Tootfinder

This is a public service announcement for all the dollar-store Sherlock Holmes’s out there who clearly have nothing better to do than to concoct conspiracy theories about people from Gaza on the fediverse who are faced with genocide and famine:
Stop.
Have some humanity.
Case in point, do not do what Daniel (@helmet91@mastodon.social) is doing here:

SpecifyUI: Supporting Iterative UI Design Intent Expression through Structured Specifications and Generative AI
Yunnong Chen, Chengwei Shi, Liuqing Chen
https://arxiv.org/abs/2509.07334

SpecifyUI: Supporting Iterative UI Design Intent Expression through Structured Specifications and Generative AI
Large language models (LLMs) promise to accelerate UI design, yet current tools struggle with two fundamentals: externalizing designers' intent and controlling iterative change. We introduce SPEC, a structured, parameterized, hierarchical intermediate representation that exposes UI elements as controllable parameters. Building on SPEC, we present SpecifyUI, an interactive system that extracts SPEC from UI references via region segmentation and vision-language models, composes UIs across multipl…

LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings
Benjamin F. Maier, Ulf Aslak, Luca Fiaschi, Nina Rismal, Kemble Fletcher, Christian C. Luhmann, Robbie Dow, Kli Pappas, Thomas V. Wiecki
https://arxiv.org/abs/2510.08338

LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings
Consumer research costs companies billions annually yet suffers from panel biases and limited scale. Large language models (LLMs) offer an alternative by simulating synthetic consumers, but produce unrealistic response distributions when asked directly for numerical ratings. We present semantic similarity rating (SSR), a method that elicits textual responses from LLMs and maps these to Likert distributions using embedding similarity to reference statements. Testing on an extensive dataset compr…

Enhancing Low-Altitude Airspace Security: MLLM-Enabled UAV Intent Recognition
Guangyu Lei, Tianhao Liang, Yuqi Ping, Xinglin Chen, Longyu Zhou, Junwei Wu, Xiyuan Zhang, Huahao Ding, Xingjian Zhang, Weijie Yuan, Tingting Zhang, Qinyu Zhang
https://arxiv.org/abs/2509.06312

Enhancing Low-Altitude Airspace Security: MLLM-Enabled UAV Intent Recognition
The rapid development of the low-altitude economy emphasizes the critical need for effective perception and intent recognition of non-cooperative unmanned aerial vehicles (UAVs). The advanced generative reasoning capabilities of multimodal large language models (MLLMs) present a promising approach in such tasks. In this paper, we focus on the combination of UAV intent recognition and the MLLMs. Specifically, we first present an MLLM-enabled UAV intent recognition architecture, where the multimo…

Airy: Reading Robot Intent through Height and Sky
Baoyang Chen, Xian Xu, Huamin Qu
https://arxiv.org/abs/2510.08381 https://arxiv.org/pdf/2510.08381…

Airy: Reading Robot Intent through Height and Sky
As industrial robots move into shared human spaces, their opaque decision making threatens safety, trust, and public oversight. This artwork, Airy, asks whether complex multi agent AI can become intuitively understandable by staging a competition between two reinforcement trained robot arms that snap a bedsheet skyward. Building on three design principles, competition as a clear metric (who lifts higher), embodied familiarity (audiences recognize fabric snapping), and sensor to sense mapping (r…

Unified Representation Learning for Multi-Intent Diversity and Behavioral Uncertainty in Recommender Systems
Wei Xu, Jiasen Zheng, Junjiang Lin, Mingxuan Han, Junliang Du
https://arxiv.org/abs/2509.04694

Unified Representation Learning for Multi-Intent Diversity and Behavioral Uncertainty in Recommender Systems
This paper addresses the challenge of jointly modeling user intent diversity and behavioral uncertainty in recommender systems. A unified representation learning framework is proposed. The framework builds a multi-intent representation module and an uncertainty modeling mechanism. It extracts multi-granularity interest structures from user behavior sequences. Behavioral ambiguity and preference fluctuation are captured using Bayesian distribution modeling. In the multi-intent modeling part, the…

Going from: "I wanted the computer to do this well-defined task, and it did it, and saved me some time because I can verify that what it did is aligned with my intent, and correct."

Going to: "I asked the computer random stuff and I'm 'obeying' without knowing why or how the output came about. I don't care much about understanding my own will anymore as long as the software says 'AI' on the label."

Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
Inbal Bolshinsky, Shani Kupiec, Almog Sasson, Yehudit Aperstein, Alexander Apartsin
https://arxiv.org/abs/2509.05006

Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
In the era of conversational AI, generating accurate and contextually appropriate service responses remains a critical challenge. A central question remains: Is explicit intent recognition a prerequisite for generating high-quality service responses, or can models bypass this step and produce effective replies directly? This paper conducts a rigorous comparative study to address this fundamental design dilemma. Leveraging two publicly available service interaction datasets, we benchmark several…

Generalized User-Oriented Image Semantic Coding Empowered by Large Vision-Language Model
Sin-Yu Huang, Vincent W. S. Wong
https://arxiv.org/abs/2509.08913 https://

Generalized User-Oriented Image Semantic Coding Empowered by Large Vision-Language Model
Semantic communication has shown outstanding performance in preserving the overall source information in wireless transmission. For semantically rich content such as images, human users are often interested in specific regions depending on their intent. Moreover, recent semantic coding models are mostly trained on specific datasets. However, real-world applications may involve images out of the distribution of training dataset, which makes generalization a crucial but largely unexplored problem…

Generative AI as a Safety Net for Survey Question Refinement
Erica Ann Metheney, Lauren Yehle
https://arxiv.org/abs/2509.08702 https://arxiv.org/pdf/2509.0…

Generative AI as a Safety Net for Survey Question Refinement
Writing survey questions that easily and accurately convey their intent to a variety of respondents is a demanding and high-stakes task. Despite the extensive literature on best practices, the number of considerations to keep in mind is vast and even small errors can render collected data unusable for its intended purpose. The process of drafting initial questions, checking for known sources of error, and developing solutions to those problems requires considerable time, expertise, and financia…

#Oakland #police chief announces intent to resign after less than two years since arriving from Lubbock TX.
"To be number 15 in the last 25 years, since I have been here. Every time a chief takes the helm, it is just a matter of time when it will occur. And that's the sad part of the condition of the police…

Oakland Police Chief Floyd Mitchell announces he's stepping down
Oakland Police Chief Floyd Mitchell announced he's stepping down, effective Dec. 5. "It has been an honor to serve the Oakland community, and I am grateful for the support I've received from the residents."

#SanFrancisco's #Mayor seeems intent of fostering community & trust? Seems a bit out of the blue and disrespectful, but I am sure there is a robust reason for treating community groups like this. /s

Mayor Lurie ends 20-year ‘heritage night’ partnership with indigenous group
American Indian Cultural Center says cutting it from Native American Heritage Night "excludes the very community the event is meant to honor."

#SanFrancisco's #Mayor seeems intent of fostering community & trust? Seems a bit out of the blue and disrespectful, but I am sure there is a robust reason for treating community groups like this. /s

Mayor Lurie ends 20-year ‘heritage night’ partnership with indigenous group
American Indian Cultural Center says cutting it from Native American Heritage Night "excludes the very community the event is meant to honor."

🇺🇦 #NowPlaying on KEXP's #SeekAndDestroy
Hidden Intent:
🎵 The Ruins
#HiddenIntent
https://hiddenintent.bandcamp.com/track/the-ruins
https://open.spotify.com/track/2IM1FhA6XJ8b90d85t96N3

Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence
Yerin Ryu, Inseop Shin, Chanwoo Kim
https://arxiv.org/abs/2509.07038 https://arxiv…

Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence
Controllable Singing Voice Synthesis (SVS) aims to generate expressive singing voices reflecting user intent. While recent SVS systems achieve high audio quality, most rely on probabilistic modeling, limiting precise control over attributes such as dynamics. We address this by focusing on dynamic control--temporal loudness variation essential for musical expressiveness--and explicitly condition the SVS model on energy sequences extracted from ground-truth spectrograms, reducing annotation costs…

Learning from Limited Multi-Phase CT: Dual-Branch Prototype-Guided Framework for Early Recurrence Prediction in HCC
Hsin-Pei Yu, Si-Qin Lyu, Yi-Hsien Hsieh, Weichung Wang, Tung-Hung Su, Jia-Horng Kao, Che Lin
https://arxiv.org/abs/2510.07347

Learning from Limited Multi-Phase CT: Dual-Branch Prototype-Guided Framework for Early Recurrence Prediction in HCC
Early recurrence (ER) prediction after curative-intent resection remains a critical challenge in the clinical management of hepatocellular carcinoma (HCC). Although contrast-enhanced computed tomography (CT) with full multi-phase acquisition is recommended in clinical guidelines and routinely performed in many tertiary centers, complete phase coverage is not consistently available across all institutions. In practice, single-phase portal venous (PV) scans are often used alone, particularly in s…

Smart Contract Intent Detection with Pre-trained Programming Language Model
Youwei Huang, Jianwen Li, Sen Fang, Yao Li, Peng Yang, Bin Hu, Tao Zhang
https://arxiv.org/abs/2508.20086

Smart Contract Intent Detection with Pre-trained Programming Language Model
Malicious intent in smart contract development can lead to substantial economic losses. SmartIntentNN is a deep learning model specifically designed to identify unsafe intents in smart contracts. This model integrates the Universal Sentence Encoder, a K-means clustering-based intent highlighting mechanism, and a Bidirectional Long Short-Term Memory network for multi-label classification, achieving an F1 of 0.8633 in distinguishing ten different intent categories. In this study, we present an up…

I keep thinking what would be an appropriate search results page for a single punctuation mark - and I think I'd expect a dictionary definition? Maybe articles on where and how to use it?
But honestly I kinda just wish Google would tell me "hey, did you search this by mistake?” and not show me any results at all.
There's no search intent here, folks. Why are we pretending that there is?

Instacart integrates its retail data with TikTok Ads Manager, letting consumer packaged goods advertisers target audiences and measure conversions within TikTok (Anu Adegbola/Search Engine Land)
https://searchengineland.com/instacart-tiktok-ads-manager-463072

Instacart brings retail media targeting to TikTok Ads Manager
The partnership lets CPG advertisers use Instacart’s retail data to target high-intent shoppers and track purchases directly within TikTok.

This would make it dramatically more difficult to fund both affordable housing and transit in California. The Howard Jarvis people want to pull up the drawbridge and make us an even more exclusionary, car-dependent and on-fire state. https://calmatters.org/housing/2025/10

Giants' Abdul Carter holding himself accountable after quiet start to rookie season: 'I gotta do better' https://www.nfl.com/news/giants-abdul-carter-holding-himself-accountable-after-quiet-start-to-rookie-se…

LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce
Yipeng Zhang, Bowen Liu, Xiaoshuang Zhang, Aritra Mandal, Zhe Wu, Canran Xu
https://arxiv.org/abs/2509.05570

LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce
User queries in e-commerce search are often vague, short, and underspecified, making it difficult for retrieval systems to match them accurately against structured product catalogs. This challenge is amplified by the one-to-many nature of user intent, where a single query can imply diverse and competing needs. Existing methods, including neural query expansion and prompting-based LLM approaches, fall short in real-world settings: they struggle to capture nuanced user intent, often generate outp…

Mitigating Jailbreaks with Intent-Aware LLMs
Wei Jie Yeo, Ranjan Satapathy, Erik Cambria
https://arxiv.org/abs/2508.12072 https://arxiv.org/pdf/2508.12072

Mitigating Jailbreaks with Intent-Aware LLMs
Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose Intent-FT, a simple and lightweight fine-tuning approach that explicitly trains LLMs to infer the underlying intent of an instruction before responding. By fine-tuning on a targeted set of adversarial instructions, Intent-FT enables LLMs to generalize intent ded…

The problem with "you can just do things" is that other people can also just do things. You can get into an arms race of just doing things, or learn how to build shared intent.
One of those approaches is masculine and exciting. The other one actually works.
Guess which one AI-powered design & development tools encourage?

The social lives of ideas (Don't Just Do Things, Part 3)
No amount of outputs will help maintain unbroken intent all the way through to delivery.

Bridging Language Models and Formal Methods for Intent-Driven Optical Network Design
Anis Bekri, Amar Abane, Abdella Battou, Saddek Bensalem
https://arxiv.org/abs/2509.22834 htt…

Bridging Language Models and Formal Methods for Intent-Driven Optical Network Design
Intent-Based Networking (IBN) aims to simplify network management by enabling users to specify high-level goals that drive automated network design and configuration. However, translating informal natural-language intents into formally correct optical network topologies remains challenging due to inherent ambiguity and lack of rigor in Large Language Models (LLMs). To address this, we propose a novel hybrid pipeline that integrates LLM-based intent parsing, formal methods, and Optical Retrieval…

RINSER: Accurate API Prediction Using Masked Language Models
Muhammad Ejaz Ahmed, Christopher Cody, Muhammad Ikram, Sean Lamont, Alsharif Abuadbba, Seyit Camtepe, Surya Nepal, Muhammad Ali Kaafar
https://arxiv.org/abs/2509.04887

RINSER: Accurate API Prediction Using Masked Language Models
Malware authors commonly use obfuscation to hide API identities in binary files, making analysis difficult and time-consuming for a human expert to understand the behavior and intent of the program. Automatic API prediction tools are necessary to efficiently analyze unknown binaries, facilitating rapid malware triage while reducing the workload on human analysts. In this paper, we present RINSER (AccuRate API predictioN using maSked languagE model leaRning), an automated framework for predictin…

LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition
Qianrui Zhou, Hua Xu, Yifan Wang, Xinzhi Dong, Hanlei Zhang
https://arxiv.org/abs/2509.01337 https://

LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition
Understanding human intents from multimodal signals is critical for analyzing human behaviors and enhancing human-machine interactions in real-world scenarios. However, existing methods exhibit limitations in their modality-level reliance, constraining relational reasoning over fine-grained semantics for complex intent understanding. This paper proposes a novel LLM-Guided Semantic Relational Reasoning (LGSRR) method, which harnesses the expansive knowledge of large language models (LLMs) to est…

New #Bandcamp purchase!
Imperium Delirium by Shadow Of Intent
#BandcampFriday

Sam Altman signs a letter of intent with Samsung and SK Hynix to supply Stargate; Samsung and SK Hynix say demand from OpenAI could hit 900K wafers per month (Yoolim Lee/Bloomberg)
https://www.bloomberg.com/news/articles/2025-1…

VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code
Lingfei Zeng, Fengdi Che, Xuhan Huang, Fei Ye, Xu Xu, Binhang Yuan, Jie Fu
https://arxiv.org/abs/2510.06296

VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code
Formal verification is the next frontier for ensuring the correctness of code generated by Large Language Models (LLMs). While methods that co-generate code and formal specifications in formal languages, like Dafny, can, in principle, prove alignment with user intent, progress is bottlenecked by specification quality evaluation. Current benchmarks rely on matching against ground-truth specifications, a manual and expertise-intensive process that has limited existing datasets to a few hundred si…

Cyber Physical Awareness via Intent-Driven Threat Assessment: Enhanced Space Networks with Intershell Links
Selen Gecgel Cetin, Tolga Ovatman, Gunes Karabulut Kurt
https://arxiv.org/abs/2508.16314

Cyber Physical Awareness via Intent-Driven Threat Assessment: Enhanced Space Networks with Intershell Links
This letter addresses essential aspects of threat assessment by proposing intent-driven threat models that incorporate both capabilities and intents. We propose a holistic framework for cyber physical awareness (CPA) in space networks, pointing out that analyzing reliability and security separately can lead to overfitting on system-specific criteria. We structure our proposed framework in three main steps. First, we suggest an algorithm that extracts characteristic properties of the received si…

Emojis get no love. I am, I’m afraid, a curmudgeon and will use whatever emojis I damn well please whenever I damn well please. Used with intent, they enrich written communication and anyone who disagrees needs to chill. 😇 https://www.

An HPC-Inspired Blueprint for a Technology-Agnostic Quantum Middle Layer
Stefano Markidis, Gilbert Netzer, Luca Pennati, Ivy Peng
https://arxiv.org/abs/2510.07079 https://

An HPC-Inspired Blueprint for a Technology-Agnostic Quantum Middle Layer
We present a blueprint for a quantum middle layer that supports applications across various quantum technologies. Inspired by concepts and abstractions from HPC libraries and middleware, our design is backend-neutral and context-aware. A program only needs to specify its intent once as typed data and operator descriptors. It declares what the quantum registers mean and which logical transformations are required, without committing to gates, pulses, continuous-variable routines, or anneal backen…

Members of Israeli government have ‘genocidal intent’, says UK minister
Good.
But at this rate the UK government will say it's a genocide just as the last Palestinian is expelled.
https://nation.cymru/news/members-of-israeli-gover…

TWIST: Training-free and Label-free Short Text Clustering through Iterative Vector Updating with LLMs
I-Fan Lin, Faegheh Hasibi, Suzan Verberne
https://arxiv.org/abs/2510.06747 …

TWIST: Training-free and Label-free Short Text Clustering through Iterative Vector Updating with LLMs
In this paper, we propose a training-free and label-free method for short text clustering that can be used on top of any existing embedder. In the context of customer-facing chatbots, companies are dealing with large amounts of user utterances that need to be clustered according to their intent. In these commercial settings, no labeled data is typically available, and the number of clusters is not known. Our method is based on iterative vector updating: it constructs sparse vectors based on rep…

Exploring the Feasibility of Gaze-Based Navigation Across Path Types
Yichuan Zhang, Liangyuting Zhang, Xuning Hu, Yong Yue, Hai-Ning Liang
https://arxiv.org/abs/2510.07184 https…

Exploring the Feasibility of Gaze-Based Navigation Across Path Types
Gaze input, as a modality inherently conveying user intent, offers intuitive and immersive experiences in extended reality (XR). With eye-tracking now being a standard feature in modern XR headsets, gaze has been extensively applied to tasks such as selection, text entry, and object manipulation. However, gaze based navigation despite being a fundamental interaction task remains largely underexplored. In particular, little is known about which path types are well suited for gaze navigation and …

This is bizarre - I made a typo and accidentally ran a #Google search for a comma. Not the word, the punctuation mark.
And yet, somehow, Google thinks that is:
1. A valid enough search to be showing a bazillion results
2. A search that needs short-form vertical videos at the top from a bunch of white women (who are they? Why them? What in the world is relevant to a singular punctuation mark that makes them pull up these videos?)
3. A search with enough inferred intent to show me a whole Q&A interface?
I know we complain about the state of #search online a lot these days and I've been part of the #SEO industry for years but something like this is so blatantly ridiculous it's hard not to stop and wonder.... what the actual fuck?

OVGrasp: Open-Vocabulary Grasping Assistance via Multimodal Intent Detection
Chen Hu, Shan Luo, Letizia Gionfrida
https://arxiv.org/abs/2509.04324 https://…

OVGrasp: Open-Vocabulary Grasping Assistance via Multimodal Intent Detection
Grasping assistance is essential for restoring autonomy in individuals with motor impairments, particularly in unstructured environments where object categories and user intentions are diverse and unpredictable. We present OVGrasp, a hierarchical control framework for soft exoskeleton-based grasp assistance that integrates RGB-D vision, open-vocabulary prompts, and voice commands to enable robust multimodal interaction. To enhance generalization in open environments, OVGrasp incorporates a visi…

When Names Disappear: Revealing What LLMs Actually Understand About Code
Cuong Chi Le, Minh V. T. Pham, Cuong Duc Van, Hoang N. Phan, Huy N. Phan, Tien N. Nguyen
https://arxiv.org/abs/2510.03178

When Names Disappear: Revealing What LLMs Actually Understand About Code
Large Language Models (LLMs) achieve strong results on code tasks, but how they derive program meaning remains unclear. We argue that code communicates through two channels: structural semantics, which define formal behavior, and human-interpretable naming, which conveys intent. Removing the naming channel severely degrades intent-level tasks such as summarization, where models regress to line-by-line descriptions. Surprisingly, we also observe consistent reductions on execution tasks that shou…

Retentive Relevance: Capturing Long-Term User Value in Recommendation Systems
Saeideh Bakhshi, Phuong Mai Nguyen, Robert Schiller, Tiantian Xu, Pawan Kodandapani, Andrew Levine, Cayman Simpson, Qifan Wang
https://arxiv.org/abs/2510.07621

Retentive Relevance: Capturing Long-Term User Value in Recommendation Systems
Recommendation systems have traditionally relied on short-term engagement signals, such as clicks and likes, to personalize content. However, these signals are often noisy, sparse, and insufficient for capturing long-term user satisfaction and retention. We introduce Retentive Relevance, a novel content-level survey-based feedback measure that directly assesses users' intent to return to the platform for similar content. Unlike other survey measures that focus on immediate satisfaction, Retenti…

Sense of Belonging and Intent to Persist: Mediating Role of Motivation and Moderating Role of Gender in Physics and Astronomy Graduate Students
Swagata Sarkar, N. Sanjay Rebello
https://arxiv.org/abs/2508.20948

Sense of Belonging and Intent to Persist: Mediating Role of Motivation and Moderating Role of Gender in Physics and Astronomy Graduate Students
This study investigates how graduate students' sense of belonging (SB) influences their intent to persist (IP) in physics and astronomy programs, and how this relationship is shaped by the basic psychological needs that drive motivation-autonomy, competence, and relatedness-as well as gender. Grounded in self-determination theory, the analysis treats these three needs as mediators and gender as a moderator. A quantitative survey was administered to graduate students in the Department of Physics…

SIG-Chat: Spatial Intent-Guided Conversational Gesture Generation Involving How, When and Where
Yiheng Huang, Junran Peng, Silei Shen, Jingwei Yang, ZeJi Wei, ChenCheng Bai, Yonghao He, Wei Sui, Muyi Sun, Yan Liu, Xu-Cheng Yin, Man Zhang, Zhaoxiang Zhang, Chuanchen Luo
https://arxiv.org/abs/2509.23852

SIG-Chat: Spatial Intent-Guided Conversational Gesture Generation Involving How, When and Where
The accompanying actions and gestures in dialogue are often closely linked to interactions with the environment, such as looking toward the interlocutor or using gestures to point to the described target at appropriate moments. Speech and semantics guide the production of gestures by determining their timing (WHEN) and style (HOW), while the spatial locations of interactive objects dictate their directional execution (WHERE). Existing approaches either rely solely on descriptive language to gen…

Day 5: Robin Wall Kimmerer
I'm taking these liberty of changing my hashtag and expanding the intent of this list to include all non-men, although Kimerer is a woman so I'll get to more gender diversity later... I've also started planning this out more and realized that I may continue a bit beyond 20...
In any case, Robin Wall Kimmerer is an Indigenous academic biologist and excellent non-fiction author whose work touches on Potawotomi philosophy, colonialism (including in academic spaces), and ideas for a better future. Anyone interested in ecology, conservation, or decolonization in North America will probably be impressed by her work and the rich connections she weaves between academic ecology and Indigenous knowledge offer a critical opportunity to expand your understanding of the world if like me you were raised deeply enmeshed in "Western" scientific tradition. I suppose a little background in skepticism helped prepare me to respect her writing, but I don't think that's essential.
I've only read "Braiding Sweetgrass," but "Gathering Moss" and her more recent "The Serviceberry" are high on my to-read list, despite my predilection for fiction. Kimmerer incorporates a backbone of fascinating anecdotes into "Braiding Sweetgrass" that makes it surprisingly easy reading for a work that's philosophical at its core. She also pulls off an impressive braided organization to the whole thing, weaving together disparate knowledges in a way that lets you see both their contradictions and their connections.
The one criticism I've seen of her work is that it's not sufficiently connected to other Indigenous philosophers & writers, and that it's perhaps too comfortable of a read for colonizers, and that seems valid to me, even though (perhaps because I am a colonizer) I still find her book important.
An excellent author in any case, and one doing concrete ideological work towards a better world.
#20AuthorsNoMen

If you use Bandcamp, you can follow me too #BandcampFriday #Bandcamp

The comments are *overwhelmingly* anti-Bezos, and many express their intent to cancel subscriptions (I access through a library subscription, canceled my own).
Opinion | Trump replacing the White House East Wing is not the end of the world - The Washington Post
https://wapo.st/4o2FcGU

Has anyone making this feature actually asked any accessibility experts and any disabled people if this is a good idea?
Because in practice this will give you terrible results, because AI can’t know what you intent do communicate with the image.
Even if it would give good results (it doesn’t and never will) and you’re too lazy to write alt text yourself, it would be better to do this on the receiving end where the disabled person could fine-tune generative alt text to their specific needs.
https://mastodon.social/@MonaApp/115406286404369048

SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval
Ren-Di Wu, Yu-Yen Lin, Huei-Fang Yang
https://arxiv.org/abs/2509.26330

SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval
Composed Image Retrieval (CIR) aims to retrieve target images that preserve the visual content of a reference image while incorporating user-specified textual modifications. Training-free zero-shot CIR (ZS-CIR) approaches, which require no task-specific training or labeled data, are highly desirable, yet accurately capturing user intent remains challenging. In this paper, we present SQUARE, a novel two-stage training-free framework that leverages Multimodal Large Language Models (MLLMs) to enha…

Packers eyed Trey Hendrickson in potential trade with Bengals before landing Micah Parsons, per report

https://www.cbssports.com/nfl/news/packers

I'm pretty sure the Fash intent is to Just Let The Poor Starve starting next week.
I hope to hell that I'm wrong.

LogPilot: Intent-aware and Scalable Alert Diagnosis for Large-scale Online Service Systems
Zhihan Jiang, Jinyang Liu, Yichen Li, Haiyu Huang, Xiao He, Tieying Zhang, Jianjun Chen, Yi Li, Rui Shi, Michael R. Lyu
https://arxiv.org/abs/2509.25874

LogPilot: Intent-aware and Scalable Alert Diagnosis for Large-scale Online Service Systems
Effective alert diagnosis is essential for ensuring the reliability of large-scale online service systems. However, on-call engineers are often burdened with manually inspecting massive volumes of logs to identify root causes. While various automated tools have been proposed, they struggle in practice due to alert-agnostic log scoping and the inability to organize complex data effectively for reasoning. To overcome these limitations, we introduce LogPilot, an intent-aware and scalable framework…

Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection
Zhengjia Wang, Qiang Sheng, Danding Wang, Beizhe Hu, Juan Cao
https://arxiv.org/abs/2509.01660

Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection
Fake news detection is an important and challenging task for defending online information integrity. Existing state-of-the-art approaches typically extract news semantic clues, such as writing patterns that include emotional words, stylistic features, etc. However, detectors tuned solely to such semantic clues can easily fall into surface detection patterns, which can shift rapidly in dynamic environments, leading to limited performance in the evolving news landscape. To address this issue, thi…

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement
Yuanzhe Shen, Zisu Huang, Zhengkang Guo, Yide Liu, Guanxu Chen, Ruicheng Yin, Xiaoqing Zheng, Xuanjing Huang
https://arxiv.org/abs/2508.20151

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement
The rapid advancement of large language models (LLMs) has driven their adoption across diverse domains, yet their ability to generate harmful content poses significant safety challenges. While extensive research has focused on mitigating harmful outputs, such efforts often come at the cost of excessively rejecting harmless prompts. Striking a balance among safety, over-refusal, and utility remains a critical challenge. In this work, we introduce IntentionReasoner, a novel safeguard mechanism th…

Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection
Yihao Guo, Haocheng Bian, Liutong Zhou, Ze Wang, Zhaoyi Zhang, Francois Kawala, Milan Dean, Ian Fischer, Yuantao Peng, Noyan Tokgozoglu, Ivan Barrientos, Riyaaz Shaik, Rachel Li, Chandru Venkataraman, Reza Shifteh Far, Moses Pawar, Venkat Sundaranatha, Michael Xu, Frank Chu

Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection
With the deployment of Large Language Models (LLMs) in interactive applications, online malicious intent detection has become increasingly critical. However, existing approaches fall short of handling diverse and complex user queries in real time. To address these challenges, we introduce ADRAG (Adversarial Distilled Retrieval-Augmented Guard), a two-stage framework for robust and efficient online malicious intent detection. In the training stage, a high-capacity teacher model is trained on adv…

Pointing-Guided Target Estimation via Transformer-Based Attention
Luca M\"uller, Hassan Ali, Philipp Allgeuer, Luk\'a\v{s} Gajdo\v{s}ech, Stefan Wermter
https://arxiv.org/abs/2509.05031

Pointing-Guided Target Estimation via Transformer-Based Attention
Deictic gestures, like pointing, are a fundamental form of non-verbal communication, enabling humans to direct attention to specific objects or locations. This capability is essential in Human-Robot Interaction (HRI), where robots should be able to predict human intent and anticipate appropriate responses. In this work, we propose the Multi-Modality Inter-TransFormer (MM-ITF), a modular architecture to predict objects in a controlled tabletop scenario with the NICOL robot, where humans indicate…

Reasoning-enhanced Query Understanding through Decomposition and Interpretation
Yunfei Zhong, Jun Yang, Yixing Fan, Jiafeng Guo, Lixin Su, Maarten de Rijke, Ruqing Zhang, Dawei Yin, Xueqi Cheng
https://arxiv.org/abs/2509.06544

Reasoning-enhanced Query Understanding through Decomposition and Interpretation
Accurate inference of user intent is crucial for enhancing document retrieval in modern search engines. While large language models (LLMs) have made significant strides in this area, their effectiveness has predominantly been assessed with short, keyword-based queries. As AI-driven search evolves, long-form queries with intricate intents are becoming more prevalent, yet they remain underexplored in the context of LLM-based query understanding (QU). To bridge this gap, we introduce ReDI: a Reaso…

A4FN: an Agentic AI Architecture for Autonomous Flying Networks
Andr\'e Coelho, Pedro Ribeiro, Helder Fontes, Rui Campos
https://arxiv.org/abs/2510.03829 https://

A4FN: an Agentic AI Architecture for Autonomous Flying Networks
This position paper presents A4FN, an Agentic Artificial Intelligence (AI) architecture for intent-driven automation in Flying Networks (FNs) using Unmanned Aerial Vehicles (UAVs) as access nodes. A4FN leverages Generative AI and Large Language Models (LLMs) to enable real-time, context-aware network control via a distributed agentic system. It comprises two components: the Perception Agent (PA), which semantically interprets multimodal input -- including imagery, audio, and telemetry data -- f…

"Refinery fires are part of life in the South Bay, which is home to several major oil production facilities." A statement suggesting maybe #FossilFools aren't competent to manage things safely. (Of course, their on the #ClimateCrisis seem more born of malicious intent, rather than …

"Refinery fires are part of life in the South Bay, which is home to several major oil production facilities." A statement suggesting maybe #FossilFools aren't competent to manage things safely. (Of course, their on the #ClimateCrisis seem more born of malicious intent, rather than …

Mitigating Category Imbalance: Fosafer System for the Multimodal Emotion and Intent Joint Understanding Challenge
Honghong Wang, Yankai Wang, Dejun Zhang, Jing Deng, Rong Zheng
https://arxiv.org/abs/2508.11362

Mitigating Category Imbalance: Fosafer System for the Multimodal Emotion and Intent Joint Understanding Challenge
This paper presents Fosafer approach to the Track 2 Mandarin in the Multimodal Emotion and Intent Joint Understandingchallenge, which focuses on achieving joint recognition of emotion and intent in Mandarin, despite the issue of category imbalance. To alleviate this issue, we use a variety of data augmentation techniques across text, video, and audio modalities. Additionally, we introduce the SampleWeighted Focal Contrastive loss, designed to address the challenges of recognizing minority class…

Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection
Ankan Mullick, Saransh Sharma, Abhik Jana, Pawan Goyal
https://arxiv.org/abs/2508.16122 https://

Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection
The rise of multimodal data, integrating text, audio, and visuals, has created new opportunities for studying multimodal tasks such as intent detection. This work investigates the effectiveness of Large Language Models (LLMs) and non-LLMs, including text-only and multi-modal models, in the multimodal intent detection task. Our study reveals that Mistral-7B, a text-only LLM, outperforms most competitive multimodal models by approximately 9% on MIntRec-1 and 4% on MIntRec2.0 datasets. This perfor…

Automated Program Repair of Uncompilable Student Code
Griffin Pitts, Aum Pandya, Darsh Rank, Tirth Bhatt, Muntasir Hoq, Bita Akram
https://arxiv.org/abs/2510.06187 https://

Automated Program Repair of Uncompilable Student Code
A significant portion of student programming submissions in CS1 learning environments are uncompilable, limiting their use in student modeling and downstream knowledge tracing. Traditional modeling pipelines often exclude these cases, discarding observations of student learning. This study investigates automated program repair as a strategy to recover uncompilable code while preserving students' structural intent for use in student modeling. Within this framework, we assess large language model…

PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance
Mengxiao Wang, Yuxuan Zhang, Guofei Gu
https://arxiv.org/abs/2508.20890 https://arx…

PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance
Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where adversaries manipulate model behavior through crafted inputs. As attackers continuously evolve with paraphrased, obfuscated, and even multi-task injection strategies, existing benchmarks are no longer sufficient to capture the full spectrum of emerging threats. …

Court filing: Elon Musk says he talked to Mark Zuckerberg in February about backing a $97.4B OpenAI bid, but neither he nor Meta signed a letter of intent (Financial Times)
https://www.ft.com/content/12494c21-e477-49c1-a2d7-683c12c281ea

I like progressive psytrance, symphonic death metal and avant-garde metal, the kind of noise that reminds me nothing matters and everything still moves in color.
Zoë Straub, Shadow of Intent, Avalon, Tristan, and Mad Tribe stay in the rotation because they actually sound like something real.
My #Bandcamp:

Evaluating NL2SQL via SQL2NL
Mohammadtaher Safarzadeh, Afshin Oroojlooyjadid, Dan Roth
https://arxiv.org/abs/2509.04657 https://arxiv.org/pdf/2509.04657

Evaluating NL2SQL via SQL2NL
Robust evaluation in the presence of linguistic variation is key to understanding the generalization capabilities of Natural Language to SQL (NL2SQL) models, yet existing benchmarks rarely address this factor in a systematic or controlled manner. We propose a novel schema-aligned paraphrasing framework that leverages SQL-to-NL (SQL2NL) to automatically generate semantically equivalent, lexically diverse queries while maintaining alignment with the original schema and intent. This enables the fi…

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions
Shiji Zhao, Ranjie Duan, Jiexi Liu, Xiaojun Jia, Fengxiang Wang, Cheng Wei, Ruoxi Cheng, Yong Xie, Chang Liu, Qing Guo, Jialing Tao, Hui Xue, Xingxing Wei
https://arxiv.org/abs/2509.01444…

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions
Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit strong reasoning skills, enabling them to infer user intent more accurately and respond appropriately. However, both LLMs and LRMs face the potential safety risks under jailbreak attacks, which raise concerns about their safety capabilities. Current safety evalua…

Spiking Neural Network Decoders of Finger Forces from High-Density Intramuscular Microelectrode Arrays
Farah Baracat, Agnese Grison, Dario Farina, Giacomo Indiveri, Elisa Donati
https://arxiv.org/abs/2509.04088

Spiking Neural Network Decoders of Finger Forces from High-Density Intramuscular Microelectrode Arrays
Restoring naturalistic finger control in assistive technologies requires the continuous decoding of motor intent with high accuracy, efficiency, and robustness. Here, we present a spike-based decoding framework that integrates spiking neural networks (SNNs) with motor unit activity extracted from high-density intramuscular microelectrode arrays. We demonstrate simultaneous and proportional decoding of individual finger forces from motor unit spike trains during isometric contractions at 15% of …

Can Synthetic Query Rewrites Capture User Intent Better than Humans in Retrieval-Augmented Generation?
JiaYing Zheng, HaiNan Zhang, Liang Pang, YongXin Tong, ZhiMing Zheng
https://arxiv.org/abs/2509.22325

Can Synthetic Query Rewrites Capture User Intent Better than Humans in Retrieval-Augmented Generation?
Multi-turn RAG systems often face queries with colloquial omissions and ambiguous references, posing significant challenges for effective retrieval and generation. Traditional query rewriting relies on human annotators to clarify queries, but due to limitations in annotators' expressive ability and depth of understanding, manually rewritten queries often diverge from those needed in real-world RAG systems, resulting in a gap between user intent and system response. We observe that high-quality …

I am very disappointed in #MayorLurie's action re TNC's on Market. It's clear the voters got snookered/[played by the language re "commercial vehicles" - where the clear intent was to allow deliveries to the businesses on Market. Conveniently ignoring the commercial licenses of TNCs - but hey, we need to keep the segment that can afford to use the TNCs happy, don't we…

Lurie is damaging transit, the environment—and democracy—on Market Street - 48 hills
The mayor is undoing the will of the voters and opening the street to Uber, Lyft, Waymo—and others are sure to follow

I am very disappointed in #MayorLurie's action re TNC's on Market. It's clear the voters got snookered/[played by the language re "commercial vehicles" - where the clear intent was to allow deliveries to the businesses on Market. Conveniently ignoring the commercial licenses of TNCs - but hey, we need to keep the segment that can afford to use the TNCs happy, don't we…

Lurie is damaging transit, the environment—and democracy—on Market Street - 48 hills
The mayor is undoing the will of the voters and opening the street to Uber, Lyft, Waymo—and others are sure to follow

Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction
Sagnik Basu, Shubham Prakash, Ashish Maruti Barge, Siddharth D Jaiswal, Abhisek Dash, Saptarshi Ghosh, Animesh Mukherjee
https://arxiv.org/abs/2510.00088

Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction
Large language models (LLMs) have been extensively used for legal judgment prediction tasks based on case reports and crime history. However, with a surge in the availability of large vision language models (VLMs), legal judgment prediction systems can now be made to leverage the images of the criminals in addition to the textual case reports/crime history. Applications built in this way could lead to inadvertent consequences and be used with malicious intent. In this work, we run an audit to i…

MINT-RVAE: Multi-Cues Intention Prediction of Human-Robot Interaction using Human Pose and Emotion Information from RGB-only Camera Data
Farida Mohsen, Ali Safa
https://arxiv.org/abs/2509.22573

MINT-RVAE: Multi-Cues Intention Prediction of Human-Robot Interaction using Human Pose and Emotion Information from RGB-only Camera Data
Efficiently detecting human intent to interact with ubiquitous robots is crucial for effective human-robot interaction (HRI) and collaboration. Over the past decade, deep learning has gained traction in this field, with most existing approaches relying on multimodal inputs, such as RGB combined with depth (RGB-D), to classify time-sequence windows of sensory data as interactive or non-interactive. In contrast, we propose a novel RGB-only pipeline for predicting human interaction intent with fra…

"Where does it hurt?" - Dataset and Study on Physician Intent Trajectories in Doctor Patient Dialogues
Tom R\"ohr, Soumyadeep Roy, Fares Al Mohamad, Jens-Michalis Papaioannou, Wolfgang Nejdl, Felix Gers, Alexander L\"oser
https://arxiv.org/abs/2508.19077

"Where does it hurt?" - Dataset and Study on Physician Intent Trajectories in Doctor Patient Dialogues
In a doctor-patient dialogue, the primary objective of physicians is to diagnose patients and propose a treatment plan. Medical doctors guide these conversations through targeted questioning to efficiently gather the information required to provide the best possible outcomes for patients. To the best of our knowledge, this is the first work that studies physician intent trajectories in doctor-patient dialogues. We use the `Ambient Clinical Intelligence Benchmark' (Aci-bench) dataset for our stu…

The DOJ says it will no longer target developers who create decentralized crypto platforms without criminal intent, as part of a regulatory retreat on crypto (Chris Prentice/Reuters)
https://www.reuters.com/sustainability/boa…

Agentic TinyML for Intent-aware Handover in 6G Wireless Networks
Alaa Saleh, Roberto Morabito, Sasu Tarkoma, Anders Lindgren, Susanna Pirttikangas, Lauri Lov\'en
https://arxiv.org/abs/2508.09147

Agentic TinyML for Intent-aware Handover in 6G Wireless Networks
As 6G networks evolve into increasingly AI-driven, user-centric ecosystems, traditional reactive handover mechanisms demonstrate limitations, especially in mobile edge computing and autonomous agent-based service scenarios. This manuscript introduces WAAN, a cross-layer framework that enables intent-aware and proactive handovers by embedding lightweight TinyML agents as autonomous, negotiation-capable entities across heterogeneous edge nodes that contribute to intent propagation and network ada…

AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
Mingdai Yang, Nurendra Choudhary, Jiangshu Du, Edward W. Huang, Philip S. Yu, Karthik Subbian, Danai Kourta
https://arxiv.org/abs/2510.05598

AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
Recent agent-based recommendation frameworks aim to simulate user behaviors by incorporating memory mechanisms and prompting strategies, but they struggle with hallucinating non-existent items and full-catalog ranking. Besides, a largely underexplored opportunity lies in leveraging LLMs'commonsense reasoning to capture user intent through substitute and complement relationships between items, which are usually implicit in datasets and difficult for traditional ID-based recommenders to capture. …

Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm
Zhensu Sun, Chengran Yang, Chao Peng, Pengfei Gao, Xiaoning Du, Li Li, David Lo
https://arxiv.org/abs/2509.24637

Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm
Large Language Models (LLMs) have significantly advanced code completion, yet they often fail when the developer's intent is underspecified in the code context. To address this, developers usually add natural language instructions (e.g., comments) into the code context to clarify their intent. However, existing code LLMs applied for code completion systems merely undergo a fill-in-the-middle (FIM) pre-training, which struggles to leverage this information effectively due to the lack of instruct…

Adaptive Motion Planning via Contact-Based Intent Inference for Human-Robot Collaboration
Jiurun Song, Xiao Liang, Minghui Zheng
https://arxiv.org/abs/2510.08811 https://…

Adaptive Motion Planning via Contact-Based Intent Inference for Human-Robot Collaboration
Human-robot collaboration (HRC) requires robots to adapt their motions to human intent to ensure safe and efficient cooperation in shared spaces. Although large language models (LLMs) provide high-level reasoning for inferring human intent, their application to reliable motion planning in HRC remains challenging. Physical human-robot interaction (pHRI) is intuitive but often relies on continuous kinesthetic guidance, which imposes burdens on operators. To address these challenges, a contact-inf…

Mouse-Guided Gaze: Semi-Supervised Learning of Intention-Aware Representations for Reading Detection
Seongsil Heo, Roberto Manduchi
https://arxiv.org/abs/2509.19574 https://

Mouse-Guided Gaze: Semi-Supervised Learning of Intention-Aware Representations for Reading Detection
Understanding user intent during magnified reading is critical for accessible interface design. Yet magnification collapses visual context and forces continual viewport dragging, producing fragmented, noisy gaze and obscuring reading intent. We present a semi-supervised framework that learns intention-aware gaze representations by leveraging mouse trajectories as weak supervision. The model is first pretrained to predict mouse velocity from unlabeled gaze, then fine-tuned to classify reading ve…

AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Yangtian Zi, Zixuan Wu, Aleksander Boruch-Gruszecki, Jonathan Bell, Arjun Guha
https://arxiv.org/abs/2509.21891

AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the changes that implement that intent. However, much of the previously collected data is noisy: commit messages are terse, human-written commits commingle several unrelated edits, and many commits come from simple, rule-based bots. The recent adoption of softwar…

Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline
Haiyang Li, Yaxiong Wang, Lianwei Wu, Lechao Cheng, Zhun Zhong
https://arxiv.org/abs/2509.25991

Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline
In recent years, detecting fake multimodal content on social media has drawn increasing attention. Two major forms of deception dominate: human-crafted misinformation (e.g., rumors and misleading posts) and AI-generated content produced by image synthesis models or vision-language models (VLMs). Although both share deceptive intent, they are typically studied in isolation. NLP research focuses on human-written misinformation, while the CV community targets AI-generated artifacts. As a result, e…

A Novel Integrated Architecture for Intent Based Approach and Zero Touch Networks
Neelam Gupta, Dibakar Das, Tamizhelakkiya K, Uma Maheswari Natarajan, Sharvari Ravindran, Komal Sharma, Jyotsna Bapat, Debabrata Das
https://arxiv.org/abs/2509.21026

A Novel Integrated Architecture for Intent Based Approach and Zero Touch Networks
The transition to Sixth Generation (6G) networks presents challenges in managing quality of service (QoS) of diverse applications and achieving Service Level Agreements (SLAs) under varying network conditions. Hence, network management must be automated with the help of Machine Learning (ML) and Artificial Intelligence (AI) to achieve real-time requirements. Zero touch network (ZTN) is one of the frameworks to automate network management with mechanisms such as closed loop control to ensure tha…

Designing a Lightweight GenAI Interface for Visual Data Analysis
Ratanond Koonchanok, Alex Kale, Khairi Reda
https://arxiv.org/abs/2509.02878 https://arxiv…

Designing a Lightweight GenAI Interface for Visual Data Analysis
Recent advances in Generative AI have transformed how users interact with data analysis through natural language interfaces. However, many systems rely too heavily on LLMs, creating risks of hallucination, opaque reasoning, and reduced user control. We present a hybrid visual analysis system that integrates GenAI in a constrained, high-level role to support statistical modeling while preserving transparency and user agency. GenAI translates natural language intent into formal statistical formul…

Utilizing Vision-Language Models as Action Models for Intent Recognition and Assistance
Cesar Alan Contreras, Manolis Chiou, Alireza Rastegarpanah, Michal Szulik, Rustam Stolkin
https://arxiv.org/abs/2508.11093

Utilizing Vision-Language Models as Action Models for Intent Recognition and Assistance
Human-robot collaboration requires robots to quickly infer user intent, provide transparent reasoning, and assist users in achieving their goals. Our recent work introduced GUIDER, our framework for inferring navigation and manipulation intents. We propose augmenting GUIDER with a vision-language model (VLM) and a text-only language model (LLM) to form a semantic prior that filters objects and locations based on the mission prompt. A vision pipeline (YOLO for object detection and the Segment An…

Multi-Intent Recognition in Dialogue Understanding: A Comparison Between Smaller Open-Source LLMs
Adnan Ahmad, Philine Kowol, Stefan Hillmann, Sebastian M\"oller
https://arxiv.org/abs/2509.10010

Multi-Intent Recognition in Dialogue Understanding: A Comparison Between Smaller Open-Source LLMs
In this paper, we provide an extensive analysis of multi-label intent classification using Large Language Models (LLMs) that are open-source, publicly available, and can be run in consumer hardware. We use the MultiWOZ 2.1 dataset, a benchmark in the dialogue system domain, to investigate the efficacy of three popular open-source pre-trained LLMs, namely LLama2-7B-hf, Mistral-7B-v0.1, and Yi-6B. We perform the classification task in a few-shot setup, giving 20 examples in the prompt with some i…

SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
Qinjian Zhao, Jiaqi Wang, Zhiqiang Gao, Zhihao Dou, Belal Abuhaija, Kaizhu Huang
https://arxiv.org/abs/2509.26345

SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms. Existing defenses including input paraphrasing, multi step evaluation, and safety expert models often suffer from high computational costs, limited generalization, or rigid workflows that fail to detect subtle malicious intent embedded in complex contexts. I…

Performance Evaluation of Intent-Based Networking Scenarios: A GitOps and Nephio Approach
Saptarshi Ghosh, Ioannis Mavromatis, Konstantinos Antonakoglou, Konstantinos Katsaros
https://arxiv.org/abs/2509.13901

Performance Evaluation of Intent-Based Networking Scenarios: A GitOps and Nephio Approach
GitOps has emerged as a foundational paradigm for managing cloud-native infrastructures by enabling declarative configuration, version-controlled state, and automated reconciliation between intents and runtime deployments. Despite its widespread adoption, the performance and scalability of GitOps tools in Intent-Based Networking (IBN) scenarios are insufficiently evaluated. This paper presents a reproducible, metric-driven benchmarking, assessing the latency and resource overheads of three wide…

Tactile-Based Human Intent Recognition for Robot Assistive Navigation
Shaoting Peng, Dakarai Crowder, Wenzhen Yuan, Katherine Driggs-Campbell
https://arxiv.org/abs/2509.16353 ht…

Tactile-Based Human Intent Recognition for Robot Assistive Navigation
Robot assistive navigation (RAN) is critical for enhancing the mobility and independence of the growing population of mobility-impaired individuals. However, existing systems often rely on interfaces that fail to replicate the intuitive and efficient physical communication observed between a person and a human caregiver, limiting their effectiveness. In this paper, we introduce Tac-Nav, a RAN system that leverages a cylindrical tactile skin mounted on a Stretch 3 mobile manipulator to provide a…

LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest
Han Wang, Alex Whitworth, Pak Ming Cheung, Zhenjie Zhang, Krishna Kamath
https://arxiv.org/abs/2509.03764

LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest
Relevance evaluation plays a crucial role in personalized search systems to ensure that search results align with a user's queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost and long turnaround time limit its scalability. In this work, we present our approach at Pinterest Search to automate relevance evaluation for online experiments using fine-tuned LLMs. We rigorously validate the alignment between LLM-generated judgments and human ann…

Controlling Intent Expressiveness in Robot Motion with Diffusion Models
Wenli Shi, Clemence Grislain, Olivier Sigaud, Mohamed Chetouani
https://arxiv.org/abs/2510.12370 https://…

Controlling Intent Expressiveness in Robot Motion with Diffusion Models
Legibility of robot motion is critical in human-robot interaction, as it allows humans to quickly infer a robot's intended goal. Although traditional trajectory generation methods typically prioritize efficiency, they often fail to make the robot's intentions clear to humans. Meanwhile, existing approaches to legible motion usually produce only a single "most legible" trajectory, overlooking the need to modulate intent expressiveness in different contexts. In this work, we propose a novel motio…

Enhancing Technical Documents Retrieval for RAG
Songjiang Lai, Tsun-Hin Cheung, Ka-Chun Fung, Kaiwen Xue, Kwan-Ho Lin, Yan-Ming Choi, Vincent Ng, Kin-Man Lam
https://arxiv.org/abs/2509.04139

Enhancing Technical Documents Retrieval for RAG
In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of understanding and retrieving complex technical content by leveraging the capabilities of Large Language Models (LLMs). First, we enhance user queries by generating expanded representations that better capture user intent and improve dataset diversity, thereby e…

Robot Trajectron V2: A Probabilistic Shared Control Framework for Navigation
Pinhao Song, Yurui Du, Ophelie Saussus, Sofie De Schrijver, Irene Caprara, Peter Janssen, Renaud Detry
https://arxiv.org/abs/2509.19954

Robot Trajectron V2: A Probabilistic Shared Control Framework for Navigation
We propose a probabilistic shared-control solution for navigation, called Robot Trajectron V2 (RT-V2), that enables accurate intent prediction and safe, effective assistance in human-robot interaction. RT-V2 jointly models a user's long-term behavioral patterns and their noisy, low-dimensional control signals by combining a prior intent model with a posterior update that accounts for real-time user input and environmental context. The prior captures the multimodal and history-dependent nature o…