Perceptually

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 27

All topics

Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation
Sep 30, 2026Siyuan Liu, Kanghui Tian, Yue Duan +4Perceptually Vista
Nanjing University · Fudan University · Nanjing University of Posts and Telecommunications
Overlapping Visual Grouping Without Semantic Priors
Sep 23, 2026Teemu Saukkio, Hashem Haghbayan, Juha PlosilaPerceptually Prior Knowledge Integration
University of Turku, Faculty of Technology, Department of Computing, Turku, Finland
Collaborative Memory for Multi-Agent VLM Systems
Sep 15, 2026Huixin Zhang, Shao-Jun Xia, Di Wang +3Visual Memory Perceptually
Meta Menlo Park, United States
On the Human and Computer Alignment of Attribute-Based Music Matches
Sep 1, 2026Roser Batlle-Roca, Woosung Choi, Joan Serrà +5Music Structure Analysis Generative Artificial Intelligence
Music Technology Group, Universitat Pompeu Fabra · Sony AI · Joint Research Centre, European Commission +1
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
Aug 31, 2026Vernon Toh, Navonil Majumder, Zhengyuan Liu +2Perceptually Artificial Intelligence Agents
DeCLaRe Lab, Nanyang Technological University, Singapore · Agency for Science, Technology, and Research (A*STAR), Singapore
PAMoR: Parameterized Affective Motion Generation in Real Time for Humanoid Robots
Aug 28, 2026Yan Pan, Lingfan Bao, Tianhu Peng +1Text-To-Motion Generation Motion
Department of Computer Science, University College London, London, UK
PERCEPT: A Corpus for POS Tagging and Analysis of Persian-English Code-Mixing
Aug 10, 2026Ghazal Kalhor, Zahra Jafari, Amirarsalan Shahbazi +1Persian Code-Switching
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran · School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran · Tehran Institute for Advanced Studies, Khatam University, Tehran, Iran
ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned Supervision
Aug 9, 2026Delin Mao, Chenghao Sun, Jingwei Song +2Recent Vision-Language Models Multimodal Reasoning Benchmarks
Shanghai Jiao Tong University · University of Chinese Academy of Sciences · Fudan University
Human-AI Perceptual Alignment by Playing Hues and Cues
Aug 7, 2026Nuria Alabau-Bosque, Jorge Vila-Tomás, Paula Daudén-Oliver +3Perceptually Artificial Intelligence Alignment
Image Processing Lab, Universitat de València, Carrer del Catedrátic José Beltrán Martinez, Paterna, 46980, Spain
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
Jul 30, 2026Yang Zhou, Zixuan Huang, Sunzhu Li +10Recent Vision-Language Models Geospatial Reasoning
Zhejiang University · Zhuoyu Technology, Shenzhen, China · Beihang University +3
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
Jul 27, 2026Zichao Lin, Yifeng Xie, Bowen Qu +30Perceptually Multimodal Large Language Models
Moonshot AI
PerceptDrive: Perception Prior World-Action Modeling with Adaptive Expert Routing for End-to-End Autonomous Driving
Jul 22, 2026Yushan Liu, Tianxiong Lv, Bohua Wang +11Perception Pipeline Efficient World-Action Model
Tsinghua University · AMap, Alibaba Group
Production and Perception in LLMs: A Token Probability Approach
Jul 13, 2026Anna Marklová, Jiří Milička, Martina Vokáčová +1Single-Token Output Distributions Linguistics
Faculty of Arts, Charles University, Prague · Faculty of Mathematics and Physics, Charles University, Prague
Mixture of Cognitive Experts in Large Vision-Language Models
Jul 12, 2026Robert Wijaya, Ngai-Man CheungRecent Vision-Language Models Multimodal Reasoning
Singapore University of Technology and Design (SUTD), Singapore
Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings
Jul 4, 2026Héctor Martel, Joe Hennessy-Priest, Taemin ChoNeural Audio Audio Understanding
BandLab Technologies, Singapore
PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation
Jun 4, 2026Nicolas Bougie, Xiaotong Ye, Gian Maria Marconi +1Generative User Interface User Simulation
1Woven by Toyota
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
Jun 2, 2026Mahtab Bigverdi, Linjie Li, Weikai Huang +8Spatial Reasoning Perceptually
University of Washington · 2Allen Institute for AI · 3Microsoft +1
P $^2$ -DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
Jun 2, 2026Ruipeng Zhang, Zhihao Li, Haozhang Yuan +2Perceptually Object Hallucination
Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science & Engineering, South China University of Technology · Pazhou Lab, Guangzhou, China · Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human, Guangzhou, China
Beyond Semantics: Modeling Factual and Affective Perceptual Experiences from Vision-Language Data
Jun 2, 2026Youssef Mohamed, Kenneth Ward Church, Mohamed ElhoseinyPerceptually Perception
KAUST · VecML
Perception First: A Frontier Native-Video Model with Self-Consistency for Implicit Video Question Answering
May 31, 2026Ali AlaviLong Video Question Answering Perceptually
The Ohio State University
Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
May 27, 2026Simardeep Singh, Paras ChopraPerceptually Layer-Wise
Indian Institute of Technology Roorkee, Roorkee, India · Lossfunk, India
Chinese sensorimotor and embodiment norms for 3,000 lexicalized concepts
May 21, 2026Jing Chen, Gábor Parti, Yin Zhong +2Sensorimotor Experience Mandarin
Department of Psychology, University of Milano-Bicocca · Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University · Center for Language Education, The Hong Kong University of Science and Technology
Modeling Subjective Urban Perception with Human Gaze
May 1, 2026Lin Che, Xi Wang, Marc Pollefeys +3Urban Environments Perceptually
ETH Zurich Switzerland
Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attacks
Feb 6, 2026Christof Duhme, Florian Eilers, Xiaoyi JiangSpectral Norm Smoothness
Department of Computer Science University of Münster Münster, Germany
Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders
Nov 7, 2025Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini +2Autoencoder Architectures Music Structure Analysis
Johannes Kepler University, Linz, AT · STMS, CNRS, IRCAM, Sorbonne Universit´e, Paris, FR · Queen Mary University, London, UK +1
DiffAU: Diffusion-Based Ambisonics Upscaling
Sep 30, 2025Amit Milstein, Nir Shlezinger, Boaz RafaelySpatial Audio Perceptually
ECE School Ben-Gurion University of the Negev, Be’er-Sheva, Israel
A Survey on Hypergame Theory: Modelling Misaligned Perceptions and Nested Beliefs for Multi-Agent Systems
Jul 25, 2025Vince Trencsenyi, Agnieszka Mensfelt, Kostas StathisGame Theory Perceptually
Department of Computer Science, Royal Holloway University of London, Egham Hill, Egham, TW200EX, Surrey, United Kingdom.

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation

Siyuan Liu, Kanghui Tian, Yue Duan, Yutao He+3

Nanjing University · Fudan University · Nanjing University of Posts and Telecommunications

Perceptually Vista

Open paper AskPDF arXiv

On-policy distillation (OPD) improves reasoning by providing token-level supervision from a teacher on a student's own trajectories. Existing methods primarily focus on enhancing this teacher-side guidance (e.g., by enriching teacher inputs and refining teacher feedback), yet we find that limited student perception is another critical bottleneck in multimodal OPD. By providing oracle visual facts, the performance of OPD-trained students can still be substantially improved for both weak and strong teachers. To address this bottleneck, we propose S-OPD, a simple multimodal on-policy distillation framework that explicitly strengthens student perceptual learning through two objectives. Specifically, Teacher-calibrated Policy Contrast separates student policies under original and masked images with teacher-based token-level gating, strengthening the student's reliance on visual evidence during reasoning. Policy Agreement aligns student policies under original and noise-perturbed images, further improving perceptual robustness to visual noise. Notably, our method can be seamlessly plugged into existing OPD frameworks, requiring no additional data annotations, model parameters or inference operations. Extensive experiments on eight benchmarks across student scales and distillation paradigms demonstrate consistent performance improvements, with gains of up to 4.25 points on LogicVista. When combined with existing teacher-side supervision methods, our method can yield further gains. Code is available at https://github.com/Sirilaw/S-OPD.

Momentum

Related topics

Latest papers 27