Tootfinder

TIL about the Littorina transgression, and what could well be a feature of sea level rise we should know about…
Rapid sea-level rise during the first phase of the Littorina transgression in the western Baltic Sea - NASA/ADS
https://ui.adsabs.harvard.edu/abs/2023

Large language models surpass human experts in predicting neuroscience results https://arxiv.org/abs/2403.03230 Well, let LLMs predict results with sensory substitution training then.

Large language models surpass human experts in predicting neuroscience results
Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offer a solution. LLMs trained on the vast scientific literature could potentially integrate noisy yet interrelated findings to forecast novel results better than human experts. To evaluate this possibility, we created BrainBench, a forward-looking benchmark for predicting neuroscience results. We find that LLMs surpass e…

✒️ Evaluating Large Language Models for Material Selection
(... actually a very nice example of an evaluation project for a generative AI)
#ai

Evaluating Large Language Models for Material Selection
Material selection is a crucial step in conceptual design due to its significant impact on the functionality, aesthetics, manufacturability, and sustainability impact of the final product. This study investigates the use of Large Language Models (LLMs) for material selection in the product design process and compares the performance of LLMs against expert choices for various design scenarios. By collecting a dataset of expert material preferences, the study provides a basis for evaluating how w…

This https://arxiv.org/abs/2403.10479 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Complete equational theories for classical and quantum Gaussian relations
We give generators and relations for the hypergraph props of Gaussian relations and positive affine Lagrangian relations. The former extends Gaussian probabilistic processes by completely-uninformative priors, and the latter extends Gaussian quantum mechanics with infinitely-squeezed states. These presentations are given by adding a generator to the presentation of real affine relations and of real affine Lagrangian relations which freely codiscards effects, as well as certain rotations. The …

This https://arxiv.org/abs/2404.07122 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Driver Attention Tracking and Analysis
We propose a novel method to estimate a driver's points-of-gaze using a pair of ordinary cameras mounted on the windshield and dashboard of a car. This is a challenging problem due to the dynamics of traffic environments with 3D scenes of unknown depths. This problem is further complicated by the volatile distance between the driver and the camera system. To tackle these challenges, we develop a novel convolutional network that simultaneously analyzes the image of the scene and the image of the…

Combinatorics of higher-categorical diagrams
Amar Hadzihasanovic
https://arxiv.org/abs/2404.07273 https://arxiv.org/pdf/2404.07273

Combinatorics of higher-categorical diagrams
This is a book on higher-categorical diagrams, including pasting diagrams. It aims to provide a thorough and modern reference on the subject, collecting, revisiting and expanding results scattered across the literature, informed by recent advances and practical experience with higher-dimensional diagram rewriting. We approach the subject as a kind of directed combinatorial topology: a diagram is a map from a "directed cell complex", encoded combinatorially as a face poset together with orient…

Measurement of atmospheric #neutrino oscillation parameters using #ConvolutionalNeuralNetworks with 9.3 years of data in #IceCube DeepCore: https://arxiv.org/abs/2405.02163 -> Measurement of atmospheric neutrino oscillation parameters using convolutional neural networks with high precision: https://icecube.wisc.edu/news/research/2024/05/measurement-of-atmospheric-neutrino-oscillation-parameters-using-convolutional-neural-networks-with-high-precision/

This https://arxiv.org/abs/2403.05386 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Sound and Complete Witnesses for Template-based Verification of LTL Properties on Polynomial Programs
We study the classical problem of verifying programs with respect to formal specifications given in the linear temporal logic (LTL). We first present novel \emph{sound and complete} witnesses for LTL verification over imperative programs. Our witnesses are applicable to both universal (all runs) and existential (some run) settings. We then consider LTL formulas in which atomic propositions can be polynomial constraints and turn our focus to polynomial arithmetic programs, i.e. programs in which…

This https://arxiv.org/abs/2404.07135 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability
Text-to-Vis is an emerging task in the natural language processing (NLP) area that aims to automatically generate data visualizations from natural language questions (NLQs). Despite their progress, existing text-to-vis models often heavily rely on lexical matching between words in the questions and tokens in data schemas. This overreliance on lexical matching may lead to a diminished level of model robustness against input variations. In this study, we thoroughly examine the robustness of curre…

Optimizing Risk-averse Human-AI Hybrid Teams
Andrew Fuchs, Andrea Passarella, Marco Conti
https://arxiv.org/abs/2403.08386 https://ar…

Optimizing Risk-averse Human-AI Hybrid Teams
We anticipate increased instances of humans and AI systems working together in what we refer to as a hybrid team. The increase in collaboration is expected as AI systems gain proficiency and their adoption becomes more widespread. However, their behavior is not error-free, making hybrid teams a very suitable solution. As such, we consider methods for improving performance for these teams of humans and AI systems. For hybrid teams, we will refer to both the humans and AI systems as agents. To im…

✒️ Evaluating Large Language Models for Material Selection
(... actually a very nice example of an evaluation project for a generative AI)
#ai

Evaluating Large Language Models for Material Selection
Material selection is a crucial step in conceptual design due to its significant impact on the functionality, aesthetics, manufacturability, and sustainability impact of the final product. This study investigates the use of Large Language Models (LLMs) for material selection in the product design process and compares the performance of LLMs against expert choices for various design scenarios. By collecting a dataset of expert material preferences, the study provides a basis for evaluating how w…

This https://arxiv.org/abs/2305.04656 has been replaced.
link: https://scholar.google.com/scholar?q=a

Preservation theorems for Tarski's relation algebra
We investigate a number of semantically defined fragments of Tarski's algebra of binary relations, including the function-preserving fragment. We address the question whether they are generated by a finite set of operations. We obtain several positive and negative results along these lines. Specifically, the homomorphism-safe fragment is finitely generated (both over finite and over arbitrary structures). The function-preserving fragment is not finitely generated (and, in fact, not expressible …

This https://arxiv.org/abs/2404.06859 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Multi-Label Continual Learning for the Medical Domain: A Novel Benchmark
Multi-label image classification in dynamic environments is a problem that poses significant challenges. Previous studies have primarily focused on scenarios such as Domain Incremental Learning and Class Incremental Learning, which do not fully capture the complexity of real-world applications. In this paper, we study the problem of classification of medical imaging in the scenario termed New Instances \& New Classes, which combines the challenges of both new class arrivals and domain shifts in…

This https://arxiv.org/abs/2212.02444 has been replaced.
link: https://scholar.google.com/scholar?q=a

Homotopy type theory as internal languages of diagrams of $\infty$-logoses
We show that certain diagrams of $\infty$-logoses are reconstructed in internal languages of their oplax limits via lex, accessible modalities, which enables us to use plain homotopy type theory to reason about not only a single $\infty$-logos but also a diagram of $\infty$-logoses. This also provides a higher dimensional version of Sterling's synthetic Tait computability -- a type theory for higher dimensional logical relations. To prove the main result, we establish a precise correspondence b…

This https://arxiv.org/abs/2403.04403 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Conjugate operators for transparent, explorable research outputs
Charts, figures, and text derived from data play an important role in decision making, from data-driven policy development to day-to-day choices informed by online articles. Making sense of, or fact-checking, outputs means understanding how they relate to the underlying data. Even for domain experts with access to the source code and data sets, this poses a significant challenge. In this paper we introduce a new program analysis framework which supports interactive exploration of fine-grained I…

This https://arxiv.org/abs/2404.07108 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

From Model-centered to Human-Centered: Revision Distance as a Metric for Text Evaluation in LLMs-based Applications
Evaluating large language models (LLMs) is fundamental, particularly in the context of practical applications. Conventional evaluation methods, typically designed primarily for LLM development, yield numerical scores that ignore the user experience. Therefore, our study shifts the focus from model-centered to human-centered evaluation in the context of AI-powered writing assistance applications. Our proposed metric, termed ``Revision Distance,'' utilizes LLMs to suggest revision edits that mimi…

Perennial Semantic Data Terms of Use for Decentralized Web
Rui Zhao, Jun Zhao
https://arxiv.org/abs/2403.07587 https://arxiv.org/pdf/…

Perennial Semantic Data Terms of Use for Decentralized Web
In today's digital landscape, the Web has become increasingly centralized, raising concerns about user privacy violations. Decentralized Web architectures, such as Solid, offer a promising solution by empowering users with better control over their data in their personal `Pods'. However, a significant challenge remains: users must navigate numerous applications to decide which application can be trusted with access to their data Pods. This often involves reading lengthy and complex Terms of Use…

This https://arxiv.org/abs/2301.10037 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Hyper Hoare Logic: (Dis-)Proving Program Hyperproperties (extended version)
Hoare logics are proof systems that allow one to formally establish properties of computer programs. Traditional Hoare logics prove properties of individual program executions (such as functional correctness). Hoare logic has been generalized to prove also properties of multiple executions of a program (so-called hyperproperties, such as determinism or non-interference). These program logics prove the absence of (bad combinations of) executions. On the other hand, program logics similar to Hoar…

This https://arxiv.org/abs/2404.06842 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching
Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Cha}nnel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif chann…

This https://arxiv.org/abs/2205.00386 has been replaced.
link: https://scholar.google.com/scholar?q=a

Internal sums for synthetic fibered $(\infty,1)$-categories
We give structural results about bifibrations of (internal) $(\infty,1)$-categories with internal sums. This includes a higher version of Moens' Theorem, characterizing cartesian bifibrations with extensive aka stable and disjoint internal sums over lex bases as Artin gluings of lex functors. We also treat a generalized version of Moens' Theorem due to Streicher which does not require the Beck--Chevalley condition. Furthermore, we show that also in this setting the Moens fibrations can be c…

This https://arxiv.org/abs/2403.05417 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

We Know I Know You Know; Choreographic Programming With Multicast and Multiply Located Values
Concurrent distributed systems are notoriously difficult to construct and reason about. Choreographic programming is a recent paradigm that describes a distributed system in a single global program called a choreography. Choreographies simplify reasoning about distributed systems and can ensure deadlock freedom by static analysis. In previous choreographic programming languages, each value is located at a single party, and the programmer is expected to insert special untyped "select" operations…

This https://arxiv.org/abs/2404.06948 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

MetaCheckGPT -- A Multi-task Hallucination Detection Using LLM Uncertainty and Meta-models
This paper presents our winning solution for the SemEval-2024 Task 6 competition. We propose a meta-regressor framework of large language models (LLMs) for model evaluation and integration that achieves the highest scores on the leader board. Our approach leverages uncertainty signals present in a diverse basket of LLMs to detect hallucinations more robustly.

Perennial Semantic Data Terms of Use for Decentralized Web
Rui Zhao, Jun Zhao
https://arxiv.org/abs/2403.07587 https://arxiv.org/pdf/…

Perennial Semantic Data Terms of Use for Decentralized Web
In today's digital landscape, the Web has become increasingly centralized, raising concerns about user privacy violations. Decentralized Web architectures, such as Solid, offer a promising solution by empowering users with better control over their data in their personal `Pods'. However, a significant challenge remains: users must navigate numerous applications to decide which application can be trusted with access to their data Pods. This often involves reading lengthy and complex Terms of Use…

This https://arxiv.org/abs/2205.02142 has been replaced.
link: https://scholar.google.com/scholar?q=a

The Sup Connective in IMALL: A Categorical Semantics
We explore a proof language for intuitionistic multiplicative additive linear logic, incorporating the sup connective that introduces additive pairs with a probabilistic elimination, and sum and scalar products within the proof-terms. We provide an abstract characterization of the language, revealing that any symmetric monoidal closed category with biproducts and a monomorphism from the semiring of scalars to the semiring Hom(I,I) is suitable for the job. Leveraging the binary biproducts, we de…

This https://arxiv.org/abs/2404.06710 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera
One of the most critical factors in achieving sharp Novel View Synthesis (NVS) using neural field methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) is the quality of the training images. However, Conventional RGB cameras are susceptible to motion blur. In contrast, neuromorphic cameras like event and spike cameras inherently capture more comprehensive temporal information, which can provide a sharp representation of the scene as additional training data. Recent methods…

This https://arxiv.org/abs/2008.11180 has been replaced.
link: https://scholar.google.com/scholar?q=a

Weakly globular double categories and weak units
Weakly globular double categories are a model of weak $2$-categories based on the notion of weak globularity, and they are known to be suitably equivalent to Tamsamani $2$-categories. Fair $2$-categories, introduced by J. Kock, model weak $2$-categories with strictly associative compositions and weak unit laws. In this paper we establish a direct comparison between weakly globular double categories and fair $2$-categories and prove they are equivalent after localisation with respect to the $2$-…

This https://arxiv.org/abs/2312.09982 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

ACPO: AI-Enabled Compiler-Driven Program Optimization
The key to performance optimization of a program is to decide correctly when a certain transformation should be applied by a compiler. This is an ideal opportunity to apply machine-learning models to speed up the tuning process; while this realization has been around since the late 90s, only recent advancements in ML enabled a practical application of ML to compilers as an end-to-end framework. This paper presents ACPO: \textbf{\underline{A}}I-Enabled \textbf{\underline{C}}ompiler-driven \tex…

This https://arxiv.org/abs/2404.06001 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Privacy Preserving Prompt Engineering: A Survey
Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models and their sizes. As a result, the sizes of these models have notably expanded in recent years, persuading researchers to adopt the term large language models (LLMs) to characterize the larger-sized PLMs. The increased size is accompanied by a distinct capabil…

Relevance Score: A Landmark-Like Heuristic for Planning
Oliver Kim, Mohan Sridharan
https://arxiv.org/abs/2403.07510 https://arxiv.or…

Relevance Score: A Landmark-Like Heuristic for Planning
Landmarks are facts or actions that appear in all valid solutions of a planning problem. They have been used successfully to calculate heuristics that guide the search for a plan. We investigate an extension to this concept by defining a novel "relevance score" that helps identify facts or actions that appear in most but not all plans to achieve any given goal. We describe an approach to compute this relevance score and use it as a heuristic in the search for a plan. We experimentally compare t…

This https://arxiv.org/abs/2312.12026 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

An Approximate Skolem Function Counter
One approach to probabilistic inference involves counting the number of models of a given Boolean formula. Here, we are interested in inferences involving higher-order objects, i.e., functions. We study the following task: Given a Boolean specification between a set of inputs and outputs, count the number of functions of inputs such that the specification is met. Such functions are called Skolem functions. We are motivated by the recent development of scalable approaches to Boolean function s…

This https://arxiv.org/abs/2404.06564 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity. Mamba-based models, with their superior long-range modeling and linear efficiency, have garnered substantial attention. This study pioneers the application of Mamba to multi-class unsupervised anomaly detection, presenting MambaAD, which consists of a pre-trained encod…

This https://arxiv.org/abs/2311.18638 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Group actions on monoidal triangulated categories and Balmer spectra
Let $G$ be a group acting on a left or right rigid monoidal triangulated category ${\mathbf K}$ which has a Noetherian Balmer spectrum. We prove that the Balmer spectrum of the crossed product category of ${\mathbf K}$ by $G$ is homeomorphic to the space of $G$-prime ideals of ${\mathbf K}$, give a concrete description of this space, and classify the $G$-invariant thick ideals of ${\mathbf K}$. Under some additional technical conditions, we prove that the Balmer spectrum of the equivariantizati…

This https://arxiv.org/abs/2304.15000 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Quantum Control Machine: The Limits of Control Flow in Quantum Programming
Quantum algorithms for tasks such as factorization, search, and simulation rely on control flow such as branching and iteration that depends on the value of data in superposition. High-level programming abstractions for control flow, such as switches, loops, and higher-order functions, are ubiquitous in classical languages. By contrast, many quantum languages do not provide high-level abstractions for control flow in superposition, and instead require the use of hardware-level logic gates to im…

This https://arxiv.org/abs/2404.05892 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture. Our architectural design advancements include multi-headed matrix-valued states and a dynamic recurrence mechanism that improve expressivity while maintaining the inference efficiency characteristics of RNNs. We introduce a new multilingual corpus with 1.12 trillion tokens and a fast tokenizer based on greedy matching for enhanced multilinguality. We trained four Eagle models, ranging fr…

Relevance Score: A Landmark-Like Heuristic for Planning
Oliver Kim, Mohan Sridharan
https://arxiv.org/abs/2403.07510 https://arxiv.or…

Relevance Score: A Landmark-Like Heuristic for Planning
Landmarks are facts or actions that appear in all valid solutions of a planning problem. They have been used successfully to calculate heuristics that guide the search for a plan. We investigate an extension to this concept by defining a novel "relevance score" that helps identify facts or actions that appear in most but not all plans to achieve any given goal. We describe an approach to compute this relevance score and use it as a heuristic in the search for a plan. We experimentally compare t…

This https://arxiv.org/abs/2306.10707 has been replaced.
link: https://scholar.google.com/scholar?q=a

Partial-order Checking with Unfolding for Linear Temporal Properties
Unfolding can tackle the path-explosion problem caused by concurrency. Traditional unfolding generation faces an NP-complete problem when adding events to the unfolding structure, which also exists in the case of verifying linear temporal logic (LTL). The reason is that it is necessary to enumerate possible concurrent event combinations after adding an event. Many state-of-the-art methods optimally explore unfolding-based structure (called event structure) by a tree-like structure, which should…

This https://arxiv.org/abs/2404.06351 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention
Predicting the trajectories of road agents is essential for autonomous driving systems. The recent mainstream methods follow a static paradigm, which predicts the future trajectory by using a fixed duration of historical frames. These methods make the predictions independently even at adjacent time steps, which leads to potential instability and temporal inconsistency. As successive time steps have largely overlapping historical frames, their forecasting should have intrinsic correlation, such …

This https://arxiv.org/abs/2307.13201 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Eilenberg-Moore categories and quiver representations of monads and comonads
We consider representations of quivers taking values in monads or comonads over a Grothendieck category $\mathcal C$. We treat these as scheme like objects whose ``structure sheaf'' consists of monads or comonads. By using systems of adjoint functors between Eilenberg-Moore categories, we obtain a categorical framework of modules over monad quivers, and of comodules over comonad quivers. Our main objective is to give conditions for these to be Grothendieck categories, which play the role of non…

This https://arxiv.org/abs/2404.05449 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

RoT: Enhancing Large Language Models with Reflection on Search Trees
Large language models (LLMs) have demonstrated impressive capability in reasoning and planning when integrated with tree-search-based prompting methods. However, since these methods ignore the previous search experiences, they often make the same mistakes in the search process. To address this issue, we introduce Reflection on search Trees (RoT), an LLM reflection framework designed to improve the performance of tree-search-based prompting methods. It uses a strong LLM to summarize guidelines f…

This https://arxiv.org/abs/2306.03045 has been replaced.
link: https://scholar.google.com/scholar?q=a

Designing Equilibria in Concurrent Games with Social Welfare and Temporal Logic Constraints
In game theory, mechanism design is concerned with the design of incentives so that a desired outcome of the game can be achieved. In this paper, we explore the concept of equilibrium design, where incentives are designed to obtain a desirable equilibrium that satisfies a specific temporal logic property. Our study is based on a framework where system specifications are represented as temporal logic formulae, games as quantitative concurrent game structures, and players' goals as mean-payoff ob…

Automatic Generation of Python Programs Using Context-Free Grammars
Kamel Yamani, Marwa Na\"ir, Riyadh Baghdadi
https://arxiv.org/abs/2403.06503 https…

Automatic Generation of Python Programs Using Context-Free Grammars
In recent years, data has emerged as the new gold, serving as a powerful tool for creating intelligent systems. However, procuring high-quality data remains challenging, especially for code. To address this, we developed TinyPy Generator, a tool that generates random Python programs using a context-free grammar. The generated programs are guaranteed to be correct by construction. Our system uses custom production rules (in the Backus-Naur Form (BNF) format) to recursively generate code. This al…

On the stochastics of human and artificial creativity
Solve S{\ae}b{\o}, Helge Brovold
https://arxiv.org/abs/2403.06996 https://arxiv…

On the stochastics of human and artificial creativity
What constitutes human creativity, and is it possible for computers to exhibit genuine creativity? We argue that achieving human-level intelligence in computers, or so-called Artificial General Intelligence, necessitates attaining also human-level creativity. We contribute to this discussion by developing a statistical representation of human creativity, incorporating prior insights from stochastic theory, psychology, philosophy, neuroscience, and chaos theory. This highlights the stochastic na…

This https://arxiv.org/abs/2404.06177 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Uncertainty-aware Evidential Fusion-based Learning for Semi-supervised Medical Image Segmentation
Although the existing uncertainty-based semi-supervised medical segmentation methods have achieved excellent performance, they usually only consider a single uncertainty evaluation, which often fails to solve the problem related to credibility completely. Therefore, based on the framework of evidential deep learning, this paper integrates the evidential predictive results in the cross-region of mixed and original samples to reallocate the confidence degree and uncertainty measure of each voxel,…

This https://arxiv.org/abs/2204.00938 has been replaced.
link: https://scholar.google.com/scholar?q=a

Two-sided cartesian fibrations of synthetic $(\infty,1)$-categories
Within the framework of Riehl-Shulman's synthetic $(\infty,1)$-category theory, we present a theory of two-sided cartesian fibrations. Central results are several characterizations of the two-sidedness condition à la Chevalley, Gray, Street, and Riehl-Verity, a two-sided Yoneda Lemma, as well as the proof of several closure properties. Along the way, we also define and investigate a notion of fibered or sliced fibration which is used later to develop the two-sided case in a modular fashion. …

This https://arxiv.org/abs/2404.04067 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

CLUE: A Clinical Language Understanding Evaluation for LLMs
Large Language Models (LLMs) have shown the potential to significantly contribute to patient care, diagnostics, and administrative processes. Emerging biomedical LLMs address healthcare-specific challenges, including privacy demands and computational constraints. However, evaluation of these models has primarily been limited to non-clinical tasks, which do not reflect the complexity of practical clinical applications. Additionally, there has been no thorough comparison between biomedical and ge…

This https://arxiv.org/abs/2301.06136 has been replaced.
link: https://scholar.google.com/scholar?q=a

Quantitative Verification with Neural Networks
We present a data-driven approach to the quantitative verification of probabilistic programs and stochastic dynamical models. Our approach leverages neural networks to compute tight and sound bounds for the probability that a stochastic process hits a target condition within finite time. This problem subsumes a variety of quantitative verification questions, from the reachability and safety analysis of discrete-time stochastic dynamical models, to the study of assertion-violation and terminatio…

Improving Memory Dependence Prediction with Static Analysis
Luke Panayi, Rohan Gandhi, Jim Whittaker, Vassilios Chouliaras, Martin Berger, Paul Kelly
https://arxiv.org/abs/2403.08056

Improving Memory Dependence Prediction with Static Analysis
This paper explores the potential of communicating information gained by static analysis from compilers to Out-of-Order (OoO) machines, focusing on the memory dependence predictor (MDP). The MDP enables loads to issue without all in-flight store addresses being known, with minimal memory order violations. We use LLVM to find loads with no dependencies and label them via their opcode. These labelled loads skip making lookups into the MDP, improving prediction accuracy by reducing false dependenc…

On the stochastics of human and artificial creativity
Solve S{\ae}b{\o}, Helge Brovold
https://arxiv.org/abs/2403.06996 https://arxiv…

On the stochastics of human and artificial creativity
What constitutes human creativity, and is it possible for computers to exhibit genuine creativity? We argue that achieving human-level intelligence in computers, or so-called Artificial General Intelligence, necessitates attaining also human-level creativity. We contribute to this discussion by developing a statistical representation of human creativity, incorporating prior insights from stochastic theory, psychology, philosophy, neuroscience, and chaos theory. This highlights the stochastic na…

This https://arxiv.org/abs/2404.05426 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Test-Time Zero-Shot Temporal Action Localization
Zero-Shot Temporal Action Localization (ZS-TAL) seeks to identify and locate actions in untrimmed videos unseen during training. Existing ZS-TAL methods involve fine-tuning a model on a large amount of annotated training data. While effective, training-based ZS-TAL approaches assume the availability of labeled data for supervised learning, which can be impractical in some applications. Furthermore, the training process naturally induces a domain bias into the learned model, which may adversely …

This https://arxiv.org/abs/2210.05344 has been replaced.
link: https://scholar.google.com/scholar?q=a

From Basic Proof-theoretic Validity to Base-extension Semantics for Intuitionistic Propositional Logic
Proof-theoretic semantics (P-tS) is the approach to meaning in logic based on proof (as opposed to truth). There are two major approaches to P-tS: proof-theor\-etic validity (P-tV) and base-extension semantics (B-eS). The former is a semantics of arguments, and the latter is a semantics of logical constants. This paper demonstrates that the B-eS for intuitionistic propositional logic (IPL) encapsulates the declarative content of a basic version of P-tV. Such relationships have been considered b…

This https://arxiv.org/abs/2404.03028 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models
Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly with a small number of examples; in instruction inference, LMs are presented with in-context examples and are then prompted to generate a natural language task description before making predictions. Each of these procedures may be thought of as invoking a different form of rea…

Higher Witt Groups for 2-Categories I: Centralizers
Hao Xu
https://arxiv.org/abs/2403.07768 https://arxiv.org/pdf/2403.07768

Higher Witt Groups for 2-Categories I: Centralizers
In this article, we investigate monoidal, braided, sylleptic centralizers of monoidal, braided, sylleptic 2-functors. We specifically focus on multifusion 2-categories and show that monoidal, braided, sylleptic centralizers are multifusion again, via studying the corresponding enveloping algebras. We provide a characterization of the non-degeneracy condition for monoidal, braided, and sylleptic fusion 2-categories, via vanishing of their centers. Applying Double Centralizer Theorems, we establi…

Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
Xuejing Zheng, Chao Yu
https://arxiv.org/abs/2403.07005 https://

Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL) problems using Reward Machines (RMs) to specify the reward functions such that the prior knowledge of high-level events in a task can be leveraged to facilitate the learning efficiency. Unlike the existing work that RMs have been incorporated into MARL for task decomposition and policy learning in relatively simple domains or with an assumption of independencies among the agents, we present Multi-Agent Reinforceme…

A Minority of C Objects Account for the Majority of Allocation CPU Time
Eugene Darashkevich, Roman Rusyaev, Roman Korostinskiy, Yegor Bugayenko
https://arxiv.org/abs/2403.06695 …

A Minority of C++ Objects Account for the Majority of Allocation CPU Time
In C++, an object can be allocated in static memory, on the stack, or on the heap, where the latter is by the order of magnitude more expensive operation, performance wise, than the first two. However, it is not clear how much overall performance loss may be attributed to the use of on-heap objects in C++ applications. This study aims to fill this gap by analyzing object allocation practices in open-source C++ code, investigating the frequency of stack and heap allocations using real-time dynam…

This https://arxiv.org/abs/2404.05392 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos
In this paper, we introduce T-DEED, a Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in sports videos. T-DEED addresses multiple challenges in the task, including the need for discriminability among frame representations, high output temporal resolution to maintain prediction precision, and the necessity to capture information at different temporal scales to handle events with varying dynamics. It tackles these challenges through its specifically designed architec…

This https://arxiv.org/abs/2103.02343 has been replaced.
link: https://scholar.google.com/scholar?q=a

Provability in BI's Sequent Calculus is Decidable
Warning: This paper contains a mistake, rendering the proof of the main theorem invalid. The logic of Bunched Implications (BI) combines both additive and multiplicative connectives, which include two primitive intuitionistic implications. As a consequence, contexts in the sequent presentation are not lists, nor multisets, but rather tree-like structures called bunches. This additional complexity notwithstanding, the logic has a well-behaved metatheory admitting all the familiar forms of semant…

This https://arxiv.org/abs/2404.01140 has been replaced.
link: https://scholar.google.com/scholar?q=a

KoCoNovel: Annotated Dataset of Character Coreference in Korean Novels
In this paper, we present KoCoNovel, a novel character coreference dataset derived from Korean literary texts, complete with detailed annotation guidelines. Comprising 178K tokens from 50 modern and contemporary novels, KoCoNovel stands as one of the largest public coreference resolution corpora in Korean, and the first to be based on literary texts. KoCoNovel offers four distinct versions to accommodate a wide range of literary coreference analysis needs. These versions are designed to support…

Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
Xuejing Zheng, Chao Yu
https://arxiv.org/abs/2403.07005 https://

Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL) problems using Reward Machines (RMs) to specify the reward functions such that the prior knowledge of high-level events in a task can be leveraged to facilitate the learning efficiency. Unlike the existing work that RMs have been incorporated into MARL for task decomposition and policy learning in relatively simple domains or with an assumption of independencies among the agents, we present Multi-Agent Reinforceme…

Flexible Non-intrusive Dynamic Instrumentation for WebAssembly
Ben L. Titzer, Elizabeth Gilbert, Bradley Wei Jie Teo, Yash Anand, Kazuyuki Takayama, Heather Miller
https://arxiv.org/abs/2403.07973

Flexible Non-intrusive Dynamic Instrumentation for WebAssembly
A key strength of managed runtimes over hardware is the ability to gain detailed insight into the dynamic execution of programs with instrumentation. Analyses such as code coverage, execution frequency, tracing, and debugging, are all made easier in a virtual setting. As a portable, low-level bytecode, WebAssembly offers inexpensive in-process sandboxing with high performance. Yet to date, Wasm engines have not offered much insight into executing programs, supporting at best bytecode-level step…

This https://arxiv.org/abs/2404.04562 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Diffusion Time-step Curriculum for One Image to 3D Generation
Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a \textbf{single} image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction of student 3D models. Despite their remarkable success, SDS-based methods often encounter geometric artifacts and texture saturation. We find out the crux is the overlooked indiscriminate treatment of diffusion time-steps during optimization: it unreasonably…

This https://arxiv.org/abs/2309.16824 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

The fork and its role in unification of closure algebras
We consider the two-pronged fork frame $F$ and the variety $\mathbf{Eq}(B_F)$ generated by its dual closure algebra $B_F$. We describe the finite projective algebras in $\mathbf{Eq}(B_F)$ and give a purely semantic proof that unification in $\mathbf{Eq}(B_F)$ is finitary and not unitary.

This https://arxiv.org/abs/2404.01019 has been replaced.
link: https://scholar.google.com/scholar?q=a

Source-Aware Training Enables Knowledge Attribution in Language Models
Large language models (LLMs) learn a vast amount of knowledge during pretraining, but they are often oblivious to the source(s) of such knowledge. We investigate the problem of intrinsic source citation, where LLMs are required to cite the pretraining source supporting a generated response. Intrinsic source citation can enhance LLM transparency, interpretability, and verifiability. To give LLMs such ability, we explore source-aware training -- a post pretraining recipe that involves (i) trainin…

Convergence of Some Convex Message Passing Algorithms to a Fixed Point
Vaclav Voracek, Tomas Werner
https://arxiv.org/abs/2403.07004 https://

Convergence of Some Convex Message Passing Algorithms to a Fixed Point
A popular approach to the MAP inference problem in graphical models is to minimize an upper bound obtained from a dual linear programming or Lagrangian relaxation by (block-)coordinate descent. Examples of such algorithms are max-sum diffusion and sequential tree-reweighted message passing. Convergence properties of these methods are currently not fully understood. They have been proved to converge to the set characterized by local consistency of active constraints, with unknown convergence rat…

Deriving Dependently-Typed OOP from First Principles - Extended Version with Additional Appendices
David Binder, Ingo Skupin, Tim S\"uberkr\"ub, Klaus Ostermann
https://arxiv.org/abs/2403.06707

Deriving Dependently-Typed OOP from First Principles - Extended Version with Additional Appendices
The expression problem describes how most types can easily be extended with new ways to produce the type or new ways to consume the type, but not both. When abstract syntax trees are defined as an algebraic data type, for example, they can easily be extended with new consumers, such as print or eval, but adding a new constructor requires the modification of all existing pattern matches. The expression problem is one way to elucidate the difference between functional or data-oriented programs (e…

This https://arxiv.org/abs/2209.13725 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the Descriptive Complexity of Groups without Abelian Normal Subgroups
In this paper, we explore the descriptive complexity theory of finite groups by examining the power of the second Ehrenfeucht-Fraïssé bijective pebble game in Hella's (Ann. Pure Appl. Log., 1989) heirarchy. This is a Spoiler-Duplicator game in which Spoiler can place up to two pebbles each round. While it trivially solves graph isomorphism, it may be nontrivial for finite groups, and other ternary relational structures. We first provide a novel generalization of Weisfeiler-Leman (WL) coloring…

This https://arxiv.org/abs/2404.03936 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Deep Learning for Satellite Image Time Series Analysis: A Review
Earth observation (EO) satellite missions have been providing detailed images about the state of the Earth and its land cover for over 50 years. Long term missions, such as NASA's Landsat, Terra, and Aqua satellites, and more recently, the ESA's Sentinel missions, record images of the entire world every few days. Although single images provide point-in-time data, repeated images of the same area, or satellite image time series (SITS) provide information about the changing state of vegetation an…

This https://arxiv.org/abs/2404.00511 has been replaced.
link: https://scholar.google.com/scholar?q=a

MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models
This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognition and Multimodal Emotion Cause Extraction (MER-MCE) framework that integrates text, audio, and visual modalities using specialized emotion encoders. Our approach sets itself apart from top-performing teams by leveraging modality-specific features for enhanced emotion understanding and causality inference. Experiment…

This https://arxiv.org/abs/2204.06068 has been replaced.
link: https://scholar.google.com/scholar?q=a

Encodability Criteria for Quantum Based Systems
Quantum based systems are a relatively new research area for that different modelling languages including process calculi are currently under development. Encodings are often used to compare process calculi. Quality criteria are used then to rule out trivial or meaningless encodings. In this new context of quantum based systems, it is necessary to analyse the applicability of these quality criteria and to potentially extend or adapt them. As a first step, we test the suitability of classical cr…

Convergence of Some Convex Message Passing Algorithms to a Fixed Point
Vaclav Voracek, Tomas Werner
https://arxiv.org/abs/2403.07004 https://

Convergence of Some Convex Message Passing Algorithms to a Fixed Point
A popular approach to the MAP inference problem in graphical models is to minimize an upper bound obtained from a dual linear programming or Lagrangian relaxation by (block-)coordinate descent. Examples of such algorithms are max-sum diffusion and sequential tree-reweighted message passing. Convergence properties of these methods are currently not fully understood. They have been proved to converge to the set characterized by local consistency of active constraints, with unknown convergence rat…

Towards Fixed-Point Formats Determination for Faust Programs
Agathe HerrouGRAME, Florent de DinechinINSA Lyon, St\'ephane LetzGRAME, Yann Orlarey, Anastasia Volkova
https://arxiv.org/abs/2403.06527

Towards Fixed-Point Formats Determination for Faust Programs
Modern programmable digital signal processing relies on floating-point numbers for their ease of use. Fixed-point number formats have the potential to save resources and improve execution time, but realising this potential burdens the programmer with the need to define each format, at every step of the computation. This article reviews existing methods to automatically determine fixed-point formats, then describes and evaluates the prototype implementation of automatic fixed-point format determ…

This https://arxiv.org/abs/2404.03778 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincaré Ball
Hierarchy is a natural representation of semantic taxonomies, including the ones routinely used in image segmentation. Indeed, recent work on semantic segmentation reports improved accuracy from supervised training leveraging hierarchical label structures. Encouraged by these results, we revisit the fundamental assumptions behind that work. We postulate and then empirically verify that the reasons for the observed improvement in segmentation accuracy may be entirely unrelated to the use of the …

This https://arxiv.org/abs/2403.17645 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

DANCER: Entity Description Augmented Named Entity Corrector for Automatic Speech Recognition
End-to-end automatic speech recognition (E2E ASR) systems often suffer from mistranscription of domain-specific phrases, such as named entities, sometimes leading to catastrophic failures in downstream tasks. A family of fast and lightweight named entity correction (NEC) models for ASR have recently been proposed, which normally build on phonetic-level edit distance algorithms and have shown impressive NEC performance. However, as the named entity (NE) list grows, the problems of phonetic confu…

This https://arxiv.org/abs/2110.12924 has been replaced.
link: https://scholar.google.com/scholar?q=a

On Enumerating Short Projected Models
Propositional model enumeration, or All-SAT, is the task to record all models of a propositional formula. It is a key task in software and hardware verification, system engineering, and predicate abstraction, to mention a few. It also provides a means to convert a CNF formula into DNF, which is relevant in circuit design. While in some applications enumerating models multiple times causes no harm, in others avoiding repetitions is crucial. We therefore present two model enumeration algorithms, …

Online Continual Learning For Interactive Instruction Following Agents
Byeonghwi Kim, Minhyuk Seo, Jonghyun Choi
https://arxiv.org/abs/2403.07548 https://<…

Online Continual Learning For Interactive Instruction Following Agents
In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realistic since a robotic agent is supposed to learn the world continuously as it explores and perceives it. To take a step towards a more realistic embodied agent learning scenario, we propose two continual learning setups for embodied agents; learning new behaviors (Behavior Incremen…

This https://arxiv.org/abs/2404.01705 has been replaced.
link: https://scholar.google.com/scholar?q=a

Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model
High-resolution remotely sensed images pose a challenge for commonly used semantic segmentation methods such as Convolutional Neural Network (CNN) and Vision Transformer (ViT). CNN-based methods struggle with handling such high-resolution images due to their limited receptive field, while ViT faces challenges in handling long sequences. Inspired by Mamba, which adopts a State Space Model (SSM) to efficiently capture global semantic information, we propose a semantic segmentation framework for h…

This https://arxiv.org/abs/2403.16099 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

A Multi-Label Dataset of French Fake News: Human and Machine Insights
We present a corpus of 100 documents, OBSINFOX, selected from 17 sources of French press considered unreliable by expert agencies, annotated using 11 labels by 8 annotators. By collecting more labels than usual, by more annotators than is typically done, we can identify features that humans consider as characteristic of fake news, and compare them to the predictions of automated classifiers. We present a topic and genre analysis using Gate Cloud, indicative of the prevalence of satire-like text…

This https://arxiv.org/abs/2404.01446 has been replaced.
link: https://scholar.google.com/scholar?q=a

Finding Regions of Interest in Whole Slide Images Using Multiple Instance Learning
Whole Slide Images (WSI), obtained by high-resolution digital scanning of microscope slides at multiple scales, are the cornerstone of modern Digital Pathology. However, they represent a particular challenge to AI-based/AI-mediated analysis because pathology labeling is typically done at slide-level, instead of tile-level. It is not just that medical diagnostics is recorded at the specimen level, the detection of oncogene mutation is also experimentally obtained, and recorded by initiatives lik…

Online Continual Learning For Interactive Instruction Following Agents
Byeonghwi Kim, Minhyuk Seo, Jonghyun Choi
https://arxiv.org/abs/2403.07548 https://<…

Online Continual Learning For Interactive Instruction Following Agents
In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realistic since a robotic agent is supposed to learn the world continuously as it explores and perceives it. To take a step towards a more realistic embodied agent learning scenario, we propose two continual learning setups for embodied agents; learning new behaviors (Behavior Incremen…

Expiring opacity problems in parametric timed automata
\'Etienne Andr\'e, Engel Lefaucheux, Dylan Marinho
https://arxiv.org/abs/2403.07647 https://…

Expiring opacity problems in parametric timed automata
Information leakage can have dramatic consequences on the security of real-time systems. Timing leaks occur when an attacker is able to infer private behavior depending on timing information. In this work, we propose a definition of expiring timed opacity w.r.t. execution time, where a system is opaque whenever the attacker is unable to deduce the reachability of some private state solely based on the execution time; in addition, the secrecy is violated only when the private state was entered "…

This https://arxiv.org/abs/2403.11322 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
It is a notable trend to use Large Language Models (LLMs) to tackle complex tasks, e.g., tasks that require a sequence of actions and dynamic interaction with tools and external environments. In this paper, we propose StateFlow, a novel LLM-based task-solving paradigm that conceptualizes complex task-solving processes as state machines. In StateFlow, we distinguish between "process grounding" (via state and state transitions) and "sub-task solving" (through actions within a state), enhancing co…

This https://arxiv.org/abs/2403.19653 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Detecting Image Attribution for Text-to-Image Diffusion Models in RGB and Beyond
Modern text-to-image (T2I) diffusion models can generate images with remarkable realism and creativity. These advancements have sparked research in fake image detection and attribution, yet prior studies have not fully explored the practical and scientific dimensions of this task. In addition to attributing images to 12 state-of-the-art T2I generators, we provide extensive analyses on what inference stage hyperparameters and image modifications are discernible. Our experiments reveal that initi…

An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning
Weiwei Gu, Senquan Wang
https://arxiv.org/abs/2403.07566 https:…

An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning
Blood Glucose (BG) control involves keeping an individual's BG within a healthy range through extracorporeal insulin injections is an important task for people with type 1 diabetes. However,traditional patient self-management is cumbersome and risky. Recent research has been devoted to exploring individualized and automated BG control approaches, among which Deep Reinforcement Learning (DRL) shows potential as an emerging approach. In this paper, we use an exponential decay model of drug concen…

This https://arxiv.org/abs/2403.08295 has been replaced.
link: https://scholar.google.com/scholar?q=a

Gemma: Open Models Based on Gemini Research and Technology
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate strong performance across academic benchmarks for language understanding, reasoning, and safety. We release two sizes of models (2 billion and 7 billion parameters), and provide both pretrained and fine-tuned checkpoints. Gemma outperforms similarly sized open models on 11 out of 18 text-based tasks, and we present compre…

This https://arxiv.org/abs/2403.18551 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Attention Calibration for Disentangled Text-to-Image Personalization
Recent thrilling progress in large-scale text-to-image (T2I) models has unlocked unprecedented synthesis quality of AI-generated content (AIGC) including image generation, 3D and video composition. Further, personalized techniques enable appealing customized production of a novel concept given only several images as reference. However, an intriguing problem persists: Is it possible to capture multiple, novel concepts from one single reference image? In this paper, we identify that existing appr…

An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning
Weiwei Gu, Senquan Wang
https://arxiv.org/abs/2403.07566 https:…

An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning
Blood Glucose (BG) control involves keeping an individual's BG within a healthy range through extracorporeal insulin injections is an important task for people with type 1 diabetes. However,traditional patient self-management is cumbersome and risky. Recent research has been devoted to exploring individualized and automated BG control approaches, among which Deep Reinforcement Learning (DRL) shows potential as an emerging approach. In this paper, we use an exponential decay model of drug concen…

This https://arxiv.org/abs/2403.04814 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
We introduce Syntax-Aware Fill-In-the-Middle (SAFIM), a new benchmark for evaluating Large Language Models (LLMs) on the code Fill-in-the-Middle (FIM) task. This benchmark focuses on syntax-aware completions of program structures such as code blocks and conditional expressions, and includes 17,720 examples from multiple programming languages, sourced from recent code submissions after April 2022 to minimize data contamination. SAFIM provides a robust framework with various prompt designs and no…

This https://arxiv.org/abs/2403.17920 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

TC4D: Trajectory-Conditioned Text-to-4D Generation
Recent techniques for text-to-4D generation synthesize dynamic 3D scenes using supervision from pre-trained text-to-video models. However, existing representations for motion, such as deformation models or time-dependent neural representations, are limited in the amount of motion they can generate-they cannot synthesize motion extending far beyond the bounding box used for volume rendering. The lack of a more flexible motion model contributes to the gap in realism between 4D generation methods …

A New Random Forest Ensemble of Intuitionistic Fuzzy Decision Trees
Yingtao Ren, Xiaomin Zhu, Kaiyuan Bai, Runtong Zhang
https://arxiv.org/abs/2403.07363 h…

A New Random Forest Ensemble of Intuitionistic Fuzzy Decision Trees
Classification is essential to the applications in the field of data mining, artificial intelligence, and fault detection. There exists a strong need in developing accurate, suitable, and efficient classification methods and algorithms with broad applicability. Random forest is a general algorithm that is often used for classification under complex conditions. Although it has been widely adopted, its combination with diverse fuzzy theory is still worth exploring. In this paper, we propose the i…

This https://arxiv.org/abs/2402.12749 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Me LLaMA: Foundation Large Language Models for Medical Applications
Recent advancements in large language models (LLMs) such as ChatGPT and LLaMA have hinted at their potential to revolutionize medical applications, yet their application in clinical settings often reveals limitations due to a lack of specialized training on medical-specific data. In response to this challenge, this study introduces Me-LLaMA, a novel medical LLM family that includes foundation models - Me-LLaMA 13/70B, along with their chat-enhanced versions - Me-LLaMA 13/70B-chat, developed thr…

This https://arxiv.org/abs/2403.11111 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models
In this work, we show that synthetic data created by generative models is complementary to computer graphics (CG) rendered data for achieving remarkable generalization performance on diverse real-world scenes for 3D human pose and shape estimation (HPS). Specifically, we propose an effective approach based on recent diffusion models, termed HumanWild, which can effortlessly generate human images and corresponding 3D mesh annotations. We first collect a large-scale human-centric dataset with com…

A New Random Forest Ensemble of Intuitionistic Fuzzy Decision Trees
Yingtao Ren, Xiaomin Zhu, Kaiyuan Bai, Runtong Zhang
https://arxiv.org/abs/2403.07363 h…

A New Random Forest Ensemble of Intuitionistic Fuzzy Decision Trees
Classification is essential to the applications in the field of data mining, artificial intelligence, and fault detection. There exists a strong need in developing accurate, suitable, and efficient classification methods and algorithms with broad applicability. Random forest is a general algorithm that is often used for classification under complex conditions. Although it has been widely adopted, its combination with diverse fuzzy theory is still worth exploring. In this paper, we propose the i…

This https://arxiv.org/abs/2402.01115 has been replaced.
link: https://scholar.google.com/scholar?q=a

Interpretation of Intracardiac Electrograms Through Textual Representations
Understanding the irregular electrical activity of atrial fibrillation (AFib) has been a key challenge in electrocardiography. For serious cases of AFib, catheter ablations are performed to collect intracardiac electrograms (EGMs). EGMs offer intricately detailed and localized electrical activity of the heart and are an ideal modality for interpretable cardiac studies. Recent advancements in artificial intelligence (AI) has allowed some works to utilize deep learning frameworks to interpret EGM…

Specification Overfitting in Artificial Intelligence
Benjamin Roth, Pedro Henrique Luz de Araujo, Yuxi Xia, Saskia Kaltenbrunner, Christoph Korab
https://arxiv.org/abs/2403.08425 …

Specification Overfitting in Artificial Intelligence
Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency. Consequently, regulatory bodies struggle with containing this technology's potential negative side effects. High-level requirements such as fairness and robustness need to be formalized into concrete specification metrics, imperfect proxies that capture isolated aspects of the underlying requirements. Given possible trade…

This https://arxiv.org/abs/2312.15918 has been replaced.
link: https://scholar.google.com/scholar?q=a

Supervised Knowledge Makes Large Language Models Better In-context Learners
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the critical challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. While previous in-context learning research has focused on enhancing models to adhere to users' specific…

This https://arxiv.org/abs/2312.01957 has been replaced.
link: https://scholar.google.com/scholar?q=a

Distilled Self-Critique of LLMs with Synthetic Data: a Bayesian Perspective
This paper proposes an interpretation of RLAIF as Bayesian inference by introducing distilled Self-Critique (dSC), which refines the outputs of a LLM through a Gibbs sampler that is later distilled into a fine-tuned model. Only requiring synthetic data, dSC is exercised in experiments regarding safety, sentiment, and privacy control, showing it can be a viable and cheap alternative to align LLMs. Code released at \url{https://github.com/vicgalle/distilled-self-critique}.

This https://arxiv.org/abs/2311.09828 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages
Despite the recent progress on scaling multilingual machine translation (MT) to several under-resourced African languages, accurately measuring this progress remains challenging, since evaluation is often performed on n-gram matching metrics such as BLEU, which typically show a weaker correlation with human judgments. Learned metrics such as COMET have higher correlation; however, the lack of evaluation data with human ratings for under-resourced languages, complexity of annotation guidelines l…

This https://arxiv.org/abs/2311.00445 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models
A central component of rational behavior is logical inference: the process of determining which conclusions follow from a set of premises. Psychologists have documented several ways in which humans' inferences deviate from the rules of logic. Do language models, which are trained on text generated by humans, replicate such human biases, or are they able to overcome them? Focusing on the case of syllogisms -- inferences from two simple premises -- we show that, within the PaLM2 family of transfo…

This https://arxiv.org/abs/2310.19956 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

The Impact of Depth on Compositional Generalization in Transformer Language Models
To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the hypothesis, motivated by theoretical and empirical work, that deeper transformers generalize more compositionally. Simply adding layers increases the total number of parameters; to address this confound between depth and size, we construct three classes of models…

This https://arxiv.org/abs/2310.06694 has been replaced.
link: https://scholar.google.com/scholar?q=a

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
The popularity of LLaMA (Touvron et al., 2023a;b) and other recently emerged moderate-sized large language models (LLMs) highlights the potential of building smaller yet powerful LLMs. Regardless, the cost of training such models from scratch on trillions of tokens remains high. In this work, we study structured pruning as an effective means to develop smaller LLMs from pre-trained, larger models. Our approach employs two key techniques: (1) targeted structured pruning, which prunes a larger mo…

This https://arxiv.org/abs/2309.05494 has been replaced.
link: https://scholar.google.com/scholar?q=a

CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts
Social media platforms play an essential role in crisis communication, but analyzing crisis-related social media texts is challenging due to their informal nature. Transformer-based pre-trained models like BERT and RoBERTa have shown success in various NLP tasks, but they are not tailored for crisis-related texts. Furthermore, general-purpose sentence encoders are used to generate sentence embeddings, regardless of the textual complexities in crisis-related texts. Advances in applications like …