Tootfinder

これ読むといいんじゃないかな。うえのさんの。
--
二つのクリスマス. ——何かを「待ちのぞむ」ということ | by ueno | Medium
https://oryzivora.page/二つのクリスマス-750d0b08d274?gi=705df5f6d027

This https://arxiv.org/abs/2502.10090 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models
Humans possess an extraordinary ability to understand and execute complex manipulation tasks by interpreting abstract instruction manuals. For robots, however, this capability remains a substantial challenge, as they cannot interpret abstract instructions and translate them into executable actions. In this paper, we present Manual2Skill, a novel framework that enables robots to perform complex assembly tasks guided by high-level manual instructions. Our approach leverages a Vision-Language Mode…

This https://arxiv.org/abs/2506.00558 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

ViVo: A Dataset for Volumetric VideoReconstruction and Compression
As research on neural volumetric video reconstruction and compression flourishes, there is a need for diverse and realistic datasets, which can be used to develop and validate reconstruction and compression models. However, existing volumetric video datasets lack diverse content in terms of both semantic and low-level features that are commonly present in real-world production pipelines. In this context, we propose a new dataset, ViVo, for VolumetrIc VideO reconstruction and compression. The da…

This https://arxiv.org/abs/2506.05394 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Attacking Attention of Foundation Models Disrupts Downstream Tasks
Foundation models represent the most prominent and recent paradigm shift in artificial intelligence.Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning. For this reason, models such as CLIP , DINO or Vision Transfomers (ViT), are becoming the bedrock of many industrial AI-powered applications. However, the reliance on pre-trained foundation models also introduces significant security concerns, as these models a…

Frosty for partial synchrony
Stephen Buttolph, Andrew Lewis-Pye, Kevin Sekniqi
https://arxiv.org/abs/2506.09823 https://arxiv.org/pdf…

Frosty for partial synchrony
Snowman is the consensus protocol used by blockchains on Avalanche. Recent work has shown both how to augment Snowman with a `liveness' module called `Frosty' that protects against liveness attacks, and also how to modify Snowman so as to be consistent in partial synchrony. Since Frosty assumes (a strong form of) synchrony, the aim of this note is to show how to modify Frosty to deal with the partially synchronous version of Snowman.

This https://arxiv.org/abs/2501.09799 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Scan-Adaptive MRI Undersampling Using Neighbor-based Optimization (SUNO)
Accelerated MRI involves collecting partial k-space measurements to reduce acquisition time, patient discomfort, and motion artifacts, and typically uses regular undersampling patterns or hand-designed schemes. Recent works have studied population-adaptive sampling patterns that are learned from a group of patients (or scans) based on population-specific metrics. However, such a general sampling pattern can be sub-optimal for any specific scan since it may lack scan or slice adaptive details. T…

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
Yuki Imajuku, Kohki Horie, Yoichi Iwata, Kensho Aoki, Naohiro Takahashi, Takuya Akiba
https://arxiv.org/abs/2506.09050

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
How well do AI systems perform in algorithm engineering for hard optimization problems in domains such as package-delivery routing, crew scheduling, factory production planning, and power-grid balancing? We introduce ALE-Bench, a new benchmark for evaluating AI systems on score-based algorithmic programming contests. Drawing on real tasks from the AtCoder Heuristic Contests, ALE-Bench presents optimization problems that are computationally hard and admit no known exact solution. Unlike short-du…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new/
[6/7]:
Spatial Reasoning with Denoising Models
https://…

Martin Davis: An Overview of his Work in Logic, Computer Science, and Philosophy
Liesbeth De Mol, Yuri V. Matiyasevich, Eugenio G. Omodeo, Alberto Policriti, Wilfried Sieg, Elaine J. Weyuker
https://arxiv.org/abs/2506.08588

Martin Davis: An Overview of his Work in Logic, Computer Science, and Philosophy
In his autobiographic essay written in 1999, ``From logic to computer science and back'', Martin David Davis (3/8/1928--1/1/2023) indicated that he viewed himself as a logician \emph{and} a computer scientist. He expanded the essay in 2016 and expressed a new perspective through a changed title, ``My life as a logician''. He points out that logic was the unifying theme underlying his scientific career. Our paper attempts to provide a consistent vision that illuminates Davis' successive contribu…

Thomason's colimit theorem for the double category of elements
Andrew Gill, Maru Sarazola
https://arxiv.org/abs/2506.08246 https://

Thomason's colimit theorem for the double category of elements
We show that, for any 2-category $C$ and 2-functor $F\colon C \to Cat$, the double category of elements $\iint_C F$ introduced by Grandis and Paré satisfies a version of Thomason's colimit theorem; that is, there is a weak homotopy equivalence $B hocolim F\simeq B(\iint_C F)$.

This https://arxiv.org/abs/2409.02516 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

The emergence of nonlinear Jeans-type instabilities for quasilinear wave equations
This article contributes a key ingredient to the longstanding open problem of understanding the fully nonlinear version of Jeans instability, as highlighted by A. Rendall [Living Rev. Relativ. 8, 6 (2005)]. We establish a family of self-increasing blowup solutions for the following class of quasilinear wave equations (a model of the Peebles' and Noh-Hwang's equations) that have not previously been studied: \[ \partial^2_t \varrho- \biggl(\frac{ \mathsf{m}^2 (\partial_{t}\varrho )^2}{(1+\varrh…

Gradual Metaprogramming
Tianyu Chen, Darshal Shetty, Jeremy G. Siek, Chao-Hong Chen, Weixi Ma, Arnaud Venet, Rocky Liu
https://arxiv.org/abs/2506.09043 htt…

Gradual Metaprogramming
Data engineers increasingly use domain-specific languages (DSLs) to generate the code for data pipelines. Such DSLs are often embedded in Python. Unfortunately, there are challenges in debugging the generation of data pipelines: an error in a Python DSL script is often detected too late, after the execution of the script, and the source code location that triggers the error is hard to pinpoint. In this paper, we focus on the F3 DSL of Meta (Facebook), which is a DSL embedded in Python (so it …

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
Yang Li, Qiang Sheng, Yehan Yang, Xueyao Zhang, Juan Cao
https://arxiv.org/abs/2506.09996

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
Though safety alignment has been applied to most large language models (LLMs), LLM service providers generally deploy a subsequent moderation as the external safety guardrail in real-world products. Existing moderators mainly practice a conventional full detection, which determines the harmfulness based on the complete LLM output, causing high service latency. Recent works pay more attention to partial detection where moderators oversee the generation midway and early stop the output if harmful…

This https://arxiv.org/abs/2506.03770 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Multiuser Beamformig for Pinching-Antenna Systems: An Element-wise Optimization Framework
The pinching-antenna system (PASS) reconstructs wireless channels through pinching beamforming, i.e., optimizing the activated locations of pinching antennas (PAs) along the waveguide. The aim of this article is to investigate the joint design of baseband beamforming and pinching beamforming. A low-complexity element-wise sequential optimization framework is proposed to address the sum-rate maximization problem in PASS-enabled downlink and uplink channels. i) For the downlink scenario, maximum …

This https://arxiv.org/abs/2506.04437 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Graph quandles: Generalized Cayley graphs of racks and right quasigroups
We solve two open problems of Valeriy Bardakov about Cayley graphs of racks and graph-theoretic realizations of right quasigroups. We also extend Didier Caucal's classification of labeled Cayley digraphs to right quasigroups and related algebraic structures like quandles. First, we characterize markings of graphs that realize racks. As an application, we construct rack-theoretic (di)graph invariants from permutation representations of graph automorphism groups. We describe how to compute thes…

This https://arxiv.org/abs/2505.24718 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Reinforcing Video Reasoning with Focused Thinking
Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations persist: 1) they often produce unfocused, verbose reasoning chains that obscure salient spatiotemporal cues and 2) binary rewarding fails to account for partially correct answers, resulting in high reward variance and inefficient learning. In this paper, we propos…

This https://arxiv.org/abs/2506.04147 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL
Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators. While reinforcement learning (RL) holds promise for autonomously acquiring robot control policies, scaling it to high-DoF embodiments remains challenging. Direct RL in the real world demands both safe exploration and high sample efficiency, which are difficult to achieve in practice. Sim-to-real RL, on the other hand, is often brittle du…

This https://arxiv.org/abs/2506.05376 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

A Red Teaming Roadmap Towards System-Level Safety
Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has effectively identified critical vulnerabilities in state-of-the-art refusal-trained LLMs. However, in our view the many conference submissions on LLM red teaming do not, in aggregate, prioritize the right research problems. First, testing against clear product safety …

Understanding the Performance and Power of LLM Inferencing on Edge Accelerators
Mayank Arya, Yogesh Simmhan
https://arxiv.org/abs/2506.09554 https://

Understanding the Performance and Power of LLM Inferencing on Edge Accelerators
Large Language Models (LLMs) have demonstrated exceptional benefits to a wide range of domains, for tasks as diverse as code generation and robot navigation. While LLMs are usually served from cloud data centers, mission-critical and privacy-sensitive applications may require local hosting of open LLM models. Given the large GPU memory footprint needed for LLMs, edge accelerators such as Nvidia Jetson Orin AGX with 64GB of shared GPU-CPU RAM are a compelling choice. However, the feasibility and…

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
Li Kang, Xiufeng Song, Heng Zhou, Yiran Qin, Jie Yang, Xiaohong Liu, Philip Torr, Lei Bai, Zhenfei Yin
https://arxiv.org/abs/2506.09049

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new/
[3/7]:
Low-Loss Space in Neural Networks is Continuous and Fully Connected
ht…

Compositional Reasoning for Parametric Probabilistic Automata
Hannah Mertens, Tim Quatmann, Joost-Pieter Katoen
https://arxiv.org/abs/2506.08525 https://…

Compositional Reasoning for Parametric Probabilistic Automata
We establish an assume-guarantee (AG) framework for compositional reasoning about multi-objective queries in parametric probabilistic automata (pPA) - an extension to probabilistic automata (PA), where transition probabilities are functions over a finite set of parameters. We lift an existing framework for PA to the pPA setting, incorporating asymmetric, circular, and interleaving proof rules. Our approach enables the verification of a broad spectrum of multi-objective queries for pPA, encompas…

Linguine: A Natural-Language Programming Language with Formal Semantics and a Clean Compiler Pipeline
Lifan Hu
https://arxiv.org/abs/2506.08396 https://

Linguine: A Natural-Language Programming Language with Formal Semantics and a Clean Compiler Pipeline
Linguine is a natural-language-inspired programming language that enables users to write programs in a fluent, controlled subset of English while preserving formal semantics. The language introduces anaphoric constructs, such as pronoun variables (e.g., "it", "them"), that are statically resolved through referent-tracking analysis combined with a Hindley-Milner-style type system. Each pronoun is guaranteed to be unambiguous and well-typed at compile time. The Linguine compiler pipeline includ…

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Amel Muminovic, Amela Kadric Muminovic
https://arxiv.org/abs/2506.09992

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Online toxic language causes real harm, especially in regions with limited moderation tools. In this study, we evaluate how large language models handle toxic comments in Serbian, Croatian, and Bosnian, languages with limited labeled data. We built and manually labeled a dataset of 4,500 YouTube and TikTok comments drawn from videos across diverse categories, including music, politics, sports, modeling, influencer content, discussions of sexism, and general topics. Four models (GPT-3.5 Turbo, G…

This https://arxiv.org/abs/2505.24247 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

50 Years of Automated Face Recognition
Over the past 50 years, automated face recognition has evolved from rudimentary, handcrafted systems into sophisticated deep learning models that rival and often surpass human performance. This paper chronicles the history and technological progression of FR, from early geometric and statistical methods to modern deep neural architectures leveraging massive real and AI-generated datasets. We examine key innovations that have shaped the field, including developments in dataset, loss function, ne…

This https://arxiv.org/abs/2412.02003 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Polynomial algorithm for alternating link equivalence
Link equivalence up to isotopy in a 3-space is the problem that lies at the root of knot theory, and is important in 3-dimensional topology and geometry. We consider its restriction to alternating links, given by two alternating diagrams with $n_1$ and $n_2$ crossings, and show that this problem has polynomial algorithm in terms of $max\{n_1, n_2\}$. For the proof, we use Tait flyping conjectures, observations stemming from the work of Lackenby, Menasco, Sundberg and Thistlethwaite on alternati…

This https://arxiv.org/abs/2506.04120 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data
Creating accurate, physical simulations directly from real-world robot motion holds great value for safe, scalable, and affordable robot learning, yet remains exceptionally challenging. Real robot data suffers from occlusions, noisy camera poses, dynamic scene elements, which hinder the creation of geometrically accurate and photorealistic digital twins of unseen objects. We introduce a novel real-to-sim framework tackling all these challenges at once. Our key insight is a hybrid scene represen…

This https://arxiv.org/abs/2506.03940 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Depermissioning Web3: a Permissionless Accountable RPC Protocol for Blockchain Networks
In blockchain networks, so-called "full nodes" serve data to and relay transactions from clients through an RPC interface. This serving layer enables integration of "Web3" data, stored on blockchains, with "Web2" mobile or web applications that cannot directly participate as peers in a blockchain network. In practice, the serving layer is dominated by a small number of centralized services ("node providers") that offer permissioned access to RPC endpoints. Clients register with these providers …

On the Performance of Cloud-based ARM SVE for Zero-Knowledge Proving Systems
Dumitrel Loghin, Shuang Liang, Shengwei Liu, Xiong Liu, Pingcheng Ruan, Zhigang Ye
https://arxiv.org/abs/2506.09505

On the Performance of Cloud-based ARM SVE for Zero-Knowledge Proving Systems
Zero-knowledge proofs (ZKP) are becoming a gold standard in scaling blockchains and bringing Web3 to life. At the same time, ZKP for transactions running on the Ethereum Virtual Machine require powerful servers with hundreds of CPU cores. The current zkProver implementation from Polygon is optimized for x86-64 CPUs by vectorizing key operations, such as Merkle tree building with Poseidon hashes over the Goldilocks field, with Advanced Vector Extensions (AVX and AVX512). With these optimizations…

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
Polina Kirichenko, Mark Ibrahim, Kamalika Chaudhuri, Samuel J. Bell
https://arxiv.org/abs/2506.09038

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or fundamentally unanswerable, require LLMs to reason about uncertainty and selectively abstain -- i.e., refuse to answer definitively. However, abstention remains understudied, without a systematic evaluation framework for modern LLMs. In this work, we introduce …

Forward and Backward Simulations for Partially Observable Probability
Chris Chen, Annabelle McIver, Carroll Morgan
https://arxiv.org/abs/2506.08437 https:/…

Forward and Backward Simulations for Partially Observable Probability
Data refinement is the standard extension of a refinement relation from programs to datatypes (i.e. a behavioural subtyping relation). Forward/backward simulations provide a tractable method for establishing data refinement, and have been thoroughly studied for nondeterministic programs. However, for standard models of mixed probability and nondeterminism, ordinary assignment statements may not commute with (variable-disjoint) program fragments. This (1) invalidates a key assumption underlying …

Verification of the Release-Acquire Semantics
Parosh Abdulla, Elli Anastasiadi, Mohamed Faouzi Atig, Samuel Grahn
https://arxiv.org/abs/2506.08238 https://…

Verification of the Release-Acquire Semantics
The Release-Acquire (RA) semantics and its variants are some of the most fundamental models of concurrent semantics for architectures, programming languages, and distributed systems. Several steps have been taken in the direction of testing such semantics, where one is interested in whether a single program execution is consistent with a memory model. The more general verification problem, i.e., checking whether all allowed program runs are consistent with a memory model, has still not been stu…

Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
Hiroshi Matsuda, Chunpeng Ma, Masayuki Asahara
https://arxiv.org/abs/2506.09983

Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
Recent advances in large language models (LLMs) have enabled impressive performance in various tasks. However, standard prompting often struggles to produce structurally valid and accurate outputs, especially in dependency parsing. We propose a novel step-by-step instruction strategy, where universal part-of-speech tagging precedes the prediction of syntactic heads and dependency labels, and a simplified CoNLL-U like output format, our method achieves state-of-the-art accuracy on Universal Depe…

This https://arxiv.org/abs/2506.02215 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Active inference as a unified model of collision avoidance behavior in human drivers
Collision avoidance -- involving a rapid threat detection and quick execution of the appropriate evasive maneuver -- is a critical aspect of driving. However, existing models of human collision avoidance behavior are fragmented, focusing on specific scenarios or only describing certain aspects of the avoidance behavior, such as response times. This paper addresses these gaps by proposing a novel computational cognitive model of human collision avoidance behavior based on active inference. Activ…

This https://arxiv.org/abs/2505.12453 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
Federated recommender system (FedRec) has emerged as a solution to protect user data through collaborative training techniques. A typical FedRec involves transmitting the full model and entire weight updates between edge devices and the server, causing significant burdens to devices with limited bandwidth and computational power. While the sparsity of embedding updates provides opportunity for payload optimization, existing sparsity-aware federated protocols generally sacrifice privacy for effi…

Efficient Task Graph Scheduling for Parallel QR Factorization in SLSQP
Soumyajit Chatterjee, Rahul Utkoor, Uppu Eshwar, Sathya Peri, V. Krishna Nandivada
https://arxiv.org/abs/2506.09463

Efficient Task Graph Scheduling for Parallel QR Factorization in SLSQP
Efficient task scheduling is paramount in parallel programming on multi-core architectures, where tasks are fundamental computational units. QR factorization is a critical sub-routine in Sequential Least Squares Quadratic Programming (SLSQP) for solving non-linear programming (NLP) problems. QR factorization decomposes a matrix into an orthogonal matrix Q and an upper triangular matrix R, which are essential for solving systems of linear equations arising from optimization problems. SLSQP uses …

A Survey of Link Prediction in N-ary Knowledge Graphs
Jiyao Wei, Saiping Guan, Da Li, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
https://arxiv.org/abs/2506.08970

A Survey of Link Prediction in N-ary Knowledge Graphs
N-ary Knowledge Graphs (NKGs) are a specialized type of knowledge graph designed to efficiently represent complex real-world facts. Unlike traditional knowledge graphs, where a fact typically involves two entities, NKGs can capture n-ary facts containing more than two entities. Link prediction in NKGs aims to predict missing elements within these n-ary facts, which is essential for completing NKGs and improving the performance of downstream applications. This task has recently gained significan…

Approximate Axiomatization for Differentially-Defined Functions
Andr\'e Platzer, Long Qian
https://arxiv.org/abs/2506.08233 https://

Approximate Axiomatization for Differentially-Defined Functions
This article establishes a complete approximate axiomatization for the real-closed field $\mathbb{R}$ expanded with all differentially-defined functions, including special functions such as $\sin(x), \cos(x), e^x, \dots$. Every true sentence is provable up to some numerical approximation, and the truth of such approximations converge under mild conditions. Such an axiomatization is a fragment of the axiomatization for differential dynamic logic, and is therefore a finite extension of the axioma…

This https://arxiv.org/abs/2505.21652 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation
Fine-grained robot manipulation, such as lifting and rotating a bottle to display the label on the cap, requires robust reasoning about object parts and their relationships with intended tasks. Despite recent advances in training general-purpose robot manipulation policies guided by language instructions, there is a notable lack of large-scale datasets for fine-grained manipulation tasks with part-level instructions and diverse 3D object instances annotated with part-level labels. In this work,…

[2025-06-11 Wed (UTC), 3 new articles found for cs.PL Programming Languages]
toXiv_bot_toot

When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text
Hillary Dawkins, Kathleen C. Fraser, Svetlana Kiritchenko
https://arxiv.org/abs/2506.09975

When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text
Detecting AI-generated text is a difficult problem to begin with; detecting AI-generated text on social media is made even more difficult due to the short text length and informal, idiosyncratic language of the internet. It is nonetheless important to tackle this problem, as social media represents a significant attack vector in online influence campaigns, which may be bolstered through the use of mass-produced AI-generated posts supporting (or opposing) particular policies, decisions, or event…

This https://arxiv.org/abs/2505.11963 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language Models
Hardware security verification is a challenging and time-consuming task. For this purpose, design engineers may utilize tools such as formal verification, linters, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Language Models (LLMs) have been used to assist during this task, either directly or in conjunction with existing tools. We improve the state of the art by proposing MARVEL, a multi-agent LLM framework for a u…

SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving
Xiangchen Li, Dimitrios Spatharakis, Saeid Ghafouri, Jiakun Fan, Dimitrios Nikolopoulos
https://arxiv.org/abs/2506.09397

SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving
Regardless the advancements in device capabilities, efficient inferencing advanced large language models (LLMs) at the edge remains challenging due to limited device memory and power constraints. Existing strategies, such as aggressive quantization, pruning, or remote inference, trade accuracy for efficiency or lead to substantial cost burdens. This position paper introduces a new approach that leverages speculative decoding, previously viewed primarily as a decoding acceleration technique for …

[2025-06-11 Wed (UTC), 4 new articles found for cs.LO Logic in Computer Science]
toXiv_bot_toot

This https://arxiv.org/abs/2505.08230 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SKiD-SLAM: Robust, Lightweight, and Distributed Multi-Robot LiDAR SLAM in Resource-Constrained Field Environments
Distributed LiDAR SLAM is crucial for achieving efficient robot autonomy and improving the scalability of mapping. However, two issues need to be considered when applying it in field environments: one is resource limitation, and the other is inter/intra-robot association. The resource limitation issue arises when the data size exceeds the processing capacity of the network or memory, especially when utilizing communication systems or onboard computers in the field. The inter/intra-robot associa…

This https://arxiv.org/abs/2504.15585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys…

Resa: Transparent Reasoning Models via SAEs
Shangshang Wang, Julian Asilis, \"Omer Faruk Akg\"ul, Enes Burak Bilgin, Ollie Liu, Deqing Fu, Willie Neiswanger
https://arxiv.org/abs/2506.09967

Resa: Transparent Reasoning Models via SAEs
How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning models trained via a novel and efficient sparse autoencoder tuning (SAE-Tuning) procedure. This method first trains an SAE to capture reasoning abilities from a source model, and then uses the trained SAE to guide a standard supervised fine-tuning process to elicit such abilities in a target model, all using verified…

ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs
Dhruv Parikh, Viktor Prasanna
https://arxiv.org/abs/2506.09282

ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs
Hyperdimensional Computing (HDC) is a brain-inspired computing paradigm that represents and manipulates information using high-dimensional vectors, called hypervectors (HV). Traditional HDC methods, while robust to noise and inherently parallel, rely on single-pass, non-parametric training and often suffer from low accuracy. To address this, recent approaches adopt iterative training of base and class HVs, typically accelerated on GPUs. Inference, however, remains lightweight and well-suited fo…

This https://arxiv.org/abs/2503.09409 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

AI-based Framework for Robust Model-Based Connector Mating in Robotic Wire Harness Installation
Despite the widespread adoption of industrial robots in automotive assembly, wire harness installation remains a largely manual process, as it requires precise and flexible manipulation. To address this challenge, we design a novel AI-based framework that automates cable connector mating by integrating force control with deep visuotactile learning. Our system optimizes search-and-insertion strategies using first-order optimization over a multimodal transformer architecture trained on visual, ta…

On the cut-elimination of the modal $\mu$-calculus: Linear Logic to the rescue
Esa\"ie Bauer, Alexis Saurin
https://arxiv.org/abs/2506.09791 https://

On the cut-elimination of the modal $μ$-calculus: Linear Logic to the rescue
This paper presents a proof-theoretic analysis of the modal $μ$-calculus. More precisely, we prove a syntactic cut-elimination for the non-wellfounded modal $μ$-calculus, using methods from linear logic and its exponential modalities. To achieve this, we introduce a new system, \muLLmodinf{}, which is a linear version of the modal $μ$-calculus, intertwining the modalities from the modal $μ$-calculus with the exponential modalities from linear logic. Our strategy for proving cut-elimination …

This https://arxiv.org/abs/2504.13398 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Insecurity Through Obscurity: Veiled Vulnerabilities in Closed-Source Contracts
Most blockchains cannot hide the binary code of programs (i.e., smart contracts) running on them. To conceal proprietary business logic and to potentially deter attacks, many smart contracts are closed-source and employ layers of obfuscation. However, we demonstrate that such obfuscation can obscure critical vulnerabilities rather than enhance security, a phenomenon we term insecurity through obscurity. To systematically analyze these risks on a large scale, we present SKANF, a novel EVM byteco…

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
Wuwei Zhang, Fangcong Yin, Howard Yen, Danqi Chen, Xi Ye
https://arxiv.org/abs/2506.09944

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
Recent work has identified retrieval heads (Wu et al., 2025b), a subset of attention heads responsible for retrieving salient information in long-context language models (LMs), as measured by their copy-paste behavior in Needle-in-a-Haystack tasks. In this paper, we introduce QRHEAD (Query-Focused Retrieval Head), an improved set of attention heads that enhance retrieval from long context. We identify QRHEAD by aggregating attention scores with respect to the input query, using a handful of exa…

TTrace: Lightweight Error Checking and Diagnosis for Distributed Training
Haitian Jiang, Shaowei Zhu, Zhen Zhang, Zhenyu Song, Xinwei Fu, Zhen Jia, Yida Wang, Jinyang Li
https://arxiv.org/abs/2506.09280

TTrace: Lightweight Error Checking and Diagnosis for Distributed Training
Distributed training is essential for scaling the training of large neural network models, such as large language models (LLMs), across thousands of GPUs. However, the complexity of distributed training programs makes them particularly prone to silent bugs, which do not produce explicit error signal but lead to incorrect training outcome. Effectively detecting and localizing such silent bugs in distributed training is challenging. Common debugging practice using metrics like training loss or gr…

This https://arxiv.org/abs/2503.04280 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models
Recent advancements in Large Language Models (LLMs) and Visual Language Models (VLMs) have significantly impacted robotics, enabling high-level semantic motion planning applications. Reinforcement Learning (RL), a complementary paradigm, enables agents to autonomously optimize complex behaviors through interaction and reward signals. However, designing effective reward functions for RL remains challenging, especially in real-world tasks where sparse rewards are insufficient and dense rewards re…

This https://arxiv.org/abs/2502.04951 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search
Recent advancements in Large Language Models (LLMs) have significantly enhanced the capabilities of AI-Powered Search Engines (AIPSEs), offering precise and efficient responses by integrating external databases with pre-existing knowledge. However, we observe that these AIPSEs raise risks such as quoting malicious content or citing malicious websites, leading to harmful or unverified information dissemination. In this study, we conduct the first safety risk quantification on seven production AI…

DHoTT: A Temporal Extension of Homotopy Type Theory for Semantic Drift
Iman Poernomo
https://arxiv.org/abs/2506.09671 https://arxiv.o…

DHoTT: A Temporal Extension of Homotopy Type Theory for Semantic Drift
We introduce Dynamic Homotopy Type Theory (DHoTT), a temporal extension of Homotopy Type Theory (HoTT) designed to reason formally about concepts whose meanings evolve continuously or rupture discontinuously over time. While traditional HoTT captures identity and equivalence within a fixed semantic landscape, DHoTT enriches this framework by explicitly indexing types with a temporal parameter, allowing types themselves to deform, rupture, and reassemble as contexts shift. Formally, we show th…

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li
https://arxiv.org/abs/2506.09942 …

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs), with verification engineering playing a central role. However, best practices for RL in instruction following remain underexplored. In this work, we explore the verification challenge in RL for instruction following and propose VerIF, a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model (e.g., QwQ-32B). …

This https://arxiv.org/abs/2502.20636 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Delayed-Decision Motion Planning in the Presence of Multiple Predictions
Reliable automated driving technology is challenged by various sources of uncertainties, in particular, behavioral uncertainties of traffic agents. It is common for traffic agents to have intentions that are unknown to others, leaving an automated driving car to reason over multiple possible behaviors. This paper formalizes a behavior planning scheme in the presence of multiple possible futures with corresponding probabilities. We present a maximum entropy formulation and show how, under certai…

A Survey of End-to-End Modeling for Distributed DNN Training: Workloads, Simulators, and TCO
Jonas Svedas, Hannah Watson, Nathan Laubeuf, Diksha Moolchandani, Abubakr Nada, Arjun Singh, Dwaipayan Biswas, James Myers, Debjyoti Bhattacharjee
https://arxiv.org/abs/2506.09275

A Survey of End-to-End Modeling for Distributed DNN Training: Workloads, Simulators, and TCO
Distributed deep neural networks (DNNs) have become a cornerstone for scaling machine learning to meet the demands of increasingly complex applications. However, the rapid growth in model complexity far outpaces CMOS technology scaling, making sustainable and efficient system design a critical challenge. Addressing this requires coordinated co-design across software, hardware, and technology layers. Due to the prohibitive cost and complexity of deploying full-scale training systems, simulators …

This https://arxiv.org/abs/2412.15289 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing methods primarily design sophisticated instructions for the LLM to follow, or rely on multiple iterations, which could hinder the performance and efficiency of jailbreaks. In this work, we propose a novel jailbreak paradigm, Simple Assistive Task Linkage (SA…

IMALL with a Mixed-State Modality: A Logical Approach to Quantum Computation
Kinnari Dave, Alejandro D\'iaz-Caro, Vladimir Zamdzhiev
https://arxiv.org/abs/2506.09545

IMALL with a Mixed-State Modality: A Logical Approach to Quantum Computation
We introduce a proof language for Intuitionistic Multiplicative Additive Linear Logic (IMALL), extended with a modality B to capture mixed-state quantum computation. The language supports algebraic constructs such as linear combinations, and embeds pure quantum computations within a mixed-state framework via B, interpreted categorically as a functor from a category of Hilbert Spaces to a category of finite-dimensional C*-algebras. Measurement arises as a definable term, not as a constant, and t…

This https://arxiv.org/abs/2502.09180 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Machine Learning Approach to Sensor Substitution from Tactile Sensing to Visual Perception for Non-Prehensile Manipulation
Mobile manipulators are increasingly deployed in complex environments, requiring diverse sensors to perceive and interact with their surroundings. However, equipping every robot with every possible sensor is often impractical due to cost and physical constraints. A critical challenge arises when robots with differing sensor capabilities need to collaborate or perform similar tasks. For example, consider a scenario where a mobile manipulator equipped with high-resolution tactile skin is skilled …

Aspect-Based Opinion Summarization with Argumentation Schemes
Wendi Zhou, Ameer Saadat-Yazd, Nadin Kokciyan
https://arxiv.org/abs/2506.09917 https://

Aspect-Based Opinion Summarization with Argumentation Schemes
Reviews are valuable resources for customers making purchase decisions in online shopping. However, it is impractical for customers to go over the vast number of reviews and manually conclude the prominent opinions, which prompts the need for automated opinion summarization systems. Previous approaches, either extractive or abstractive, face challenges in automatically producing grounded aspect-centric summaries. In this paper, we propose a novel summarization system that not only captures pred…

Multi-GPU Acceleration of PALABOS Fluid Solver using C Standard Parallelism
Jonas Latt, Christophe Coreixas
https://arxiv.org/abs/2506.09242 https://

Multi-GPU Acceleration of PALABOS Fluid Solver using C++ Standard Parallelism
This article presents the principles, software architecture, and performance analysis of the GPU port of the lattice Boltzmann software library Palabos (J. Latt et al., "Palabos: Parallel lattice Boltzmann solver", Comput. Math. Appl. 81, 334-350, (2021)). A hybrid CPU-GPU execution model is adopted, in which numerical components are selectively assigned to either the CPU or the GPU, depending on considerations of performance or convenience. This design enables a progressive porting strategy, a…

This https://arxiv.org/abs/2412.03283 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of watermarking techniques that are easy to implement and highly robust against various perturbations. However, our work demonstrates a fundamental security vulnerability of semantic watermarks. We show that attackers can leverage unrelated models, even with differen…

Syntactic Effectful Realizability in Higher-Order Logic
Liron Cohen (BGU), Ariel Grunfeld (BGU), Dominik Kirst (PICUBE), \'Etienne Miquey (I2M)
https://arxiv.org/abs/2506.09458

Syntactic Effectful Realizability in Higher-Order Logic
Realizability interprets propositions as specifications for computational entities in programming languages. Specifically, syntactic realizability is a powerful machinery that handles realizability as a syntactic translation of propositions into new propositions that describe what it means to realize the input proposition. This paper introduces EffHOL (Effectful Higher-Order Logic), a novel framework that expands syntactic realizability to uniformly support modern programming paradigms with sid…

This https://arxiv.org/abs/2501.00296 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models
Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract symbolic world models that facilitate zero-shot generalization to novel goals via planning. A critical component of such models is the set of symbolic predicates that define properties of and relationships between objects. In this work, we leverage pretrained …

This https://arxiv.org/abs/2411.13425 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations of various watermarkers, especially their attack robustness? ii) How do various design choices impact their robustness? iii) How to optimally operate watermarkers in adversarial environments? To fill this gap, we systematize existing LLM watermarkers and water…

EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model
Alyssa Pinnock, Shakya Jayakody, Kawsher A Roxy, Md Rubel Ahmed
https://arxiv.org/abs/2506.09061

EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model
This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation, their high computational, memory, and power requirements often confine them to cloud environments. EdgeProfiler addresses these challenges by providing a systematic methodology for assessing LLM performance in resource-constrained edge settings. The framework pro…

PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
Zheng Zhao, Clara Vania, Subhradeep Kayal, Naila Khan, Shay B. Cohen, Emine Yilmaz
https://arxiv.org/abs/2506.09902

PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
Large language models (LLMs) have advanced conversational AI assistants. However, systematically evaluating how well these assistants apply personalization--adapting to individual user preferences while completing tasks--remains challenging. Existing personalization benchmarks focus on chit-chat, non-conversational tasks, or narrow domains, failing to capture the complexities of personalized task-oriented assistance. To address this, we introduce PersonaLens, a comprehensive benchmark for evalu…

Abstraction-Based Proof Production in Formal Verification of Neural Networks
Yizhak Yisrael Elboher, Omri Isac, Guy Katz, Tobias Ladner, Haoze Wu
https://arxiv.org/abs/2506.09455 …

Abstraction-Based Proof Production in Formal Verification of Neural Networks
Modern verification tools for deep neural networks (DNNs) increasingly rely on abstraction to scale to realistic architectures. In parallel, proof production is becoming a critical requirement for increasing the reliability of DNN verification results. However, current proofproducing verifiers do not support abstraction-based reasoning, creating a gap between scalability and provable guarantees. We address this gap by introducing a novel framework for proof-producing abstraction-based DNN verif…

This https://arxiv.org/abs/2412.13664 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Skeleton-Based Topological Planner for Exploration in Complex Unknown Environments
The capability of autonomous exploration in complex, unknown environments is important in many robotic applications. While recent research on autonomous exploration have achieved much progress, there are still limitations, e.g., existing methods relying on greedy heuristics or optimal path planning are often hindered by repetitive paths and high computational demands. To address such limitations, we propose a novel exploration framework that utilizes the global topology information of observed …

This https://arxiv.org/abs/2410.16316 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

A Computational Harmonic Detection Algorithm to Detect Data Leakage through EM Emanation
Unintended electromagnetic emissions, called EM emanations, can be exploited to recover sensitive information, posing security risks. Metal shielding, used by defense organizations to prevent data leakage, is costly and impractical for widespread use. This issue is particularly significant for IoT devices due to their sheer volume and varied deployment environments. Therefore, there is a research need for an automated detection method to monitor facilities and address data leakage promptly. To …

[2025-06-12 Thu (UTC), 10 new articles found for cs.DC Distributed, Parallel, and Cluster Computing]
toXiv_bot_toot

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
Yuxin Chen, Yiran Zhao, Yang Zhang, An Zhang, Kenji Kawaguchi, Shafiq Joty, Junnan Li, Tat-Seng Chua, Michael Qizhe Shieh, Wenxuan Zhang
https://arxiv.org/abs/2506.09890

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts. This has led to the widespread assumption that LLMs may "think" in English. However, more recent results showing strong multilingual performance, even surpassing English performance on specific tasks in other…

This https://arxiv.org/abs/2412.08468 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Multi-GraspLLM: A Multimodal LLM for Multi-Hand Semantic Guided Grasp Generation
Multi-hand semantic grasp generation aims to generate feasible and semantically appropriate grasp poses for different robotic hands based on natural language instructions. Although the task is highly valuable, due to the lack of multihand grasp datasets with fine-grained contact description between robotic hands and objects, it is still a long-standing difficult task. In this paper, we present Multi-GraspSet, the first large-scale multi-hand grasp dataset with automatically contact annotations.…

From Partial to Monadic: Combinatory Algebra with Effects
Liron Cohen (BGU), Ariel Grunfeld (BGU), Dominik Kirst (PICUBE), \'Etienne Miquey (I2M)
https://arxiv.org/abs/2506.09453

From Partial to Monadic: Combinatory Algebra with Effects
Partial Combinatory Algebras (PCAs) provide a foundational model of the untyped $λ$-calculus and serve as the basis for many notions of computability, such as realizability theory. However, PCAs support a very limited notion of computation by only incorporating non-termination as a computational effect. To provide a framework that better internalizes a wide range of computational effects, this paper puts forward the notion of Monadic Combinatory Algebras (MCAs). MCAs generalize the notion of P…

This https://arxiv.org/abs/2409.17458 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions…

Attention Head Embeddings with Trainable Deep Kernels for Hallucination Detection in LLMs
Rodion Oblovatny, Alexandra Bazarova, Alexey Zaytsev
https://arxiv.org/abs/2506.09886

Attention Head Embeddings with Trainable Deep Kernels for Hallucination Detection in LLMs
We present a novel approach for detecting hallucinations in large language models (LLMs) by analyzing the probabilistic divergence between prompt and response hidden-state distributions. Counterintuitively, we find that hallucinated responses exhibit smaller deviations from their prompts compared to grounded responses, suggesting that hallucinations often arise from superficial rephrasing rather than substantive reasoning. Leveraging this insight, we propose a model-intrinsic detection method t…

This https://arxiv.org/abs/2412.07664 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Dynamic Obstacle Avoidance of Unmanned Surface Vehicles in Maritime Environments Using Gaussian Processes Based Motion Planning
During recent years, unmanned surface vehicles are extensively utilised in a variety of maritime applications such as the exploration of unknown areas, autonomous transportation, offshore patrol and others. In such maritime applications, unmanned surface vehicles executing relevant missions that might collide with potential static obstacles such as islands and reefs and dynamic obstacles such as other moving unmanned surface vehicles. To successfully accomplish these missions, motion planning a…

[2025-06-12 Thu (UTC), 6 new articles found for cs.LO Logic in Computer Science]
toXiv_bot_toot

This https://arxiv.org/abs/2409.03788 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
With the growing deployment of LLMs in daily applications like chatbots and content generation, efforts to ensure outputs align with human values and avoid harmful content have intensified. However, increasingly sophisticated jailbreak attacks threaten this alignment, aiming to induce unsafe outputs. Current defense efforts either focus on prompt rewriting or detection, which are limited in effectiveness due to the various design of jailbreak prompts, or on output control and detection, which a…

This https://arxiv.org/abs/2411.12206 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Safe Navigation in Dynamic Environments using Density Functions
This work presents a density-based framework for safe navigation in dynamic environments characterized by time-varying obstacle sets and time-varying target regions. We propose an analytical construction of time-varying density functions that enables the synthesis of a feedback controller defined as the positive gradient of the resulting density field. The primary contribution of this paper is a rigorous convergence proof demonstrating almost-everywhere safe navigation under the proposed framew…

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
Xiangning Yu, Zhuohan Wang, Linyi Yang, Haoxuan Li, Anjie Liu, Xiao Xue, Jun Wang, Mengyue Yang
https://arxiv.org/abs/2506.09853

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
Chain-of-Thought (CoT) prompting plays an indispensable role in endowing large language models (LLMs) with complex reasoning capabilities. However, CoT currently faces two fundamental challenges: (1) Sufficiency, which ensures that the generated intermediate inference steps comprehensively cover and substantiate the final conclusion; and (2) Necessity, which identifies the inference steps that are truly indispensable for the soundness of the resulting answer. We propose a causal framework that …

This https://arxiv.org/abs/2408.16220 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Place Protections at the Right Place: Targeted Hardening for Cryptographic Code against Spectre v1
Spectre v1 attacks pose a substantial threat to security-critical software, particularly cryptographic implementations. Existing software mitigations, however, often introduce excessive overhead by indiscriminately hardening instructions without assessing their vulnerability. We propose an analysis framework that employs a novel fixpoint algorithm to detect Spectre vulnerabilities and apply targeted hardening. The fixpoint algorithm accounts for program behavior changes induced by stepwise hard…

This https://arxiv.org/abs/2410.22931 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Third-Order Gaussian Process Trajectory Representation Framework with Closed-Form Kinematics for Continuous-Time Motion Estimation
In this paper, we propose a third-order, i.e., white-noise-on-jerk, Gaussian Process (GP) Trajectory Representation (TR) framework for continuous-time (CT) motion estimation (ME) tasks. Our framework features a unified trajectory representation that encapsulates the kinematic models of both $SO(3)\times\mathbb{R}^3$ and $SE(3)$ pose representations. This encapsulation strategy allows users to use the same implementation of measurement-based factors for either choice of pose representation, whic…

Dataset of News Articles with Provenance Metadata for Media Relevance Assessment
Tomas Peterka, Matyas Bohacek
https://arxiv.org/abs/2506.09847 https://

Dataset of News Articles with Provenance Metadata for Media Relevance Assessment
Out-of-context and misattributed imagery is the leading form of media manipulation in today's misinformation and disinformation landscape. The existing methods attempting to detect this practice often only consider whether the semantics of the imagery corresponds to the text narrative, missing manipulation so long as the depicted objects or scenes somewhat correspond to the narrative at hand. To tackle this, we introduce News Media Provenance Dataset, a dataset of news articles with provenance-…

This https://arxiv.org/abs/2407.03883 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Protecting Deep Learning Model Copyrights with Adversarial Example-Free Reuse Detection
Model reuse techniques can reduce the resource requirements for training high-performance deep neural networks (DNNs) by leveraging existing models. However, unauthorized reuse and replication of DNNs can lead to copyright infringement and economic loss to the model owner. This underscores the need to analyze the reuse relation between DNNs and develop copyright protection techniques to safeguard intellectual property rights. Existing white-box testing-based approaches cannot address the common…

This https://arxiv.org/abs/2410.03483 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Versatile Neural Network Configuration Space Planning and Control Strategy for Modular Soft Robot Arms
Modular soft robot arms (MSRAs) are composed of multiple modules connected in a sequence, and they can bend at different angles in various directions. This capability allows MSRAs to perform more intricate tasks than single-module robots. However, the modular structure also induces challenges in accurate planning and control. Nonlinearity and hysteresis complicate the physical model, while the modular structure and increased DOFs further lead to cumulative errors along the sequence. To address …

This https://arxiv.org/abs/2406.10281 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Watermarking Language Models with Error Correcting Codes
Recent progress in large language models enables the creation of realistic machine-generated content. Watermarking is a promising approach to distinguish machine-generated text from human text, embedding statistical signals in the output that are ideally undetectable to humans. We propose a watermarking framework that encodes such signals through an error correcting code. Our method, termed robust binary code (RBC) watermark, introduces no noticeable degradation in quality. We evaluate our wate…

Error-Guided Pose Augmentation: Enhancing Rehabilitation Exercise Assessment through Targeted Data Generation
Omar Sherif, Ali Hamdi
https://arxiv.org/abs/2506.09833

Error-Guided Pose Augmentation: Enhancing Rehabilitation Exercise Assessment through Targeted Data Generation
Effective rehabilitation assessment is essential for monitoring patient progress, particularly in home-based settings. Existing systems often face challenges such as data imbalance and difficulty detecting subtle movement errors. This paper introduces Error-Guided Pose Augmentation (EGPA), a method that generates synthetic skeleton data by simulating clinically relevant movement mistakes. Unlike standard augmentation techniques, EGPA targets biomechanical errors observed in rehabilitation. Comb…

This https://arxiv.org/abs/2410.00117 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

An Overview of the Burer-Monteiro Method for Certifiable Robot Perception
This paper presents an overview of the Burer-Monteiro method (BM), a technique that has been applied to solve robot perception problems to certifiable optimality in real-time. BM is often used to solve semidefinite programming relaxations, which can be used to perform global optimization for non-convex perception problems. Specifically, BM leverages the low-rank structure of typical semidefinite programs to dramatically reduce the computational cost of performing optimization. This paper discus…

This https://arxiv.org/abs/2405.20771 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Towards Black-Box Membership Inference Attack for Diffusion Models
Given the rising popularity of AI-generated art and the associated copyright concerns, identifying whether an artwork was used to train a diffusion model is an important research topic. The work approaches this problem from the membership inference attack (MIA) perspective. We first identify the limitation of applying existing MIA methods for proprietary diffusion models: the required access of internal U-nets. To address the above problem, we introduce a novel membership inference attack metho…

This https://arxiv.org/abs/2409.18122 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

RT-GuIDE: Real-Time Gaussian splatting for Information-Driven Exploration
We propose a framework for active mapping and exploration that leverages Gaussian splatting for constructing dense maps. Further, we develop a GPU-accelerated motion planning algorithm that can exploit the Gaussian map for real-time navigation. The Gaussian map constructed onboard the robot is optimized for both photometric and geometric quality while enabling real-time situational awareness for autonomy. We show through simulation experiments that our method yields comparable Peak Signal-to-No…

This https://arxiv.org/abs/2404.08793 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models
The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential misuse. Addressing these concerns necessitates a comprehensive analysis of jailbreak prompts to evaluate LLMs' defensive capabilities and identify potential weaknesses. However, the complexity of evaluating jailbreak performance and understanding prompt char…

This https://arxiv.org/abs/2409.17641 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Scene Exploration by Vision-Language Models
Active perception enables robots to dynamically gather information by adjusting their viewpoints, a crucial capability for interacting with complex, partially observable environments. In this paper, we present AP-VLM, a novel framework that combines active perception with a Vision-Language Model (VLM) to guide robotic exploration and answer semantic queries. Using a 3D virtual grid overlaid on the scene and orientation adjustments, AP-VLM allows a robotic manipulator to intelligently select opt…

This https://arxiv.org/abs/2409.12949 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Learning-based Quadcopter Controller with Extreme Adaptation
This paper introduces a learning-based low-level controller for quadcopters, which adaptively controls quadcopters with significant variations in mass, size, and actuator capabilities. Our approach leverages a combination of imitation learning and reinforcement learning, creating a fast-adapting and general control framework for quadcopters that eliminates the need for precise model estimation or manual tuning. The controller estimates a latent representation of the vehicle's system parameters …

This https://arxiv.org/abs/2409.10283 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

ASMA: An Adaptive Safety Margin Algorithm for Vision-Language Drone Navigation via Scene-Aware Control Barrier Functions
In the rapidly evolving field of vision-language navigation (VLN), ensuring safety for physical agents remains an open challenge. For a human-in-the-loop language-operated drone to navigate safely, it must understand natural language commands, perceive the environment, and simultaneously avoid hazards in real time. Control Barrier Functions (CBFs) are formal methods that enforce safe operating conditions. Model Predictive Control (MPC) is an optimization framework that plans a sequence of futur…

This https://arxiv.org/abs/2409.06990 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SIS: Seam-Informed Strategy for T-shirt Unfolding
Seams are information-rich components of garments. The presence of different types of seams and their combinations helps to select grasping points for garment handling. In this paper, we propose a new Seam-Informed Strategy (SIS) for finding actions for handling a garment, such as grasping and unfolding a T-shirt. Candidates for a pair of grasping points for a dual-arm manipulator system are extracted using the proposed Seam Feature Extraction Method (SFEM). A pair of grasping points for the ro…

This https://arxiv.org/abs/2309.04154 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Modeling, control, and stiffness regulation of layer jamming-based continuum robots
Continuum robots with variable compliance have gained significant attention due to their adaptability in unstructured environments. Among various stiffness modulation techniques, layer jamming (LJ) provides a simple yet effective approach for achieving tunable stiffness. However, most existing LJ-based continuum robot models rely on static or quasi-static approximations, lacking a rigorous control-oriented dynamical formulation. Consequently, they are unsuitable for real-time control tasks requ…