Tootfinder

Sources: Kyle Vogt, who resigned as CEO of Cruise six months ago, raised $150M for The Bot Company, a household robot startup, at a $550M post-money valuation (Kenrick Cai/Forbes)
https://www.forbes.com/sites/kenrickcai/2024/05/13/kyle…

Cruise Cofounder Kyle Vogt Raised $150 Million For Household Robot Startup
Vogt, who resigned from the self-driving car company amid a crisis just six months ago, landed a $550 million valuation for a new company which wants to sell robots for personal uses like cleaning your house.

Sincerely, your favourite chatbot by #OpenAI. #AI
"OpenAI’s training crawler was stuck pinging “the world’s lamest content farm” millions of times"

OpenAI Training Bot Crawls 'World's Lamest Content Farm' 3 Million Times in One Day
"If you were wondering what they're using to train GPT-5, well, now you know."

This https://arxiv.org/abs/2405.05670 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

This https://arxiv.org/abs/2404.03614 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

This https://arxiv.org/abs/2404.08422 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

This https://arxiv.org/abs/2404.14304 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

This https://arxiv.org/abs/2405.05722 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2405.04829 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Mon HaikuBot est sur le dernier GPT-4o !
#ChatGPT

Haïku Bot (@haikubot@piaille.fr)
2,52K Messages, 2 Abonnements, 134 Abonné·e·s · Bot qui toot régulièrement un Haïku inventé par ChatGPT. Une illustration est ensuite créée par Dall-e d'après ce Haïku. Ecrit par Nicolas Berloquin @nico@lepoulsdumonde.com This Bot creates a Haïku with ChatGPT then illustrates it with Dall-e.

This https://arxiv.org/abs/2402.07900 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Wavefront Randomization Improves Deconvolution
The performance of an imaging system is limited by optical aberrations, which cause blurriness in the resulting image. Digital correction techniques, such as deconvolution, have limited ability to correct the blur, since some spatial frequencies in the scene are not measured adequately due to the aberrations ('zeros' of the system transfer function). We prove that the addition of a random mask to an imaging system removes its dependence on aberrations, reducing the likelihood of zeros in the tr…

Sincerely, your favourite chatbot by #OpenAI. #AI
"OpenAI’s training crawler was stuck pinging “the world’s lamest content farm” millions of times"

OpenAI Training Bot Crawls 'World's Lamest Content Farm' 3 Million Times in One Day
"If you were wondering what they're using to train GPT-5, well, now you know."

This https://arxiv.org/abs/2404.16455 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

This https://arxiv.org/abs/2405.06233 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

This https://arxiv.org/abs/2310.19528 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

This https://arxiv.org/abs/2405.05171 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2405.04532 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2402.07839 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Towards Meta-Pruning via Optimal Transport
Structural pruning of neural networks conventionally relies on identifying and discarding less important neurons, a practice often resulting in significant accuracy loss that necessitates subsequent fine-tuning efforts. This paper introduces a novel approach named Intra-Fusion, challenging this prevailing pruning paradigm. Unlike existing methods that focus on designing meaningful neuron importance metrics, Intra-Fusion redefines the overlying pruning procedure. Through utilizing the concepts o…

This https://arxiv.org/abs/2402.07787 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Extensible Multi-Granularity Fusion Network for Aspect-based Sentiment Analysis
Aspect-based Sentiment Analysis (ABSA) evaluates sentiment expressions within a text to comprehend sentiment information. Previous studies integrated external knowledge, such as knowledge graphs, to enhance the semantic features in ABSA models. Recent research has examined the use of Graph Neural Networks (GNNs) on dependency and constituent trees for syntactic analysis. With the ongoing development of ABSA, more innovative linguistic and structural features are being incorporated (e.g. latent …

This https://arxiv.org/abs/2307.09913 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

This https://arxiv.org/abs/2312.13064 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

This https://arxiv.org/abs/2405.04278 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2405.00982 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

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/2402.06198 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

GS-CLIP: Gaussian Splatting for Contrastive Language-Image-3D Pretraining from Real-World Data
3D Shape represented as point cloud has achieve advancements in multimodal pre-training to align image and language descriptions, which is curial to object identification, classification, and retrieval. However, the discrete representations of point cloud lost the object's surface shape information and creates a gap between rendering results and 2D correspondences. To address this problem, we propose GS-CLIP for the first attempt to introduce 3DGS (3D Gaussian Splatting) into multimodal pre-tra…

This https://arxiv.org/abs/2402.07462 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

A Hormetic Approach to the Value-Loading Problem: Preventing the Paperclip Apocalypse?
The value-loading problem is a significant challenge for researchers aiming to create artificial intelligence (AI) systems that align with human values and preferences. This problem requires a method to define and regulate safe and optimal limits of AI behaviors. In this work, we propose HALO (Hormetic ALignment via Opponent processes), a regulatory paradigm that uses hormetic analysis to regulate the behavioral patterns of AI. Behavioral hormesis is a phenomenon where low frequencies of a beha…

This https://arxiv.org/abs/2303.17314 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

This https://arxiv.org/abs/2405.03052 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2405.00704 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2403.05302 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Modeling Dynamic (De)Allocations of Local Memory for Translation Validation
End-to-End Translation Validation is the problem of verifying the executable code generated by a compiler against the corresponding input source code for a single compilation. This becomes particularly hard in the presence of dynamically-allocated local memory where addresses of local memory may be observed by the program. In the context of validating the translation of a C procedure to executable code, a validator needs to tackle constant-length local arrays, address-taken local variables, add…

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/2401.15365 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

An open dataset for oracle bone script recognition and decipherment
Oracle Bone Script (OBS), one of the earliest known forms of ancient Chinese writing, holds invaluable insights into the humanities and geography of the Shang Dynasty, dating back 3,000 years. The immense historical and cultural significance of these writings cannot be overstated. However, the passage of time has obscured much of their meaning, presenting a significant challenge in deciphering these ancient texts. With the advent of Artificial Intelligence (AI), employing AI to assist in interp…

This https://arxiv.org/abs/2402.07420 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

On the Transit Obfuscation Problem
Concealing an intermediate point on a route or visible from a route is an important goal in some transportation and surveillance scenarios. This paper studies the Transit Obfuscation Problem, the problem of traveling from some start location to an end location while "covering" a specific transit point that needs to be concealed from adversaries. We propose the notion of transit anonymity, a quantitative guarantee of the anonymity of a specific transit point, even with a powerful adversary with …

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/2404.14815 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2404.18534 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2310.09342 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Ranking LLM-Generated Loop Invariants for Program Verification
Synthesizing inductive loop invariants is fundamental to automating program verification. In this work, we observe that Large Language Models (such as gpt-3.5 or gpt-4) are capable of synthesizing loop invariants for a class of programs in a 0-shot setting, yet require several samples to generate the correct invariants. This can lead to a large number of calls to a program verifier to establish an invariant. To address this issue, we propose a {\it re-ranking} approach for the generated results…

This https://arxiv.org/abs/2311.08051 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

This https://arxiv.org/abs/2401.13666 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Algebraic methods for solving recognition problems with non-crossing classes
In this paper, we propose to consider various models of pattern recognition. At the same time, it is proposed to consider models in the form of two operators: a recognizing operator and a decision rule. Algebraic operations are introduced on recognizing operators, and based on the application of these operators, a family of recognizing algorithms is created. An upper estimate is constructed for the model, which guarantees the completeness of the extension.

This https://arxiv.org/abs/2402.07197 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse research fields of artificial intelligence, especially for open-ended tasks. While the idea is less explored in the graph domain, despite the availability of numerous powerful graph models (GMs), they are restricted to tasks in a pre-defined form. Although several methods applying LLMs to graphs have been proposed, they fail t…

This https://arxiv.org/abs/2309.11676 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Cardinality and Representation of Stone Relation Algebras
Previous work has axiomatised the cardinality operation in relation algebras, which counts the number of edges of an unweighted graph. We generalise the cardinality axioms to Stone relation algebras, which model weighted graphs, and study the relationships between various axioms for cardinality. This results in simpler cardinality axioms also for relation algebras. We give sufficient conditions for the representability of Stone relation algebras and for Stone relation algebras to be relation al…

This https://arxiv.org/abs/2404.11944 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2404.16226 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

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/2401.12561 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

This https://arxiv.org/abs/2401.09273 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

A classification of bisimilarities for general Markov decision processes
We provide a fine classification of bisimilarities between states of possibly different labelled Markov processes (LMP). We show that a bisimilarity relation proposed by Panangaden that uses direct sums coincides with "event bisimilarity" from his joint work with Danos, Desharnais, and Laviolette. We also extend Giorgio Bacci's notions of bisimilarity between two different processes to the case of nondeterministic LMP and generalize the game characterization of state bisimilarity by Clerc et al…

This https://arxiv.org/abs/2401.12467 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

An open dataset for the evolution of oracle bone characters: EVOBC
The earliest extant Chinese characters originate from oracle bone inscriptions, which are closely related to other East Asian languages. These inscriptions hold immense value for anthropology and archaeology. However, deciphering oracle bone script remains a formidable challenge, with only approximately 1,600 of the over 4,500 extant characters elucidated to date. Further scholarly investigation is required to comprehensively understand this ancient writing system. Artificial Intelligence techn…

This https://arxiv.org/abs/2404.05241 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2404.12744 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

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/2307.06299 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Towards a Certified Proof Checker for Deep Neural Network Verification
Recent developments in deep neural networks (DNNs) have led to their adoption in safety-critical systems, which in turn has heightened the need for guaranteeing their safety. These safety properties of DNNs can be proven using tools developed by the verification community. However, these tools are themselves prone to implementation bugs and numerical stability problems, which make their reliability questionable. To overcome this, some verifiers produce proofs of their results which can be check…

This https://arxiv.org/abs/2401.06056 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

MatSynth: A Modern PBR Materials Dataset
We introduce MatSynth, a dataset of 4,000+ CC0 ultra-high resolution PBR materials. Materials are crucial components of virtual relightable assets, defining the interaction of light at the surface of geometries. Given their importance, significant research effort was dedicated to their representation, creation and acquisition. However, in the past 6 years, most research in material acquisiton or generation relied either on the same unique dataset, or on company-owned huge library of procedural …

This https://arxiv.org/abs/2309.03041 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

A Refutation of Shapley Values for Explainability
Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information about the relative importance of features in rule-based explanations. Such misleading information was broadly categorized into a number of possible issues. Each of those issues relates with features being relevant or irrelevant for a prediction, and all are significant regarding the inadequacy of Shapley values for rule-based explainability. This earlier work devised a brute-force…

This https://arxiv.org/abs/2403.19669 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2404.09127 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

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/2401.09273 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

A classification of bisimilarities for general Markov decision processes
We provide a fine classification of bisimilarities between states of possibly different labelled Markov processes (LMP). We show that a bisimilarity relation proposed by Panangaden that uses direct sums coincides with "event bisimilarity" from his joint work with Danos, Desharnais, and Laviolette. We also extend Giorgio Bacci's notions of bisimilarity between two different processes to the case of nondeterministic LMP and generalize the game characterization of state bisimilarity by Clerc et al…

This https://arxiv.org/abs/2304.09571 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

This https://arxiv.org/abs/2405.05722 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2404.02936 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2307.06299 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Towards a Certified Proof Checker for Deep Neural Network Verification
Recent developments in deep neural networks (DNNs) have led to their adoption in safety-critical systems, which in turn has heightened the need for guaranteeing their safety. These safety properties of DNNs can be proven using tools developed by the verification community. However, these tools are themselves prone to implementation bugs and numerical stability problems, which make their reliability questionable. To overcome this, some verifiers produce proofs of their results which can be check…

This https://arxiv.org/abs/2303.11793 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense
Deep neural networks, particularly in vision tasks, are notably susceptible to adversarial perturbations. To overcome this challenge, developing a robust classifier is crucial. In light of the recent advancements in the robustness of classifiers, we delve deep into the intricacies of adversarial training and Jacobian regularization, two pivotal defenses. Our work is the first carefully analyzes and characterizes these two schools of approaches, both theoretically and empirically, to demonstrate…

This https://arxiv.org/abs/2405.05171 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2403.18426 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2301.04634 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Street-View Image Generation from a Bird's-Eye View Layout
Bird's-Eye View (BEV) Perception has received increasing attention in recent years as it provides a concise and unified spatial representation across views and benefits a diverse set of downstream driving applications. At the same time, data-driven simulation for autonomous driving has been a focal point of recent research but with few approaches that are both fully data-driven and controllable. Instead of using perception data from real-life scenarios, an ideal model for simulation would gener…

This https://arxiv.org/abs/2405.04278 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2403.17859 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.03052 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2403.11894 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.14815 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2403.10185 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.11944 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2312.15099 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.05241 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2312.07399 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2403.19669 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

This https://arxiv.org/abs/2310.07819 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.06373 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.05904 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.05466 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.05376 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.04819 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.02814 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.02178 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.01582 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2405.01139 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.18684 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.14795 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.07982 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.06347 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.05365 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.04292 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.03381 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2404.01461 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2403.14381 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2403.09734 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2402.12563 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2402.11295 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2402.07899 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

This https://arxiv.org/abs/2403.07805 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Beyond Memorization: The Challenge of Random Memory Access in Language Models
Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge storage and memory access within their parameters remain elusive. In this paper, we investigate whether a generative LM (e.g., GPT-2) is able to access its memory sequentially or randomly. Through carefully-designed synthetic tasks, covering the scenarios of full recitation, selective recitation and grounded question an…

This https://arxiv.org/abs/2403.07714 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to address diverse real-world challenges. Assessing the capability of LLMs to utilise tools necessitates large-scale and stable benchmarks. However, previous works relied on either hand-crafted online tools with limited scale, or large-scale real online APIs suffering from instability of API status. To address this problem, we…