Loop

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 280% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction
Oct 1, 2026Moyang Li, Zihan Zhu, Wei Zhang +2Feed-Forward 3D Reconstruction 3D Reconstruction
ETH Zurich · University of Stuttgart · Microsoft
Closing the Loop: Practical Training Recipes for Looped Language Models
Sep 30, 2026Andrei Marchenko, Viacheslav Bezrukov, Oleg Kashurin +5Recurrent Model Loop
RND NLP, DAIMLD, Russian Federation
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Sep 30, 2026Xinge Peng, Yiting Lu, Tianwu Zhi +4Multimodal Reasoning Perception Pipeline
University of Science and Technology of China · ByteDance · City University of Hong Kong
Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does
Sep 30, 2026Jiaju Wu, Yi Hu, Muhan ZhangTransformer Architectures Loop
Institute for Artificial Intelligence, Peking University. · School of Mathematical Sciences, Peking University.
A Tilted Bowl Is Not a Slippery Slope: Compressing Looped Models
Sep 30, 2026Steven Kolawole, Pearse Jim, Opegbemi M. Busoye +2Compressed Model Model Weights
Carnegie Mellon University · ML Collective
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
Sep 29, 2026Sicheng Xie, Yitong Chen, Haidong Cao +3Human-To-Robot Transfer Embodied Agents
Institute of Trustworthy Embodied AI, Fudan University · Shanghai Innovation Institute · NeoteAI.
How to Loop MoE: Flatten the Experts, Untie the Attention
Sep 28, 2026Shouren Wang, Chuang Ma, Mohsen Hariri +6Mixture-Of-Experts Experts
Case Western Reserve University · Kyoto University · NII LLMC
AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?
Sep 28, 2026Haotian Luo, Haoyu Wang, Zeyu Qin +5Data Science Agents Agentic Benchmarks
HKUST · SLAI · NTU
FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL
Sep 28, 2026Xun Wang, Ruishuo Chen, Yu Chen +2Offline Reinforcement Learning Loop
Institute for Interdisciplinary Information Sciences, Tsinghua University
Error- and Prediction-Driven Motor Learning in the Cortico-Cerebellar Loop
Sep 24, 2026Ana Carolina Filipe, Rui Ponte Costa, Cláudia SoaresLearning-Based Control Learning Dynamics
Department of Computer Science, NOVA School of Science and Technology, Caparica, Portugal · Centre for Neural Circuits and Behaviour, University of Oxford
CLOOPD: Closing the Learner Loop in On-Policy Distillation
Sep 21, 2026Keye Zheng, Hanyu Li, Zhan Cheng +1Loop
Alibaba Group
CoRELoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection
Sep 17, 2026Kunyu Feng, Yuxiang Wang, Li Wang +2Audio Deepfake Detection Neural Audio
The Chinese University of Hong Kong, Shenzhen · Amphion Technology Co., Ltd.
LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers
Sep 15, 2026SangLyul Cho, Langqing Cui, Sehoon Kim +2Speculative Decoding Transformer Architectures
1Seoul National University · 2KAIST
Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECG
Sep 14, 2026Pawel Olszowiec, Michal Byra, Grzegorz Gruszczynski +2Transformer Encoder Adult-To-Pediatric Electrocardiogram Transfer
Samsung AI Center, Warsaw, Poland · IFTR, Polish Academy of Sciences, Warsaw, Poland
Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification
Sep 12, 2026Joshua Ong Jun Leang, Haonan Li, Zheng Zhao +6Mathematical Reasoning Theorem Proving
Institute of Foundation Models · Imperial College London · University of Edinburgh +1
One Loop, Two Gains: Can Active Learning win the Lottery for Free?
Sep 9, 2026Benedikt Tscheschner, Eduardo Veas, Marc MasanaPool-Based Active Learning Active Learning
University of Technology Graz Know-Center Research GmbH Austria · Institute of Visual Computing University of Technology Graz Austria
ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback
Sep 8, 2026Min Zeng, Yuzhou Liu, Zhenyu Cao +5Loop Decomposition
vivo AI Lab
Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents
Sep 8, 2026Wenbo Gao, Zhaomou Song, Zhiyuan Ji +7On-Policy Self-Evolution Self-Evolving Agents
1The Hong Kong Polytechnic University · 2Huawei · 3Renmin University of China
Vectorizer: Vectorizing NumPy Programs with Shape-Guided Rewrite
Sep 8, 2026Jingqian Liu, Xiaoyu Liu, Yuepeng WangVectorization Python
Simon Fraser University Burnaby, British Columbia, Canada
LOCI: A Locator-Critic with Refinement Loop
Aug 31, 2026Walid Bousselham, Mathilde Caron, Arsha Nagrani +1Recent Vision-Language Models Visual Evidence
Google DeepMind
Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops
Aug 31, 2026Bowei He, Weixu Zhang, Yili Jin +1Algorithmic Cores Artificial Intelligence Research
MBZUAI · McGill University · MirrorSpace Technology +1
AI Agents Push Humans Out of the Loop
Aug 24, 2026Margaret Mitchell, Avijit Ghosh, Samir PassiArtificial Intelligence Agents Cognitive Science
Hugging Face · Data & Society
BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation
Aug 23, 2026Jiaqi Wang, Zhuo Zhang, Haining Guan +15Microscopic Traffic Simulations Playable Video World Generation
AFARI World Model Team
Closing the loop in learning with missing data
Aug 10, 2026Dimitrios Pylorof, Humberto E. GarciaMissing Data Learning Dynamics
U.S. Department of Energy Idaho National Laboratory
You Don't Need To Stay in The Loop: An Agentic Robotics Loop for Robot-Policy Improvement
Aug 2, 2026Hang YuRobot Policies Agent Loop
Independent Researcher, United States.
LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation
Jul 31, 2026Han Li, Zhemin Fang, Rili Feng +8Coding Agents Agent Loop
Microsoft · Nanjing University · Shanghai Jiao Tong University +1
Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering
Jul 23, 2026Wenchao Ma, Changran Liu, Sharon X. Huang +1Autoregressive Video Generation Generative Video Models
Roblox · The Pennsylvania State University
Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation
Jul 20, 2026Peng Ren, Haoyang Ge, Jiang Zhao +4Humanoid Loco-Manipulation Goal-Conditioned Dynamic Manipulation
1BUAA · 2BZA · 4DeepCybo +2
Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents
Jul 20, 2026Yitao Wu, Si Shen, Rui Yang +2Verification Framework Self-Verification
saofund.ai, Shenzhen, China · Shenzhen Xingqing Zhiti Technology Co., Ltd., Shenzhen, China · School of Information Technology and Engineering, Lanzhou University, Lanzhou, China
Loop the Loopies!
Jul 17, 2026Zitian Gao, Yilong Chen, Yihao Xiao +4Transformer Architectures Mixture-Of-Experts Large Language Models
IQuest Research
A Predict-then-Correct Loop Based on Few-Shot Continuous Contextual Bandit for Demand Forecasting
Jul 17, 2026Zhiwei Lei, Benedict Jun Ma, Ilya JacksonContextual Bandit Framework Loop
Thrust of Intelligent Transportation, Hong Kong University of Science and Technology (Guangzhou), China · Center for Transportation and Logistics, Massachusetts Institute of Technology, USA
DeepLoop: Depth Scaling for Looped Transformers
Jul 15, 2026Shuzhen Li, Yifan Zhang, Jiacheng Guo +2Transformer Residual Streams Transformer Architectures
Princeton University · University of California, Los Angeles
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
Jul 8, 2026Mingguang Chen, Licheng Wang, Bo QuRecursive Self-Improvement Self-Evaluation
University of California, Riverside (UCR) · AlphaAvatar · Illinois Institute of Technology (IIT)
Memory in the Loop: In-Process Retrieval as ExtendedWorking Memory for Language Agents
Jul 6, 2026Yusuf Khan, Carlo LipizziWorking Memory Loop
Stevens
EvalLoop: A Methodology for Evaluation-Driven Iterative Improvement of Business AI Systems
Jul 6, 2026Kenneth Benavides, Josh Fleischer, Danti ChenLoop Methodology
Robert Half
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
Jun 30, 2026Ying Fan, Anej Svete, Kangwook LeeEfficient Latent Reasoning Chain-of-Thought Reasoning
Microsoft Research · 2ETH Zürich · 3KRAFTON +1
Knowing in Advance When an Evolutionary Outer Loop Will Not Help: A Pre-Registered Cheap-Baseline Screening Rule
Jun 28, 2026Ramchand KumaresanScreening Early Stopping
Murai Labs
PinNet: Keypoint-Aware Learned Local Descriptors with Geometric Embedding for Loop Closure in LiDAR SLAM
Jun 26, 2026Yanlong Ma, Nakul S. Joshi, Christa S. Robison +2Point Cloud Registration Visual Place Recognition
University of California, Los Angeles, Los Angeles, CA, USA. · DEVCOM Army Research Laboratory (ARL), Adelphi, MD, USA.
Semantic Early-Stopping for Iterative LLM Agent Loops
Jun 25, 2026Sahil ShrivastavaEarly Stopping Large Language Model Agents
Semantic Halting Problem (SHP) Project
Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist
Jun 24, 2026Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby +5Cognitive Science Artificial Intelligence Scientists
Princeton AI Lab, Princeton University
Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation
Jun 17, 2026Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas +2Linear Activation Steering Symbolic Music Generation
Athens University of Economics and Business, Athens, Greece · Orfium Research, Athens, Greece · Hellenic Mediterranean University, Chania, Greece +2
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Jun 16, 2026Jian Yang, Shawn Guo, Wei Zhang +16Code Optimization Loop
1Beihang University · 2IQuest Research · 4Renming University of China +1
Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models
Jun 15, 2026Martin JaggiMixture-Of-Experts Large Language Models Experts
EPFL
Can Editing 1 Neuron Fix Repetition Loops in LLMs?
Jun 9, 2026Aristotelis Lazaridis, Aman Sharma, Dylan Bates +3Instruction-Tuned Models Repetition
Edgerunner AI
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
Jun 4, 2026Ziyue Li, Yang Li, Tianyi ZhouLLM Inference Optimization LLM Reasoning Strategies
University of Maryland, College Park, MD, USA · 2MBZUAI, Abu Dhabi, UAE.
Closing the Loop on Latent Reasoning via Test-Time Reconstruction
Jun 4, 2026Xiaopeng Yuan, Haibo Jin, Ye Yu +4Efficient Latent Reasoning Loop
University of Illinois Urbana-Champaign · Google · Florida State University
The Differentiable Auditory Loop (DAL): An ML Framework for Hyper-Personalized Hearing Aids
Jun 2, 2026Alejandro Ballesta Rosen, Jason Mikiel-Hunter, Julian Maclaren +3Dysarthric Speech Loop
1Google Research Australia · 2Macquarie University
Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery
Jun 1, 2026Ekaterina Alimaskina, Darya Rudas, Denis Shveykin +3Large Reasoning Models Large Language Model Quantization
BRAIn Lab, Moscow, Russia
SEMBridge: Tagless-Final Program Semantics with Weakest-Precondition and Bounded-Checking Interpretations
May 29, 2026Eric LiangFormal Verification Proof
Oracle
When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop
May 28, 2026Yang Zhang, Xiukun Wei, Xueru ZhangPreference Alignment Reinforcement Learning From Human Feedback
Department of Computer Science and Engineering, The Ohio State University, Columbus, Ohio.
ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
May 27, 2026Yihan Xia, Taotao WangJournal Loop
Shenzhen University, China
GrowLoop: Self-Evolving Conversation Evaluation Seeded by Human
May 26, 2026Yihang Lin, Yunze Gao, Zeyang Lin +3Dialogue Benchmarks Co-Evolution
Amap, Alibaba Group · The Chinese University of Hong Kong, Shenzhen
Voices in the Loop: Mapping Participatory AI
May 16, 2026Rashid MushkaniArtificial Intelligence Governance Atlas
Right to AI · Mila – Québec AI Institute, Canada
Solve the Loop: Attractor Models for Language and Reasoning
May 12, 2026Jacob Fein-Ashley, Paria RashidinejadLarge Language Model Pretraining Transformer Architectures
University of Southern California
Simply Stabilizing the Loop via Fully Looped Transformer
May 11, 2026Rao Fu, Zixuan Yang, Jiankun Zhang +4Transformer Architectures Loop
Hong Kong Baptist University · Jilin University
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
May 7, 2026Jingjie Ning, Xiaochuan Li, Ji Zeng +2Auto Research Loop
School of Computer Science, Carnegie Mellon University
Closing the Loop: Unified 3D Scene Generation and Immersive Interaction via LLM-RL Coupling
May 7, 2026Anh H. Vo, Sungyo Lee, Phil-Joong Kim +23D Scene Generation Immersion
Department of Computer Engineering, Sejong University, Seoul, Republic of Korea
HumanSplatHMR: Closing the Loop Between Human Mesh Recovery and Gaussian Splatting Avatar
May 4, 2026Yeheng Zong, Pou-Chun Kung, Yike Pan +4Human Mesh Recovery Avatar Reconstruction
University of Michigan
Grammar-Constrained Refinement of Safety Operational Rules Using Language in the Loop: What Could Go Wrong
Apr 26, 2026Khouloud Gaaloul, Zaid Ghazal, Madhu Latha Pulimi +1Safety Claims Cyber-Physical System
University of Michigan–Dearborn Dearborn, MI, USA
Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization
Apr 25, 2026Ziyang Liu, Xinyan Guo, Xuchen Wei +2Self-Evolution Evolutionary Optimization Methods
Shenzhen X-Institute; Soochow University · Soochow University · Shenzhen X-Institute +2

Oct 1, 2026, cs.CVJ/K move · Enter open · S save

CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction

Moyang Li, Zihan Zhu, Wei Zhang, Marc Pollefeys+1

ETH Zurich · University of Stuttgart · Microsoft

Feed-Forward 3D Reconstruction 3D Reconstruction Loop

Open paper AskPDF arXiv

Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in long-context streaming reconstruction due to error accumulation. In this paper, we revisit loop closure with streaming reconstruction foundation models to enable accurate, drift-free, kilometer-scale reconstruction. Specifically, our method detects loop candidates through global descriptor retrieval, and constructs loop-conditioned windows to estimate the relative poses between looped frames. Given the observation that our adopted streaming reconstruction backbone produces a globally consistent scale, we optimize all frame poses on the SE(3) manifold with sequential and loop closure constraints, avoiding the pose graph optimization on the Sim(3) or higher-dimensional SL(4) manifolds employed in prior works. Extensive experiments show that our method reduces drift and produces consistent geometry on kilometer-scale sequences, significantly outperforming the state of the art. Code is available at https://github.com/MoyangLi00/CLoSeR.git.

Momentum

Related topics

Latest papers 66