mastodon.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
The original server operated by the Mastodon gGmbH non-profit

Administered by:

Server stats:

297K
active users

#cs

7 posts7 participants0 posts today

🤥 Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics

arxiv.org/abs/2501.17273

arXiv logo
arXiv.orgTailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated StatisticsLarge Language Models (LLMs) are becoming increasingly persuasive, demonstrating the ability to personalize arguments in conversation with humans by leveraging their personal data. This may have serious impacts on the scale and effectiveness of disinformation campaigns. We studied the persuasiveness of LLMs in a debate setting by having humans $(n=33)$ engage with LLM-generated arguments intended to change the human's opinion. We quantified the LLM's effect by measuring human agreement with the debate's hypothesis pre- and post-debate and analyzing both the magnitude of opinion change, as well as the likelihood of an update in the LLM's direction. We compare persuasiveness across established persuasion strategies, including personalized arguments informed by user demographics and personality, appeal to fabricated statistics, and a mixed strategy utilizing both personalized arguments and fabricated statistics. We found that static arguments generated by humans and GPT-4o-mini have comparable persuasive power. However, the LLM outperformed static human-written arguments when leveraging the mixed strategy in an interactive debate setting. This approach had a $\mathbf{51\%}$ chance of persuading participants to modify their initial position, compared to $\mathbf{32\%}$ for the static human-written arguments. Our results highlight the concerning potential for LLMs to enable inexpensive and persuasive large-scale disinformation campaigns.
#lie#llm#cs

-𝟘: The Power of Negative Zero: Datatype Customization for Quantized Large Language Models

(... they get an amazing boost in performance from this!)

arxiv.org/abs/2501.04052

arXiv logo
arXiv.orgThe Power of Negative Zero: Datatype Customization for Quantized Large Language ModelsLarge language models (LLMs) have demonstrated remarkable performance across various machine learning tasks, quickly becoming one of the most prevalent AI workloads. Yet the substantial memory requirement of LLMs significantly hinders their deployment for end users. Post-training quantization (PTQ) serves as one of the most hardware-efficient methods to mitigate the memory and computational demands of LLMs. Although the traditional integer (INT) datatype has received widespread adoption in PTQ methods, floating-point (FP) quantization has emerged as a viable alternative thanks to its effectiveness in fitting LLM numerical distributions. However, the FP datatype in sign-magnitude binary representation contains both positive and negative zero, which constrains its representation capability, particularly under low precision (3 and 4 bits). In this paper, we extend the basic FP datatype to perform Redundant Zero Remapping (RaZeR), which remaps the negative zero FP encoding to a set of pre-defined special values to maximally utilize FP quantization encodings and to better fit LLM numerical distributions. Through careful selection of special values, RaZeR outperforms conventional asymmetric INT quantization while achieving high computational efficiency. We demonstrate that RaZeR can be seamlessly integrated with quantization algorithms for both weights and KV-cache, including advanced methods with clipping and transformations, and consistently achieve better model accuracy. Additionally, we implement a fast GEMV kernel with fused dequantization that efficiently converts the 4-bit RaZeR value to FP16 through novel bit-level manipulation. On modern GPUs, our evaluation shows that RaZeR improves the GEMV speed by up to 7.56$\times$ compared to the FP16 implementation, while achieving up to 2.72$\times$ speedup in the LLM decoding throughput.
#ai#ml#cs

📰 "Deep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted Therapeutics"
arxiv.org/abs/2502.01012 #Q-Bio.Qm #Stat.Me #Matrix #Force #Cs.Lg

arXiv logo
arXiv.orgDeep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted TherapeuticsRecent technological advances have introduced new high-throughput methods for studying host-virus interactions, but testing synergistic interactions between host gene pairs during infection remains relatively slow and labor intensive. Identification of multiple gene knockdowns that effectively inhibit viral replication requires a search over the combinatorial space of all possible target gene pairs and is infeasible via brute-force experiments. Although active learning methods for sequential experimental design have shown promise, existing approaches have generally been restricted to single-gene knockdowns or small-scale double knockdown datasets. In this study, we present an integrated Deep Active Learning (DeepAL) framework that incorporates information from a biological knowledge graph (SPOKE, the Scalable Precision Medicine Open Knowledge Engine) to efficiently search the configuration space of a large dataset of all pairwise knockdowns of 356 human genes in HIV infection. Through graph representation learning, the framework is able to generate task-specific representations of genes while also balancing the exploration-exploitation trade-off to pinpoint highly effective double-knockdown pairs. We additionally present an ensemble method for uncertainty quantification and an interpretation of the gene pairs selected by our algorithm via pathway analysis. To our knowledge, this is the first work to show promising results on double-gene knockdown experimental data of appreciable scale (356 by 356 matrix).

📰 "Single-neuron deep generative model uncovers underlying physics of neuronal activity in Ca imaging data"
arxiv.org/abs/2501.14615 #Dynamics #Q-Bio.Nc #Cs.Lg #Cell

arXiv logo
arXiv.orgSingle-neuron deep generative model uncovers underlying physics of neuronal activity in Ca imaging dataCalcium imaging has become a powerful alternative to electrophysiology for studying neuronal activity, offering spatial resolution and the ability to measure large populations of neurons in a minimally invasive manner. This technique has broad applications in neuroscience, neuroengineering, and medicine, enabling researchers to explore the relationship between neuron location and activity. Recent advancements in deep generative models (DGMs) have facilitated the modeling of neuronal population dynamics, uncovering latent representations that provide insights into behavior prediction and neuronal variance. However, these models often rely on spike inference algorithms and primarily focus on population-level dynamics, limiting their applicability for single-neuron analyses. To address this gap, we propose a novel framework for single-neuron representation learning using autoregressive variational autoencoders (AVAEs). Our approach embeds individual neurons' spatiotemporal signals into a reduced-dimensional space without the need for spike inference algorithms. The AVAE excels over traditional linear methods by generating more informative and discriminative latent representations, improving tasks such as visualization, clustering, and the understanding of neuronal activity. Additionally, the reconstruction performance of the AVAE outperforms the state of the art, demonstrating its ability to accurately recover the original fluorescence signal from the learned representation. Using realistic simulations, we show that our model captures underlying physical properties and connectivity patterns, enabling it to distinguish between different firing and connectivity types. These findings position the AVAE as a versatile and powerful tool for advancing single-neuron analysis and lays the groundwork for future integration of multimodal single-cell datasets in neuroscience.

📰 "Pressure Field Reconstruction with SIREN: A Mesh-Free Approach for Image Velocimetry in Complex Noisy Environments"
arxiv.org/abs/2501.17987 #Physics.Flu-Dyn #Pressure #Matrix #Cs.Cv

arXiv logo
arXiv.orgPressure Field Reconstruction with SIREN: A Mesh-Free Approach for Image Velocimetry in Complex Noisy EnvironmentsThis work presents a novel approach for pressure field reconstruction from image velocimetry data using SIREN (Sinusoidal Representation Network), emphasizing its effectiveness as an implicit neural representation in noisy environments and its mesh-free nature. While we briefly assess two recently proposed methods - one-shot matrix-omnidirectional integration (OS-MODI) and Green's function integral (GFI) - the primary focus is on the advantages of the SIREN approach. The OS-MODI technique performs well in noise-free conditions and with structured meshes but struggles when applied to unstructured meshes with high aspect ratio. Similarly, the GFI method encounters difficulties due to singularities inherent from the Newtonian kernel. In contrast, the proposed SIREN approach is a mesh-free method that directly reconstructs the pressure field, bypassing the need for an intrinsic grid connectivity and, hence, avoiding the challenges associated with ill-conditioned cells and unstructured meshes. This provides a distinct advantage over traditional mesh-based methods. Moreover, it is shown that changes in the architecture of the SIREN can be used to filter out inherent noise from velocimetry data. This work positions SIREN as a robust and versatile solution for pressure reconstruction, particularly in noisy environments characterized by the absence of mesh structure, opening new avenues for innovative applications in this field.

📰 "Exploring Biologically Inspired Mechanisms of Adversarial Robustness"
arxiv.org/abs/2405.00679 #Q-Bio.Nc #Dynamics #Cs.Ai #Cs.Ne #Cell

arXiv logo
arXiv.orgExploring Biologically Inspired Mechanisms of Adversarial RobustnessBackpropagation-optimized artificial neural networks, while precise, lack robustness, leading to unforeseen behaviors that affect their safety. Biological neural systems do solve some of these issues already. Unlike artificial models, biological neurons adjust connectivity based on neighboring cell activity. Understanding the biological mechanisms of robustness can pave the way towards building trust worthy and safe systems. Robustness in neural representations is hypothesized to correlate with the smoothness of the encoding manifold. Recent work suggests power law covariance spectra, which were observed studying the primary visual cortex of mice, to be indicative of a balanced trade-off between accuracy and robustness in representations. Here, we show that unsupervised local learning models with winner takes all dynamics learn such power law representations, providing upcoming studies a mechanistic model with that characteristic. Our research aims to understand the interplay between geometry, spectral properties, robustness, and expressivity in neural representations. Hence, we study the link between representation smoothness and spectrum by using weight, Jacobian and spectral regularization while assessing performance and adversarial robustness. Our work serves as a foundation for future research into the mechanisms underlying power law spectra and optimally smooth encodings in both biological and artificial systems. The insights gained may elucidate the mechanisms that realize robust neural networks in mammalian brains and inform the development of more stable and reliable artificial systems.