film as a form of artificial intelligence (AI). This non-anthropocentric hypothesis was first formulated in 1946 by filmmaker and theorist Jean Epstein and regards film as the thinking performance of a technical apparatus, the cinematograph, which is a manifestation of machine thinking based on the holistic entanglement of thought and world, film and philosophy. The article pursues an enquiry into ‘thinking’: one of the most prominent and oldest topics considered in philosophy, and also essential to art and film. Thinking is not only characterised as a sense (like sight or taste) but as a creative and, ultimately, intra-active act. The possibility of film as AI is approached not only from a Deleuzian angle, long appraised by film-philosophy, but also through questions recently raised by theories of artistic research and the speculative-materialist turn in contemporary philosophy. The latter have as a common denominator a strong critique of anthropocentrism in Western philosophy; the article enquires into this criticism from different angles and applies it to the main hypothesis of this analysis – to regard film as a form of AI.

J. Katzav

C H

Books Received

E. A. Gradoboeva, Zh. S. Tyulko, A. V. Fadeev et al.

Relevance. To date, no detailed analysis of the variants of the pathogen circulating at different times on the territory of the Omsk region has been carried out.Aim. Comparative analysis of the diversity of circulating variants of SARS­CoV­-2 based on molecular genetic data, determine the lines and time of their appearance, compare the data obtained with data from the GISAID database.Materials and methods. Genome­wide sequencing of 222 primary and 5 culture (passages on Vero E6 and SPEV cell cultures) samples of SARS­-CoV­-2 from the Omsk region, collected from April 2020 to February 2022, on Oxford Nanopore Technologies and Illumina platforms, was carried out. Genetic lines were determined in Pangolin. The analysis was performed in MEGA7 and BioEdit.Results. 227 genome­wide SARS­-CoV­-2 sequences were obtained. 222 genomes have been uploaded to the GISAID database. The lines to which the samples belong were determined, phylogenetic trees were constructed for various regions of the SARS-CoV­-2 genome, the levels of virus homology were assessed and mutations in the S­protein region were analyzed.Conclusions. According to the data obtained, it is possible to roughly judge the time of the appearance of a particular variant, its consolidation and distribution in the population, and observe the rare mutations and the circulation of some rare lines. To assess the possibility of significant geographically linked changes in the SARS­-CoV­-2 in the Omsk region, the data obtained are insufficient. Virus variants circulating in the region are grouped into one cluster with identical variants from other regions or countries. A more pronounced intracluster differentiation of the lines can be observed when analyzing the RBD region. The situation with COVID­-19 in the Omsk region generally coincides with that in the whole country and the world. However, this does not exclude the parallel occurrence of certain mutations in remote territories from each other.

Iaan Reynolds

Haim Barad, Ekaterina Aidova, Yury Gorbachev

Inference optimizations are critical for improving user experience and reducing infrastructure costs and power consumption. In this article, we illustrate a form of dynamic execution known as speculative sampling to reduce the overall latency of text generation and compare it with standard autoregressive sampling. This can be used together with model-based optimizations (e.g. quantization) to provide an optimized solution. Both sampling methods make use of KV caching. A Jupyter notebook and some sample executions are provided.

J. Katzav

ABSTRACT This paper introduces the philosophy of Grace Andrus de Laguna in order to renew interest in it. I show that, in the 1910s and 1920s, she develops ideas and arguments that are also found playing key roles in the development of analytic philosophy decades later. Further, I describe her sympathetic, but acute, criticism of pragmatism and Heideggerian ontology, and situate her work in the tradition of American, speculative philosophy. Before 1920, we will see, de Laguna appeals to multiple realizability to undermine reductionism in science, to support perspectival, scientific realism and, with help from a private language argument, to favour the view that mental states are classified by behavioural, teleological roles over what came to be called ‘type physicalism’. Her view of speech, mostly developed in the 1920s, tells us that its primary role is coordinating group behaviour rather than expressing thoughts. Belief is understood in terms of its causal role, including its causal relations to other kinds of mental states, when coordinating group behaviour. Thought is similarly understood. In developing her theory of mind, de Laguna rejects the pragmatist claims that belief can be reduced to dispositions to behaviour and that thought’s function is to address specific, rather than general, problems. She also favours meaning holism and rejects the analytic–synthetic distinction. In later work, de Laguna argues that individuals’ activity of self-maintenance brings universals, conceived of as irreducible potentialities, into being and makes them increasingly determinate. Further, she identifies the existence of all individuals with forms of self-maintenance and takes the existence of people to include maintenance of the cultural world. Such a unified treatment of existence, she holds, permits making its evolution intelligible. Heidegger’s view of being is rejected for not permitting this. All de Laguna’s work, we will see, fits a vision of philosophy as the systematic, imaginative and naturalistic examination of being as well as a source of criticism of science.

J. Katzav, K. Vaesen

This article contributes to explaining the rise of logical empiricism in mid-twentieth century (North) America and to a better understanding of American philosophy of science before the dominance of logical empiricism. We show that, contrary to a number of existing histories, philosophy of science was already a distinct subfield of philosophy, one with its own approaches and issues, even before logical empiricists arrived in America. It was a form of speculative philosophy with a concern for speculative metaphysics, normative issues relating to science and society, and issues that later were associated with logical empiricist philosophy of science, issues such as confirmation, scientific explanation, reductionism, and laws of nature. Further, philosophy of science was not primarily pragmatist in orientation. We also show, with the help of our historical characterization, that a recent account of the emergence of analytic philosophy applies to the rise of logical empiricism. It has been argued that the emergence of American analytic philosophy is partly explained by analytic philosophers’ use of key institutions, including journals, to marginalize speculative philosophy and promote analytic philosophy. We argue that this use of institutions included the marginalization of speculative and value-laden philosophy of science and the promotion of logical empiricism.

J. Katzav

Sara Ishii

Abstract:In a 1983 interview with Christine Weiland, Gloria Anzaldúa posited that human and nonhuman connectivity exists outside hierarchical arrangements. Some twenty years after Anzaldúa’s interview, the “Speculative Turn” emerged in continental philosophy which critiques anthropocentrism in modern philosophy and reconceptualizes nonhuman subjectivity. While Anzaldúa’s scholarship addresses core issues that are highlighted by the speculative turn, little scholarship exists that places her into conversation with these new trajectories in continental philosophy. In this essay, I aim to contribute to this nascent scholarship and explore the question, How can Anzaldúa’s creative work contribute to and expand scholarship of the speculative turn? I investigate how Anzaldúa’s work can help bridge connections between differing veins of speculative turn thought, specifically Graham Harman’s object-oriented philosophy (OOP) and Jane Bennett’s vital materialism (VM). Conversations between Harman and Bennett demonstrate a split in understanding nonhuman autonomy and relationality and represent incompatibilities between OOP and VM. Interested in these departures, I posit that Anzaldúa’s creative works, such as poetry and drawing, offer ways to challenge problematic human/nonhuman relations and bridge philosophical divides within the speculative turn.

A. A. Golubkova, T. A. Platonova, S. S. Smirnova et al.

Relevance. The new coronavirus infection (COVID-19), which appeared in late 2019 in China, has spread to almost all countries of the world in just a few months. The explosive nature of its spread was accompanied by the formation of large epidemic foci in organizations of various profiles, including leisure and sports. Aims. To establish the conditions and causes of the spread of SARS-CoV-2 among the members of one of the sports clubs based on an in-depth epidemiological analysis. Materials and methods. To study the features of the spread of the SARS-CoV-2 virus in a sports organization, the following documents were used previously developed by the authors and successfully tested in practice: «Act of epidemiological investigation of group and outbreak morbidity of new coronavirus infection (COVID-19) at an enterprise/organization/institution» and «Individual card of a patient with a new coronavirus infection (COVID-19) at the enterprise / organization/institution». In the process of epidemiological investigation, in order to detect SARS-CoV-2 RNA in PCR, a laboratory examination of sports club participants (sick and contact) was conducted, followed by genome-wide sequencing of isolated SARS-CoV-2 viruses on the basis of the Laboratory of Molecular Virology of the A. A. Smorodintsev Influenza Research Institute, which performs these types of studies. Results. Within 17 days, 26 cases of COVID- 19 were registered among the sports team members and staff from the support group (coaching staff, medical staff, administrators), which was 74.3% of their actual number. The majority of patients (76.9%) had mild acute respiratory infection, two (7.7%) had no symptoms, and four (15.4%) had interstitial pneumonia. Of the clinical manifestations of the disease, the most frequent were weakness, fever, headache, muscle and joint pain, difficulty in nasal breathing and serous-mucous discharge from the nose, sore throat, cough, shortness of breath, anosmia and dyspeptic manifestations in the form of diarrhea, nausea or vomiting. The occurrence of the outbreak was the result of the introduction of infection from the opposing team at the tournament. The leading factors that contributed to the spread of COVID-19 among sports club members were the admission to games and training of athletes with acute respiratory infections, prolonged close contact between players during training and competitions, violations in the use of personal protective equipment, compliance with hygiene and hand antiseptics, disinfection measures in the premises of sports institutions and defects in the implementation of the regulations for the examination of teams for SARS-CoV-2 during tournaments. Conclusion. Based on the results of the study, data were obtained on the features of the spread of SARS-CoV-2 in sports organizations, which can be used in conducting preventive and anti-epidemic measures in sports and leisure institutions.

Rafael dos Reis Ferreira, João Antonio de Moraes, Pedro Bravo de Souza et al.

A Kínesis – Revista de Estudos dos Pós-Graduandos em Filosofia apresenta para a comunidade acadêmica filosófica mais uma edição, o Volume 14, Número 36 (2022). Publicamos 23 artigos e 2 traduções. Agradecemos aos pesquisadores que compõem o Conselho Científico da Kínesis e também aos pareceristas ad hoc pela colaboração e disponibilidade permanente para atender nossas solicitações de parecer. Agradecemos, também, aos autores pesquisadores por confiarem a submissão e publicação de suas pesquisas à Kínesis. Convidamos nossos leitores para apreciarem mais este número.