The paper introduces 2D GauSS-MI, an active scene reconstruction framework that uses 2D Gaussian Splatting (2DGS) to efficiently process incremental RGB‑D data. It presents an online 2DGS mapping pipeline and a probabilistic reliability model to assess view‑dependent reconstruction quality. Leveraging this model, the authors define a Shannon Mutual Information metric that guides active view selection, balancing visual and geometric quality while reducing computational cost and storage compared to state‑of‑the‑art baselines.
By Yuhan Xie, Jia Pan
OpenSAL360 is an open‑source platform that enables scalable, low‑cost collection of 360° video saliency data using only a standard screen, mouse, and internet connection. It bypasses the need for VR headsets, allowing parallel data collection from crowdsourced assessors. The authors validated the protocol against seven VR eye‑tracking datasets, performed ablation studies, and released a new dataset of 500 omnidirectional videos annotated by over 2,000 assessors, the largest in the field to date.
By Alexey Bryncev, Andrey Moskalenko, Kira Shilovskaya, Ivan Kosmynin, Dmitriy Vatolin
GEM-MPC is a reinforcement learning method that blends MPPI planning with policy learning to balance exploration and exploitation in high-dimensional continuous control tasks. It trains a policy to clone the planner while also maintaining a KL-regularized policy that explores around the planner’s suggestions, thereby improving the synergy between planning and learning. The approach introduces Gated Prior Distillation, which selectively updates policies from stored planning distributions only when they offer better targets, reducing the influence of stale data without costly reanalysis. Across continuous-control benchmarks, GEM-MPC outperforms existing planning-based baselines while using lower computational budgets.
By Alvaro Serra-Gomez, Thomas Moerland
arXiv:2609. 21872v1 Announce Type: cross Abstract: We introduce Chronosphere, a spatio-temporal neural field that learns representations of climate.
By Daniel Cher, Eric Xing, Kexing Li, Brian Wei, Isaac Corley, Nathan Jacobs
The paper introduces Prototype Purification and Regulation (PPR), a multi‑label few‑shot learning framework for medical image classification that addresses two key limitations of existing metric‑based meta‑learning methods. PPR first purifies prototypes by using sample‑level comorbidity scores to highlight disease‑specific features, then regulates inter‑class prototype distances with disease‑level comorbidity statistics to create a comorbidity‑aware embedding space. Experiments on four chest X‑ray datasets, including cross‑domain tests, show that PPR outperforms state‑of‑the‑art methods, improving disease detection and demonstrating robust generalization and clinical applicability.
By Ying-Chih Lin, Po-Chih Kuo, Yong-Sheng Chen
The paper revisits Breiman’s insight that lowering inter‑tree correlation can boost random forest performance. It introduces two new variants—Dirichlet‑Multinomial Bagging Random Forest (DM) and Dirichlet‑Weighted Random Forest (DW)—which adjust sample reweighting through a concentration parameter α>0. A theoretical criterion is presented to determine when these methods behave like standard random forests, guiding a lightweight tuning approach. Experiments on public classification benchmarks show DM and DW consistently match or outperform other random‑forest baselines with minimal extra runtime.
By Quoc Viet Le, Joonha Park
arXiv:2609.20824v1 Announce Type: new
Abstract: We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small Language Models (SLMs) with fewer than 3 billion...
By Prashant Mudgal
arXiv:2609.20839v1 Announce Type: new
Abstract: Phoneme-centric visual speech recognition reconstructs sentences from intermediate phoneme predictions, making overall recognition performance highly d...
By Matthew Kit Khinn Teng, Haibo Zhang, Takeshi Saitoh
The paper introduces a general framework for multi-domain clustering using measure quantization, where a shared set of cluster prototypes is learned by minimizing a probability metric (e.g., Sinkhorn divergence or Maximum Mean Discrepancy) between each domain’s probability measure and the prototype measure. Data points are assigned to clusters either by nearest centroid or via optimal transport, a collaborative strategy that couples all samples within a domain. A mini‑batch optimization strategy makes both fitting and assignment scalable, reducing memory and computational cost while preserving clustering performance, and experimental results on five multi‑domain benchmarks (image, audio, and sensor data) show that the Sinkhorn‑based method consistently outperforms classical and multi‑domain clustering baselines, even when scaling to hundreds of thousands of samples.
By Rafael Pereira Eufrazio, Eduardo Fernandes Montesuma, Charles Casimiro Cavalcante
BrainWideBench is a benchmark that evaluates across‑animal transfer on multi‑region neural recordings from 139 mice, covering 276 brain regions. It comprises three task suites—behavior decoding, neural activity prediction, and anatomical organization recovery—to test whether learned representations support diverse downstream objectives. The benchmark shows that while pretraining improves performance over single‑session baselines, current methods vary in transfer ability and none perform uniformly well across all suites, highlighting the challenge of developing general‑purpose neural representations.
By Alexandre Andre, Shivashriganesh P. Mahato, Vinam Arora, Keshav Balaji, Divyansha Lachi, Nanda H. Krishna, Jingyun Xiao, Yizi Zhang, Ximeng Mao, Wenrui Ma, Han Yu, International Brain Laboratory, Daniel Birman, Niccol\`o Bonacchi, Gaelle A. Chapuis, Joana A. Catarino, Felicia Davatolhagh, Mayo Faulkner, Laura Freitas-Silva, Fei Hu, Julia M. Huntenburg, Anup Khanal, In\^es Laranjeira, Petrina Lau, Guido T. Meijer, Nathaniel J. Miska, Jean-Paul Noel, Alejandro Pan-Vazquez, Georg Raiser, Cyrille Rossant, Karolina Z. Socha, Anne E. Urai, Miles J. Wells, Steven J. West, Olivier Winter, Blake Richards, Guillaume Lajoie, Cole Hurwitz, Mehdi Azabou, Matthew R. Whiteway, Liam Paninski, Eva L. Dyer
The paper introduces Survival Reinforcement Learning (SRL), an online classification-based method that extends the survival value learning framework to maximize an agent’s dwell time at target goals. SRL addresses limitations of contrastive reinforcement learning (CRL) in long-horizon, goal-conditioned tasks by avoiding the uniformity-tolerance dilemma and reducing undesirable bang-bang control behaviors. Across robotic benchmarks, SRL matches CRL on manipulation tasks and outperforms it by 2x to 8x on stable, long-horizon locomotion tasks, suggesting classification-based approaches are a promising direction for scaling reinforcement learning.
By Franki Nguimatsia-Tiofack, Fabian Schramm, Th\'eotime Le Hellard, Justin Carpentier
arXiv:2609.21084v1 Announce Type: cross
Abstract: Modern automatic speech recognition (ASR) systems trained on extremely large datasets can produce transcripts with numbers written in Arabic numerals...
By Stanis{\l}aw Kacprzak, Mieszko Fra\'s
arXiv:2511.13254v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have displayed remarkable capabilities across diverse domains, but their training remains resource- and time-intensive...
By Shalini Maiti, Amar Budhiraja, Bhavul Gauri, Gaurav Chaurasia, Anton Protopopov, Alexis Audran-Reiss, Michael Slater, Despoina Magka, Tatiana Shavrina, Roberta Raileanu, Yoram Bachrach
arXiv:2609.21347v1 Announce Type: new
Abstract: Recent progress in 3D Gaussian Splatting (3DGS) has enabled dense visual SLAM with pinhole cameras, yet most pipelines are not designed for panoramic i...
By Xiangfei Guo, Hao Shi, Yufan Zhang, Zhonghua Yi, Yongqi Mao, Xiaoting Yin, Kaiwei Wang
arXiv:2609.21593v1 Announce Type: new
Abstract: Four-dimensional scanning transmission electron microscopy (4D-STEM) records a two-dimensional diffraction pattern at each electron-probe position, yie...
By Yuyan Guan, Haoran Zhang, Zian Mao, Antong Yang, Caifei Li, Jialong Wang, Chuying Ouyang, Hong Wang, Xiaoqin Zeng, Yujun Xie
arXiv:2504.06647v4 Announce Type: replace
Abstract: Safety-critical autonomous driving motivates the effective use of prior information. For online vectorized HD map construction, temporal prediction...
By Nan Peng, Xun Zhou, Mingming Wang, Guisong Chen, Wenqi Xu
The paper investigates how the topology of attention graphs can differentiate hallucinated from non-hallucinated responses in large language models. By analyzing Forman-Ricci curvature, the authors identify structural bottlenecks and develop a method that captures both semi-local and global information-flow characteristics of attention heads associated with hallucinations. Extensive evaluation across multiple LLMs and benchmarks shows that this single-pass approach consistently outperforms existing attention-based and multi-response baselines, while also revealing that impaired context sharing—such as over-reliance on self-attention and information over-squashing—correlates strongly with hallucination occurrences.
By Amir Jalilifard, Anderson Rocha, Eric Wong, Marcos Medeiros Raimundo
The paper introduces a two‑step test‑time training protocol, Embed‑TTT, for Vision ARC (VARC) that first fine‑tunes only the task embedding and then fine‑tunes the backbone. This approach consistently produces task embeddings that better align with the underlying rules, improves retrieval and linear probing, and recovers the geometric structure of parametric rules. Even fine‑tuning only the tiny embedding component solves a significant portion of ARC‑AGI‑1, ConceptARC, and Mini‑ARC tasks, while the full two‑step pipeline further enhances performance and demonstrates compositional rule interpolation.
By Adrien Deli\`ege, Claas Beger, Marc Van Droogenbroeck, Melanie Mitchell
arXiv:2609.21208v1 Announce Type: new
Abstract: Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but...
By Ana Nunez, Peyman Najafirad
The paper introduces an ability‑residual decoupled framework for affective cognitive diagnosis, which first isolates unmodeled cognitive residuals—such as item calibration bias, concept bias, and student‑concept deviations—using student, item, concept, student‑concept, and low‑rank student‑item components. It then applies an affective module that modulates guess/slip effects, with a Q‑matrix‑constrained concept residual attention mechanism to aggregate only item‑relevant concept residuals. Experiments on multiple datasets and backbones demonstrate improved response prediction and better affect alignment, while ablation and analysis studies show that the residual modeling reduces cognitive contamination in the affective branch and enhances robustness and accuracy.
By Boyuan Zhao, Meng Ye