Tootfinder

What MLLMs Learn about When they Learn about Multimodal Reasoning: Perception, Reasoning, or their Integration?
Jiwan Chung, Neel Joshi, Pratyusha Sharma, Youngjae Yu, Vibhav Vineet
https://arxiv.org/abs/2510.01719

What MLLMs Learn about When they Learn about Multimodal Reasoning: Perception, Reasoning, or their Integration?
Multimodal reasoning models have recently shown promise on challenging domains such as olympiad-level geometry, yet their evaluation remains dominated by aggregate accuracy, a single score that obscures where and how models are improving. We introduce MathLens, a benchmark designed to disentangle the subskills of multimodal reasoning while preserving the complexity of textbook-style geometry problems. The benchmark separates performance into three components: Perception: extracting information …

ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations
Qiyuan Zeng, Chengmeng Li, Jude St. John, Zhongyi Zhou, Junjie Wen, Guorui Feng, Yichen Zhu, Yi Xu
https://arxiv.org/abs/2510.01607

ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations
We present ActiveUMI, a framework for a data collection system that transfers in-the-wild human demonstrations to robots capable of complex bimanual manipulation. ActiveUMI couples a portable VR teleoperation kit with sensorized controllers that mirror the robot's end-effectors, bridging human-robot kinematics via precise pose alignment. To ensure mobility and data quality, we introduce several key techniques, including immersive 3D model rendering, a self-contained wearable computer, and effic…

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

Did you see the sound? A Bayesian perspective on crossmodal perception in low vision https://www.biorxiv.org/content/10.64898/2025.12.24.696433v1 Temporal "audiovisual interactions are constrained by the presence of a usable visual signal"

"Did Joseph Carl Robnett Licklider (1915-1990) read “An Experiment in Time”? Could it be that he had a series of dreams between 1960 and 1968, and that he quickly wrote them down in his diary before breakfast? We can only speculate. But we do know for a fact that those dreams begat a nothing short of extraordinary sequence of writings."

J. C. R. Licklider & M. Mitchell Waldrop
The writings of Jorge Luis Borges twist our perception of time and space. In between articles about Shaw, Chesterton, Wilde, and Coleridge, his 1952 book "Otras Inquisiciones" included an unexpected gem: a short story called "El Tiempo y J. W. Dunne". The question is, who was this John William Dunne and what does he have to do with time? Well, his name might be forgotten by contemporary audiences, but Dunne was the author of one of the biggest bestsellers of the first half of the twentieth cent…

TriAlignXA: An Explainable Trilemma Alignment Framework for Trustworthy Agri-product Grading
Jianfei Xie, Ziyang Li
https://arxiv.org/abs/2510.01990 https://

TriAlignXA: An Explainable Trilemma Alignment Framework for Trustworthy Agri-product Grading
The 'trust deficit' in online fruit and vegetable e-commerce stems from the inability of digital transactions to provide direct sensory perception of product quality. This paper constructs a 'Trust Pyramid' model through 'dual-source verification' of consumer trust. Experiments confirm that quality is the cornerstone of trust. The study reveals an 'impossible triangle' in agricultural product grading, comprising biological characteristics, timeliness, and economic viability, highlighting the li…

Sounds easy, looks nice: Crossmodal transfer of auditory processing fluency to visual object preference https://link.springer.com/article/10.3758/s13414-025-03177-5

Sounds easy, looks nice: Crossmodal transfer of auditory processing fluency to visual object preference - Attention, Perception, & Psychophysics
Fluent (i.e., rapid and efficient) processing of perceptual objects is vital for humans to successfully navigate their environments. The experience of fluent processing per se tends to trigger positive affect; however, this affect is often misattributed by perceivers to the objects themselves, meaning that easy-to-perceive objects are judged more positively. These fluency-based preference effects have been robustly demonstrated unimodally, and specifically in situations in which fluency and pre…

Multimodal Feedback for Task Guidance in Augmented Reality
Hu Guo, Lily Patel, Rohan Gupt
https://arxiv.org/abs/2510.01690 https://arxiv.org/pdf/2510.01690…

Multimodal Feedback for Task Guidance in Augmented Reality
Optical see-through augmented reality (OST-AR) overlays digital targets and annotations on the physical world, offering promising guidance for hands-on tasks such as medical needle insertion or assembly. Recent work on OST-AR depth perception shows that target opacity and tool visualization significantly affect accuracy and usability; opaque targets and rendering the real instrument reduce depth errors, whereas transparent targets and absent tools impair performance. However, reliance on visual…

Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions
Mengyu Yang, Yiming Chen, Haozheng Pei, Siddhant Agarwal, Arun Balajee Vasudevan, James Hays
https://arxiv.org/abs/2510.02313

Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions
Can a model distinguish between the sound of a spoon hitting a hardwood floor versus a carpeted one? Everyday object interactions produce sounds unique to the objects involved. We introduce the sounding object detection task to evaluate a model's ability to link these sounds to the objects directly involved. Inspired by human perception, our multimodal object-aware framework learns from in-the-wild egocentric videos. To encourage an object-centric approach, we first develop an automatic pipelin…

Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
Haibo Hu, Lianming Huang, Xinyu Wang, Yufei Cui, Nan Guan, Chun Jason Xue
https://arxiv.org/abs/2510.01795

Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
Vision-Language Models (VLMs) are increasingly applied in autonomous driving for unified perception and reasoning, but high inference latency hinders real-time deployment. Early-exit reduces latency by terminating inference at intermediate layers, yet its task-dependent nature limits generalization across diverse scenarios. We observe that this limitation aligns with autonomous driving: navigation systems can anticipate upcoming contexts (e.g., intersections, traffic lights), indicating which t…

“Alliances are built on common values and a common threat perception,”
said Danish Defense Analyst Jacob Kaarsbo
“Trump shares neither of those with us
and I would argue he doesn’t share it with most Europeans.”
https://www.

MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
Jiyao Liu, Jinjie Wei, Wanying Qu, Chenglong Ma, Junzhi Ning, Yunheng Li, Ying Chen, Xinzhe Luo, Pengcheng Chen, Xin Gao, Ming Hu, Huihui Xu, Xin Wang, Shujian Gao, Dingkang Yang, Zhongying Deng, Jin Ye, Lihao Liu, Junjun He, Ningsheng Xu
https://arxiv…

MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
Medical Image Quality Assessment (IQA) serves as the first-mile safety gate for clinical AI, yet existing approaches remain constrained by scalar, score-based metrics and fail to reflect the descriptive, human-like reasoning process central to expert evaluation. To address this gap, we introduce MedQ-Bench, a comprehensive benchmark that establishes a perception-reasoning paradigm for language-based evaluation of medical image quality with Multi-modal Large Language Models (MLLMs). MedQ-Bench d…

What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
Hongze Wang, Boyang Sun, Jiaxu Xing, Fan Yang, Marco Hutter, Dhruv Shah, Davide Scaramuzza, Marc Pollefeys
https://arxiv.org/abs/2510.01830

What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
Object-Goal Navigation (ObjectNav) is a critical component toward deploying mobile robots in everyday, uncontrolled environments such as homes, schools, and workplaces. In this context, a robot must locate target objects in previously unseen environments using only its onboard perception. Success requires the integration of semantic understanding, spatial reasoning, and long-horizon planning, which is a combination that remains extremely challenging. While reinforcement learning (RL) has become…

Perception of Mayfield shifting amid MVP-type run https://www.espn.com/nfl/story/_/id/46534098/perception-bucs-baker-mayfield-shifting-amid-mvp-type-run

📼 A unified model of memory and perception: How Hebbian learning explains our recall of past events
https://medicalxpress.com/news/2025-11-memory-perception-hebbian-recall-events.html

A unified model of memory and perception: How Hebbian learning explains our recall of past events
A collaboration between SISSA's Physics and Neuroscience groups has taken a step forward in understanding how memories are stored and retrieved in the brain. The study, recently published in Neuron, shows that distinct perceptual biases—long thought to arise from separate brain systems—can, in fact, be explained by a single, biologically grounded mechanism.

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

Spectral peak picking improves tactile speech perception https://www.nature.com/articles/s41598-025-28930-6 "The algorithm is suitable for real-time use in wearable sensory substitution devices and could aid the development of effective haptic hearing aids."

LangGrasp: Leveraging Fine-Tuned LLMs for Language Interactive Robot Grasping with Ambiguous Instructions
Yunhan Lin, Wenqi Wu, Zhijie Zhang, Huasong Min
https://arxiv.org/abs/2510.02104

LangGrasp: Leveraging Fine-Tuned LLMs for Language Interactive Robot Grasping with Ambiguous Instructions
The existing language-driven grasping methods struggle to fully handle ambiguous instructions containing implicit intents. To tackle this challenge, we propose LangGrasp, a novel language-interactive robotic grasping framework. The framework integrates fine-tuned large language models (LLMs) to leverage their robust commonsense understanding and environmental perception capabilities, thereby deducing implicit intents from linguistic instructions and clarifying task requirements along with targe…

🇺🇦 #NowPlaying on #BBC6Music's #TheHueyShow
SHOLTO:
🎵 Tied To The Mast
#SHOLTO
#newRelease 🆕 single
https://sholto2.bandcamp.com/track/persephones-perception-2
https://open.spotify.com/track/3ZzN6oNgloLOJMNYgs5kJx

Circles or rectangles? What do you see? What does this tell you about your perception and consciousness?
Always fascinated by Anil Seth.
https://www.theguardian.com/commentisfree/2025/jul/05/optical-illusions-see-world-perception<…

Leider sehr nah an Erich Fromms Homophobie. Dennoch: Es geht um Rollen, die egal von welchem Geschlecht, eingenommen werden müssen, um psychisch gesunde Kinder zu erziehen und damit insgesamt zu einer friedlichen Gesellschaft zu kommen.
Beyond Perception: Wie entsteht Krieg? Die Folgen von Kindheitsprägung & Gefühlsstau | Dr. Hans-Joachim Maaz (#201)
Webseite der Episode:

Wie entsteht Krieg? Die Folgen von Kindheitsprägung & Gefühlsstau | Dr. Hans-Joachim Maaz (#201) von Beyond Perception
Der Workshop ‘Die Kunst des Erschaffens’ vermittelt dir die Grundprinzipien der Kreativität, Intuition und Realitätsgestaltung. Um dich mit deinem kreativen Potenzial zu verbinden und zu befähigen das was dir am Herzen liegt, in deinem Leben frei zu setzen - nimm jetzt teil: https://simonrilling.com/events/kunst-des-erschaffens-1 🎁 Mein Geschenk an dich 🎁 Durch intuitives Sprechen deinen Sprachfluss anstoßen und gleichzeitig Einfühlungsvermögen und geistige Flexibilität traini…

Production Over Perception: Kenneth Murray Will Start in Dallas https://insidethestar.com/production-over-perception-kenneth-murray-will-start-in-dallas

An evening discussing falling enrollment in #STEM courses at universities across Europe, especially traditional studies like chemistry, geology and meteorology. I wonder if young people are unaware of just how interesting #STEM careers to be? Or do they have the perception it's "too hard" compared to other subjects where easier grades may be had? Or is it simply they think they can have "better"* jobs in other fields?
#AcademicChatter
*Where better might mean higher paid, more prestigious, more certain of employment, or less workload or some combination of all of these... ?

"When #billionaires own major media outlets, “news” becomes something closer to state messaging. Not because the government controls it, but because the financial class that funds political power also owns the platforms that shape public perception."
#kleptocracy
Legacy M…

Legacy Media's License To Kill
We've lived to see the day when a newspaper excuses the man who butchered their journalist By November, 2018, the CIA had concluded that Saudi Arabia was responsible for the murder of Washington Post journalist Jamal Khashoggi. And moreover—that Saudi Crown Prince Mohammed bin Salman personally ordered the killing.

Even #Nature now uses #AI to generate content: Sensory substitution devices and perception https://www.

I had thought we'd see Ekitike on the left, with Chiesa on the right. Slot, instead, puts Ekitike on the right and leaves Gakpo in.
Happy to see Jones make it into the midfield, as he's been good all year and a) Gravenberch needs to rest that ankle; and b) Mac Allister needs to rest period. Will be interested to see how far forward Szoboszlai plays.
Robbo and Frimpong make sense. I think Bradley has been better than the general perception, but Frimpong should get a run ou…

CHUCKLE -- When Humans Teach AI To Learn Emotions The Easy Way
Ankush Pratap Singh, Houwei Cao, Yong Liu
https://arxiv.org/abs/2510.09382 https://arxiv.org…

CHUCKLE -- When Humans Teach AI To Learn Emotions The Easy Way
Curriculum learning (CL) structures training from simple to complex samples, facilitating progressive learning. However, existing CL approaches for emotion recognition often rely on heuristic, data-driven, or model-based definitions of sample difficulty, neglecting the difficulty for human perception, a critical factor in subjective tasks like emotion recognition. We propose CHUCKLE (Crowdsourced Human Understanding Curriculum for Knowledge Led Emotion Recognition), a perception-driven CL frame…

MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
Reuben A. Luera, Ryan Rossi, Franck Dernoncourt, Samyadeep Basu, Sungchul Kim, Subhojyoti Mukherjee, Puneet Mathur, Ruiyi Zhang, Jihyung Kil, Nedim Lipka, Seunghyun Yoon, Jiuxiang Gu, Zichao Wang, Cindy Xiong Bearfield, Branislav Kveton
https://

MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
In an ideal design pipeline, user interface (UI) design is intertwined with user research to validate decisions, yet studies are often resource-constrained during early exploration. Recent advances in multimodal large language models (MLLMs) offer a promising opportunity to act as early evaluators, helping designers narrow options before formal testing. Unlike prior work that emphasizes user behavior in narrow domains such as e-commerce with metrics like clicks or conversions, we focus on subje…

Audio-Guided Visual Perception for Audio-Visual Navigation
Yi Wang, Yinfeng Yu, Fuchun Sun, Liejun Wang, Wendong Zheng
https://arxiv.org/abs/2510.11760 https://

Audio-Guided Visual Perception for Audio-Visual Navigation
Audio-Visual Embodied Navigation aims to enable agents to autonomously navigate to sound sources in unknown 3D environments using auditory cues. While current AVN methods excel on in-distribution sound sources, they exhibit poor cross-source generalization: navigation success rates plummet and search paths become excessively long when agents encounter unheard sounds or unseen environments. This limitation stems from the lack of explicit alignment mechanisms between auditory signals and correspo…

Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
Ziyang Ma, Ruiyang Xu, Zhenghao Xing, Yunfei Chu, Yuxuan Wang, Jinzheng He, Jin Xu, Pheng-Ann Heng, Kai Yu, Junyang Lin, Eng Siong Chng, Xie Chen
https://arxiv.org/abs/2510.12720

Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
Fine-grained perception of multimodal information is critical for advancing human-AI interaction. With recent progress in audio-visual technologies, Omni Language Models (OLMs), capable of processing audio and video signals in parallel, have emerged as a promising paradigm for achieving richer understanding and reasoning. However, their capacity to capture and describe fine-grained details remains limited explored. In this work, we present a systematic and comprehensive investigation of omni de…

The BBC publishes the results from its "Our Future, Our BBC" survey, completed by 872K viewers, showing only 43% say it is "effective" in being independent (Jake Kanter/Deadline)
https://deadline.com/2025/10/bbc-study-viewer…

Major BBC Study Finds Viewers Have Doubts About Broadcaster’s Independence From Government
The BBC has an independence perception problem, according to a major study of 872,701 viewers.

The number of Computer Misuse Act 1990 prosecutions hasn't really risen in the last five years, despite the perception of a rise in "cyber crime". Maybe this indicates a ceiling on the resources allocated to investigate and prosecute, or maybe not.
https://questions-state…

For Raiders QB Geno Smith, Perception is Reality https://www.si.com/nfl/raiders/las-vegas-geno-smith-chip-kelly-tennessee-titans

Deceptive Planning Exploiting Inattention Blindness
Mustafa O. Karabag, Jesse Milzman, Ufuk Topcu
https://arxiv.org/abs/2510.02714 https://arxiv.org/pdf/25…

Deceptive Planning Exploiting Inattention Blindness
We study decision-making with rational inattention in settings where agents have perception constraints. In such settings, inaccurate prior beliefs or models of others may lead to inattention blindness, where an agent is unaware of its incorrect beliefs. We model this phenomenon in two-player zero-sum stochastic games, where Player 1 has perception constraints and Player 2 deceptively deviates from its security policy presumed by Player 1 to gain an advantage. We formulate the perception constr…

My lord, to be able to write science this well. This is like the opening of an econ or law paper.
From Donald Hoffman's "The Interface Theory of Perception",
https://sites.socsci.uci.edu/~ddhoff/interface.pdf

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

🇺🇦 #NowPlaying on BBCRadio3's #RoundMidnight
SHOLTO:
🎵 Persephone's Perception
#SHOLTO
https://open.spotify.com/track/0mT6XUgnPE9ZpX7sQY79ZG

Although I must admit, I much prefer crystal-clear problems (URL NO CONNECT) with clean fixes over the sort I spend most of my time on, where I can only see the problem through the lens of other people's perception of slow vs. fast across something like a 10k-mile connection. With all the concomitant obscurants, both technical and cultural.
#Sysadminnery

New study indicates language, but not music, plays a powerful role in tactile perception https://www.fu-berlin.de/en/presse/informationen/fup/2025/fup_25_166-brain-language-laboratory-miller/index.html "Neuroscientist…

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Hanyang Chen, Mark Zhao, Rui Yang, Qinwei Ma, Ke Yang, Jiarui Yao, Kangrui Wang, Hao Bai, Zhenhailong Wang, Rui Pan, Mengchao Zhang, Jose Barreiros, Aykut Onol, ChengXiang Zhai, Heng Ji, Manling Li, Huan Zhang, Tong Zhang
https://arxiv…

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are costly to deploy, while smaller VLMs lack the necessary knowledge and skills to succeed. To bridge this gap, we present \textit{Embodied Reasoning Agent (ERA)}, a two-stage framework that integrates prior knowledge learning and online reinforcement learning …

Trump corrupts the minds of Americans
Normalizes bigotry, misogyny,
graft and greed
From: @apron.rupar@threads.net
https://www.threads.com/@aaron.rupar/post/DP1koWjiWp9

Aaron Rupar (@aaron.rupar) on Threads
Neguse: "What Donald Trump and his administration are attempting to do is create this perception that he has all the power, and create a sense of hopelessness or helplessness in the American public. We've gotta resist the temptation. He is electorally unpopular. In fact, the most unpopular president at this juncture than any modern president in the history of our country."

Spotlight on Token Perception for Multimodal Reinforcement Learning
Siyuan Huang, Xiaoye Qu, Yafu Li, Yun Luo, Zefeng He, Daizong Liu, Yu Cheng
https://arxiv.org/abs/2510.09285 …

Spotlight on Token Perception for Multimodal Reinforcement Learning
While Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Vision-Language Models (LVLMs), most existing methods in multimodal reasoning neglect the critical role of visual perception within the RLVR optimization process. In this paper, we undertake a pioneering exploration of multimodal RLVR through the novel perspective of token perception, which measures the visual dependency of each generated token. With a granular analysis of Chain-of-Thoug…

The Third Visual Pathway for Social Perception
David Pitcher
https://arxiv.org/abs/2512.09351 https://arxiv.org/pdf/2512.09351 https://arxiv.org/html/2512.09351
arXiv:2512.09351v1 Announce Type: new
Abstract: Influential models of primate visual cortex describe two functionally distinct pathways: a ventral pathway for object recognition and the dorsal pathway for spatial and action processing. However, recent human and non-human primate research suggests the existence of a third visual pathway projecting from early visual cortex through the motion-selective area V5/MT into the superior temporal sulcus (STS). Here we integrate anatomical, neuroimaging, and neuropsychological evidence demonstrating that this pathway specializes in processing dynamic social cues such as facial expressions, eye gaze, and body movements. This third pathway supports social perception by computing the actions and intentions of other people. These findings enhance our understanding of visual cortical organization and highlight the STS's critical role in social cognition, suggesting that visual processing encompasses a dedicated neural circuit for interpreting socially relevant motion and behavior.
toXiv_bot_toot

The fact that so many on the Fediverse remain so uneducated isn’t surprising. It only reveals how deeply bourgeois ideology continues to shape public consciousness, molding perception to serve the interests of capital, especially US imperialism.
Just as it took decades for many to see the war on terror for what it truly was, and even longer to grasp Palestine’s struggle against imperialism and settler colonialism, the same pattern will repeat.
I wholeheartedly reject imperialis…

FRIDAY, October 31st
From 7:30 – 9:30 PM
@ Yale CCAM Sound Art Series
(149 York St, New Haven, CT)
"SIGNIFICANTLY LESS DECEPTIVE"
An audio visual live performance by #Negativland SUE-C
Free, open to the public, but limited capacity – first come first serve!

The Adoption Paradox: A Comparative Analysis of Veterinary AI Adoption in China and the North America
Shumin Li, Xiaoyun Lai
https://arxiv.org/abs/2510.11758 https://

The Adoption Paradox: A Comparative Analysis of Veterinary AI Adoption in China and the North America
This study compares the perception, adoption, and application of artificial intelligence (AI) among veterinary professionals in China and North America (NA), testing the hypothesis that adoption patterns are shaped by regional market and demographic factors. A descriptive, cross-sectional survey was conducted with 455 veterinary professionals in China between May and July 2025. The results were compared with published data from a 2024 survey of 3,968 veterinary professionals in the United State…

Generative Latent Video Compression
Zongyu Guo, Zhaoyang Jia, Jiahao Li, Xiaoyi Zhang, Bin Li, Yan Lu
https://arxiv.org/abs/2510.09987 https://arxiv.org/pd…

Generative Latent Video Compression
Perceptual optimization is widely recognized as essential for neural compression, yet balancing the rate-distortion-perception tradeoff remains challenging. This difficulty is especially pronounced in video compression, where frame-wise quality fluctuations often cause perceptually optimized neural video codecs to suffer from flickering artifacts. In this paper, inspired by the success of latent generative models, we present Generative Latent Video Compression (GLVC), an effective framework for…

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning
Xingang Guo, Utkarsh Tyagi, Advait Gosai, Paula Vergara, Ernesto Gabriel Hern\'andez Montoya, Chen Bo Calvin Zhang, Bin Hu, Yunzhong He, Bing Liu, Rakshith Sharma Srinivasa
https://arxiv.org/abs/2510.12712

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning
Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient visual cues. Beyond static visual perception, MLLMs must also think with images: dynamically transforming visual content and integrating it with other tools to solve complex tasks. However, this shift from treating vision as passive context to a manipulable cogni…

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

Two-stream network-driven vision-based tactile sensor for object feature extraction and fusion perception
Muxing Huang, Zibin Chen, Weiliang Xu, Zilan Li, Yuanzhi Zhou, Guoyuan Zhou, Wenjing Chen, Xinming Li
https://arxiv.org/abs/2510.12528

Two-stream network-driven vision-based tactile sensor for object feature extraction and fusion perception
Tactile perception is crucial for embodied intelligent robots to recognize objects. Vision-based tactile sensors extract object physical attributes multidimensionally using high spatial resolution; however, this process generates abundant redundant information. Furthermore, single-dimensional extraction, lacking effective fusion, fails to fully characterize object attributes. These challenges hinder the improvement of recognition accuracy. To address this issue, this study introduces a two-stre…

Role of thalamus in human conscious perception revealed by low-intensity focused ultrasound neuromodulation https://www.nature.com/articles/s41467-025-66832-3 these findings "underscore the modulatory potential of thalamocortical networks in shaping visual experience";

Fundamentals of Building Autonomous LLM Agents
Victor de Lamo Castrillo, Habtom Kahsay Gidey, Alexander Lenz, Alois Knoll
https://arxiv.org/abs/2510.09244 https://

Fundamentals of Building Autonomous LLM Agents
This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs). Motivated by the limitations of traditional LLMs in real-world tasks, the research aims to explore patterns to develop "agentic" LLMs that can automate complex tasks and bridge the performance gap with human capabilities. Key components include a perception system that converts environmental percepts into meaningful representations; a reasoning system that formulates plans, adapts t…

Causal role of the individual alpha phase in #multisensory #perception https://www.biorxiv.org/content/10.1101/20

Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
Nikos Theodoridis, Tim Brophy, Reenu Mohandas, Ganesh Sistu, Fiachra Collins, Anthony Scanlan, Ciaran Eising
https://arxiv.org/abs/2510.08352

Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
Vision-Language Models (VLMs) are becoming increasingly powerful, demonstrating strong performance on a variety of tasks that require both visual and textual understanding. Their strong generalisation abilities make them a promising component for automated driving systems, which must handle unexpected corner cases. However, to be trusted in such safety-critical applications, a model must first possess a reliable perception system. Moreover, since critical objects and agents in traffic scenes ar…

Dart, Giants hope win over Eagles shifts narrative https://www.espn.com/nfl/story/_/id/46549170/jaxson-dart-giants-hope-win-eagles-shifts-narrative

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/5]:
- Team Xiaomi EV-AD VLA: Learning to Navigate Socially Through Proactive Risk Perception - Technica...
Xiao, Zhang, Tang, Cheng, Xu, Ding, Zhou, Chen, Ye, Hao

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

Team Xiaomi EV-AD VLA: Learning to Navigate Socially Through Proactive Risk Perception - Technical Report for IROS 2025 RoboSense Challenge Social Navigation Track
Erjia Xiao, Lingfeng Zhang, Yingbo Tang, Hao Cheng, Renjing Xu, Wenbo Ding, Lei Zhou, Long Chen, Hangjun Ye, Xiaoshuai Hao
https://arxiv.org/abs/2510.07871

Team Xiaomi EV-AD VLA: Learning to Navigate Socially Through Proactive Risk Perception - Technical Report for IROS 2025 RoboSense Challenge Social Navigation Track
In this report, we describe the technical details of our submission to the IROS 2025 RoboSense Challenge Social Navigation Track. This track focuses on developing RGBD-based perception and navigation systems that enable autonomous agents to navigate safely, efficiently, and socially compliantly in dynamic human-populated indoor environments. The challenge requires agents to operate from an egocentric perspective using only onboard sensors including RGB-D observations and odometry, without acces…

🇺🇦 #NowPlaying on #BBC6Music's #FocusBeats
El Jazzy Chavo:
🎵 Perception
#ElJazzyChavo
https://villagelive.bandcamp.com/track/el-jazzy-chavo-perception
https://open.spotify.com/track/13LNkGnhDFsAU8vh9FGwEm

Advances in artificial vision systems: a comprehensive review of technologies, applications, and future directions https://link.springer.com/article/10.1007/s13534-025-00513-4 "clinical value hinges on durability, effective resolution, surgical practicality, and user t…

Advances in artificial vision systems: a comprehensive review of technologies, applications, and future directions - Biomedical Engineering Letters
This review article focuses on recent advancements and persistent challenges in artificial vision prostheses designed to restore sight for patients affected by retinal diseases. It comprehensively examines various approaches, including epiretinal, subretinal, and suprachoroidal implants, as well as optic nerve and visual cortex stimulation strategies. The critical role of the retina in visual perception is explored, emphasizing how retinal degeneration affects the transmission of visual informa…

Active Semantic Perception
Huayi Tang, Pratik Chaudhari
https://arxiv.org/abs/2510.05430 https://arxiv.org/pdf/2510.05430

Active Semantic Perception
We develop an approach for active semantic perception which refers to using the semantics of the scene for tasks such as exploration. We build a compact, hierarchical multi-layer scene graph that can represent large, complex indoor environments at various levels of abstraction, e.g., nodes corresponding to rooms, objects, walls, windows etc. as well as fine-grained details of their geometry. We develop a procedure based on large language models (LLMs) to sample plausible scene graphs of unobser…

Generative inference unifies feedback processing for learning and perception in natural and artificial vision (here not prosthetic vision) https://www.biorxiv.org/content/10.1101/2025.10.21.683535v2

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
Junyan Ye, Dongzhi Jiang, Jun He, Baichuan Zhou, Zilong Huang, Zhiyuan Yan, Hongsheng Li, Conghui He, Weijia Li
https://arxiv.org/abs/2510.09361

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
Recently, Multimodal Large Language Models (MLLMs) have made rapid progress, particularly in enhancing their reasoning capabilities. However, existing reasoning benchmarks still primarily assess language-based reasoning, often treating visual input as replaceable context. To address this gap, we introduce BLINK-Twice, a vision-centric reasoning benchmark grounded in challenging perceptual tasks. Instead of relying on external knowledge, our tasks require models to reason from visual content alo…

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

🇺🇦 #NowPlaying on #BBC6Music's #FocusBeats
El Jazzy Chavo:
🎵 Perception
#ElJazzyChavo
https://villagelive.bandcamp.com/track/el-jazzy-chavo-perception
https://open.spotify.com/track/13LNkGnhDFsAU8vh9FGwEm

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

Causal role of the individual alpha phase in multisensory perception https://www.biorxiv.org/content/10.1101/2025.11.11.687884v2 more info in the X thread

Injecting Hallucinations in Autonomous Vehicles: A Component-Agnostic Safety Evaluation Framework
Alexandre Moreira Nascimento, Gabriel Kenji Godoy Shimanuki, L\'ucio Flavio Vismari, Jo\~ao Batista Camargo Jr, Jorge Rady de Almeida Jr, Paulo Sergio Cugnasca, Anna Carolina Muller Queiroz, Jeremy Noah Bailenson
https://arxiv.org/abs/2510…

Injecting Hallucinations in Autonomous Vehicles: A Component-Agnostic Safety Evaluation Framework
Perception failures in autonomous vehicles (AV) remain a major safety concern because they are the basis for many accidents. To study how these failures affect safety, researchers typically inject artificial faults into hardware or software components and observe the outcomes. However, existing fault injection studies often target a single sensor or machine perception (MP) module, resulting in siloed frameworks that are difficult to generalize or integrate into unified simulation environments. …

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

Enhanced pitch perception in early blind individuals and musicians is due to reduced internal noise https://www.biorxiv.org/content/10.1101/2025.11.25.690447v1

SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
Zhiliu Yang, Jinyu Dai, Jianyuan Zhang, Zhu Yang
https://arxiv.org/abs/2510.12749

SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
The scene perception, understanding, and simulation are fundamental techniques for embodied-AI agents, while existing solutions are still prone to segmentation deficiency, dynamic objects' interference, sensor data sparsity, and view-limitation problems. This paper proposes a novel framework, named SPORTS, for holistic scene understanding via tightly integrating Video Panoptic Segmentation (VPS), Visual Odometry (VO), and Scene Rendering (SR) tasks into an iterative and unified perspective. Fir…

Long-term visual-to-tactile stimulation induces functional reorganization of thalamic pathways to achieve visual perception https://www.sciencedirect.com/science/article/pii/S105381192500655X using haptic sensory substitution;

MCOP: Multi-UAV Collaborative Occupancy Prediction
Zefu Lin, Wenbo Chen, Xiaojuan Jin, Yuran Yang, Lue Fan, Yixin Zhang, Yufeng Zhang, Zhaoxiang Zhang
https://arxiv.org/abs/2510.12679

MCOP: Multi-UAV Collaborative Occupancy Prediction
Unmanned Aerial Vehicle (UAV) swarm systems necessitate efficient collaborative perception mechanisms for diverse operational scenarios. Current Bird's Eye View (BEV)-based approaches exhibit two main limitations: bounding-box representations fail to capture complete semantic and geometric information of the scene, and their performance significantly degrades when encountering undefined or occluded objects. To address these limitations, we propose a novel multi-UAV collaborative occupancy predi…

Visual–tactile shape perception in Argus II participants: The impact of prolonged device use and blindness on performance https://jov.arvojournals.org/article.aspx?articleid=2810954 "data highlight individual differences in performance over prolonged device use and the …

Detect Anything via Next Point Prediction
Qing Jiang, Junan Huo, Xingyu Chen, Yuda Xiong, Zhaoyang Zeng, Yihao Chen, Tianhe Ren, Junzhi Yu, Lei Zhang
https://arxiv.org/abs/2510.12798

Detect Anything via Next Point Prediction
Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to leverage MLLMs to tackle this task, they face challenges like low recall rate, duplicate predictions, coordinate misalignment, etc. In this work, we bridge this gap and propose Rex-Omni, a 3B-scale MLLM that achieves state-of-the-art object perception performance. On benchmarks like COCO and LVIS, Rex-Omni attains performan…

PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
Bingquan Li, Ning Wang, Tianwei Zhang, Zhicheng He, Yucong Wu
https://arxiv.org/abs/2510.12346 http…

PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
Recently, biped robot walking technology has been significantly developed, mainly in the context of a bland walking scheme. To emulate human walking, robots need to step on the positions they see in unknown spaces accurately. In this paper, we present PolyMap, a perception-based locomotion planning framework for humanoid robots to climb stairs. Our core idea is to build a real-time polygonal staircase plane semantic map, followed by a footstep planar using these polygonal plane segments. These …

SilvaScenes: Tree Segmentation and Species Classification from Under-Canopy Images in Natural Forests
David-Alexandre Duclos, William Guimont-Martin, Gabriel Jeanson, Arthur Larochelle-Tremblay, Th\'eo Defosse, Fr\'ed\'eric Moore, Philippe Nolet, Fran\c{c}ois Pomerleau, Philippe Gigu\`ere
https://arxiv.org/abs/2510.09458…

SilvaScenes: Tree Segmentation and Species Classification from Under-Canopy Images in Natural Forests
Interest in robotics for forest management is growing, but perception in complex, natural environments remains a significant hurdle. Conditions such as heavy occlusion, variable lighting, and dense vegetation pose challenges to automated systems, which are essential for precision forestry, biodiversity monitoring, and the automation of forestry equipment. These tasks rely on advanced perceptual capabilities, such as detection and fine-grained species classification of individual trees. Yet, exi…

Automated Behavior Planning for Fruit Tree Pruning via Redundant Robot Manipulators: Addressing the Behavior Planning Challenge
Gaoyuan Liu, Bas Boom, Naftali Slob, Yuri Durodi\'e, Ann Now\'e, Bram Vanderborght
https://arxiv.org/abs/2510.12509

Automated Behavior Planning for Fruit Tree Pruning via Redundant Robot Manipulators: Addressing the Behavior Planning Challenge
Pruning is an essential agricultural practice for orchards. Proper pruning can promote healthier growth and optimize fruit production throughout the orchard's lifespan. Robot manipulators have been developed as an automated solution for this repetitive task, which typically requires seasonal labor with specialized skills. While previous research has primarily focused on the challenges of perception, the complexities of manipulation are often overlooked. These challenges involve planning and con…

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
Shaoqi Dong, Chaoyou Fu, Haihan Gao, Yi-Fan Zhang, Chi Yan, Chu Wu, Xiaoyu Liu, Yunhang Shen, Jing Huo, Deqiang Jiang, Haoyu Cao, Yang Gao, Xing Sun, Ran He, Caifeng Shan
https://arxiv.org/abs/2510.09607

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
Vision-Language Action (VLA) models significantly advance robotic manipulation by leveraging the strong perception capabilities of pretrained vision-language models (VLMs). By integrating action modules into these pretrained models, VLA methods exhibit improved generalization. However, training them from scratch is costly. In this work, we propose a simple yet effective distillation-based framework that equips VLMs with action-execution capability by transferring knowledge from pretrained small…

Neural correlates of phosphene perception in blind individuals: A step toward a bidirectional cortical visual prosthesis https://www.science.org/doi/10.1126/sciadv.adv8846 "Cortical prostheses could one day restore functional vision in some blind subjects"

Robot Soccer Kit: Omniwheel Tracked Soccer Robots for Education
Gregoire Passault (UB, LaBRI), Clement Gaspard (UB, LaBRI), Olivier Ly (UB, LaBRI)
https://arxiv.org/abs/2510.11552

Robot Soccer Kit: Omniwheel Tracked Soccer Robots for Education
Recent developments of low cost off-the-shelf programmable components, their modularity, and also rapid prototyping made educational robotics flourish, as it is accessible in most schools today. They allow to illustrate and embody theoretical problems in practical and tangible applications, and gather multidisciplinary skills. They also give a rich natural context for project-oriented pedagogy. However, most current robot kits all are limited to egocentric aspect of the robots perception. This …

Wireless device uses light patterns to deliver information directly to the brain https://medicalxpress.com/news/2025-12-wireless-device-patterns-brain.html
Patterned wireless transcranial optogenetics generates artificial perception (in mice)

Wireless device uses light patterns to deliver information directly to the brain
In a new leap for neurobiology and bioelectronics, Northwestern University scientists have developed a wireless device that uses light to send information directly to the brain—bypassing the body's natural sensory pathways.

Have We Scene It All? Scene Graph-Aware Deep Point Cloud Compression
Nikolaos Stathoulopoulos, Christoforos Kanellakis, George Nikolakopoulos
https://arxiv.org/abs/2510.08512 ht…

Have We Scene It All? Scene Graph-Aware Deep Point Cloud Compression
Efficient transmission of 3D point cloud data is critical for advanced perception in centralized and decentralized multi-agent robotic systems, especially nowadays with the growing reliance on edge and cloud-based processing. However, the large and complex nature of point clouds creates challenges under bandwidth constraints and intermittent connectivity, often degrading system performance. We propose a deep compression framework based on semantic scene graphs. The method decomposes point cloud…

Scalable Offline Metrics for Autonomous Driving
Animikh Aich, Adwait Kulkarni, Eshed Ohn-Bar
https://arxiv.org/abs/2510.08571 https://arxiv.org/pdf/2510.08…

Scalable Offline Metrics for Autonomous Driving
Real-World evaluation of perception-based planning models for robotic systems, such as autonomous vehicles, can be safely and inexpensively conducted offline, i.e., by computing model prediction error over a pre-collected validation dataset with ground-truth annotations. However, extrapolating from offline model performance to online settings remains a challenge. In these settings, seemingly minor errors can compound and result in test-time infractions or collisions. This relationship is unders…

Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis
David Nguyen, Zulfiqar Zaidi, Kevin Karol, Jessica Hodgins, Zhaoming Xie
https://arxiv.org/abs/2510.08754

Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis
Developing table tennis robots that mirror human speed, accuracy, and ability to predict and respond to the full range of ball spins remains a significant challenge for legged robots. To demonstrate these capabilities we present a system to play dynamic table tennis for quadrupedal robots that integrates high speed perception, trajectory prediction, and agile control. Our system uses external cameras for high-speed ball localization, physical models with learned residuals to infer spin and pred…

Online Generic Event Boundary Detection
Hyungrok Jung, Daneul Kim, Seunggyun Lim, Jeany Son, Jonghyun Choi
https://arxiv.org/abs/2510.06855 https://arxiv.o…

Online Generic Event Boundary Detection
Generic Event Boundary Detection (GEBD) aims to interpret long-form videos through the lens of human perception. However, current GEBD methods require processing complete video frames to make predictions, unlike humans processing data online and in real-time. To bridge this gap, we introduce a new task, Online Generic Event Boundary Detection (On-GEBD), aiming to detect boundaries of generic events immediately in streaming videos. This task faces unique challenges of identifying subtle, taxonom…

MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency
Dongki Jung, Jaehoon Choi, Yonghan Lee, Sungmin Eum, Heesung Kwon, Dinesh Manocha
https://arxiv.org/abs/2510.07119 …

MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency
Monocular 3D foundation models offer an extensible solution for perception tasks, making them attractive for broader 3D vision applications. In this paper, we propose MoRe, a training-free Monocular Geometry Refinement method designed to improve cross-view consistency and achieve scale alignment. To induce inter-frame relationships, our method employs feature matching between frames to establish correspondences. Rather than applying simple least squares optimization on these matched points, we …

FOGMACHINE -- Leveraging Discrete-Event Simulation and Scene Graphs for Modeling Hierarchical, Interconnected Environments under Partial Observations from Mobile Agents
Lars Ohnemus, Nils Hantke, Max Wei{\ss}er, Kai Furmans
https://arxiv.org/abs/2510.09483

FOGMACHINE -- Leveraging Discrete-Event Simulation and Scene Graphs for Modeling Hierarchical, Interconnected Environments under Partial Observations from Mobile Agents
Dynamic Scene Graphs (DSGs) provide a structured representation of hierarchical, interconnected environments, but current approaches struggle to capture stochastic dynamics, partial observability, and multi-agent activity. These aspects are critical for embodied AI, where agents must act under uncertainty and delayed perception. We introduce FOGMACHINE , an open-source framework that fuses DSGs with discrete-event simulation to model object dynamics, agent observations, and interactions at scal…

Seeing like Meta: Smart glasses and the ethics of augmented reality #AR

Seeing like Meta: Smart glasses and the ethics of augmented reality - ABC Religion & Ethics
Meta’s smart glasses are not just another consumer gadget; they are a step toward enclosing perception itself within a private platform — and when the interface is your glasses, there is no “outside”.

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models
Andong Deng, Taojiannan Yang, Shoubin Yu, Lincoln Spencer, Mohit Bansal, Chen Chen, Serena Yeung-Levy, Xiaohan Wang
https://arxiv.org/abs/2510.08559

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models
Large Multimodal Models (LMMs) have achieved remarkable progress across various capabilities; however, complex video reasoning in the scientific domain remains a significant and challenging frontier. Current video benchmarks predominantly target general scenarios where perception/recognition is heavily relied on, while with relatively simple reasoning tasks, leading to saturation and thus failing to effectively evaluate advanced multimodal cognitive skills. To address this critical gap, we intr…

IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction
Yandu Chen, Kefan Gu, Yuqing Wen, Yucheng Zhao, Tiancai Wang, Liqiang Nie
https://arxiv.org/abs/2510.07778

IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction
Vision-Language-Action (VLA) models leverage pretrained vision-language models (VLMs) to couple perception with robotic control, offering a promising path toward general-purpose embodied intelligence. However, current SOTA VLAs are primarily pretrained on multimodal tasks with limited relevance to embodied scenarios, and then finetuned to map explicit instructions to actions. Consequently, due to the lack of reasoning-intensive pretraining and reasoning-guided manipulation, these models are una…

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Hongxing Li, Dingming Li, Zixuan Wang, Yuchen Yan, Hang Wu, Wenqi Zhang, Yongliang Shen, Weiming Lu, Jun Xiao, Yueting Zhuang
https://arxiv.org/abs/2510.08531

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this limitation stems from a critical gap: existing methods attempt to learn spatial reasoning directly without establishing the hierarchical foundations of perception and understanding. To address this challenge, we present a comprehensive methodology for building spatial intelligence progressively. We in…

Electrotactile characteristics of rectified random noise stimulation (r-tRNS) on the forehead: a comparison with tDCS https://ieeexplore.ieee.org/document/11252854 "r-tRNS has the potential to be effectively utilized in applications requiring electrotactile perception, such as sensor…

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
Haolin Yang, Yuxing Long, Zhuoyuan Yu, Zihan Yang, Minghan Wang, Jiapeng Xu, Yihan Wang, Ziyan Yu, Wenzhe Cai, Lei Kang, Hao Dong
https://arxiv.org/abs/2510.08173

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
Instruction-following navigation is a key step toward embodied intelligence. Prior benchmarks mainly focus on semantic understanding but overlook systematically evaluating navigation agents' spatial perception and reasoning capabilities. In this work, we introduce the NavSpace benchmark, which contains six task categories and 1,228 trajectory-instruction pairs designed to probe the spatial intelligence of navigation agents. On this benchmark, we comprehensively evaluate 22 navigation agents, in…

Semantic Segmentation Algorithm Based on Light Field and LiDAR Fusion
Jie Luo, Yuxuan Jiang, Xin Jin, Mingyu Liu, Yihui Fan
https://arxiv.org/abs/2510.06687 https://

Semantic Segmentation Algorithm Based on Light Field and LiDAR Fusion
Semantic segmentation serves as a cornerstone of scene understanding in autonomous driving but continues to face significant challenges under complex conditions such as occlusion. Light field and LiDAR modalities provide complementary visual and spatial cues that are beneficial for robust perception; how- ever, their effective integration is hindered by limited viewpoint diversity and inherent modality discrepancies. To address these challenges, the first multimodal semantic segmentation datase…

Active Next-Best-View Optimization for Risk-Averse Path Planning
Amirhossein Mollaei Khass, Guangyi Liu, Vivek Pandey, Wen Jiang, Boshu Lei, Kostas Daniilidis, Nader Motee
https://arxiv.org/abs/2510.06481

Active Next-Best-View Optimization for Risk-Averse Path Planning
Safe navigation in uncertain environments requires planning methods that integrate risk aversion with active perception. In this work, we present a unified framework that refines a coarse reference path by constructing tail-sensitive risk maps from Average Value-at-Risk statistics on an online-updated 3D Gaussian-splat Radiance Field. These maps enable the generation of locally safe and feasible trajectories. In parallel, we formulate Next-Best-View (NBV) selection as an optimization problem on…

Visual Representations inside the Language Model
Benlin Liu, Amita Kamath, Madeleine Grunde-McLaughlin, Winson Han, Ranjay Krishna
https://arxiv.org/abs/2510.04819 https://

Visual Representations inside the Language Model
Despite interpretability work analyzing VIT encoders and transformer activations, we don't yet understand why Multimodal Language Models (MLMs) struggle on perception-heavy tasks. We offer an under-studied perspective by examining how popular MLMs (LLaVA-OneVision, Qwen2.5-VL, and Llama-3-LLaVA-NeXT) process their visual key-value tokens. We first study the flow of visual information through the language model, finding that image value tokens encode sufficient information to perform several per…

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu
https://arxiv.org/abs/2510.07143

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
Recent endeavors to accelerate inference in Multimodal Large Language Models (MLLMs) have primarily focused on visual token compression. The effectiveness of these methods is typically assessed by measuring the accuracy drop on established benchmarks, comparing model performance before and after compression. However, these benchmarks are originally designed to assess the perception and reasoning capabilities of MLLMs, rather than to evaluate compression techniques. As a result, directly applyin…

DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining
Zhiliang Zhu, Tao Zeng, Tao Yang, Guoliang Luo, Jiyong Zeng
https://arxiv.org/abs/2510.06746

DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining
Image deraining is crucial for improving visual quality and supporting reliable downstream vision tasks. Although Mamba-based models provide efficient sequence modeling, their limited ability to capture fine-grained details and lack of frequency-domain awareness restrict further improvements. To address these issues, we propose DeRainMamba, which integrates a Frequency-Aware State-Space Module (FASSM) and Multi-Directional Perception Convolution (MDPConv). FASSM leverages Fourier transform to d…

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Yunlong Tang, Jing Bi, Pinxin Liu, Zhenyu Pan, Zhangyun Tan, Qianxiang Shen, Jiani Liu, Hang Hua, Junjia Guo, Yunzhong Xiao, Chao Huang, Zhiyuan Wang, Susan Liang, Xinyi Liu, Yizhi Song, Yuhe Nie, Jia-Xing Zhong, Bozheng Li, Daiqing Qi, Ziyun Zeng, Ali Vosoughi, Luchuan Song, Zeliang Zhang, Daiki Shimada, Han Liu, Jiebo Luo, Chenliang Xu

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large Multimodal Models (Video-LMMs), which integrate visual encoders with powerful decoder-based language models, has demonstrated remarkable capabilities in video understanding tasks. However, the critical phase that transforms these models from basic perception sys…