CS Paper Radar

Weekly top 20

2026-W44 Oct 26 – Nov 01, 2026

Ranked from 4,790 papers submitted on 7 days. Each research area gets slots in proportion to its share of this week's papers (at least one), filled by score; near-duplicates are removed. Why

Score = weighted mean ofCitations 20%Upvotes 10%Code stars 10%Venue 15%Code/data 10%Novelty 15%Momentum 15%Substance 5%how it works
1

GPU-accelerated Incremental Euclidean Distance Transform for Online Motion Planning of Mobile Robots

cs.RO ·2026-10-30 ·Yizhou Chen, Shupeng Lai, Jinqiang Cui, Biao Wang, Ben M. Chen
top venuecode/datahighly cited
Abstract · Published in RA-L 2022. Author-accepted manuscript. Code: https://github.com/JINXER000/GIE-mapping

In this letter, we present a volumetric mapping system that effectively calculates Occupancy Grid Maps (OGMs) and Euclidean Distance Transforms (EDTs) with parallel computing. Unlike these mappers for high-precision structural reconstruction, our system incrementally constructs global EDT and outputs high-frequency local distance information for online robot motion planning. The proposed system constructs OGM with massive amount of data from multiple types of sensor inputs. Using GPU programming techniques, the system quickly computes EDT in parallel within local volume. The new observation is continuously integrated into the global EDT using the parallel wavefront algorithm while preserving the historical observations. Experiments with datasets have shown that our proposed approach outperforms existing state-of-the-art robot mapping systems and is particularly suitable for mapping unexplored areas. In its actual implementations on aerial and ground vehicles, the proposed system achieves real-time performance with limited onboard computational resources.

0.87
2

APPlace: Co-Optimizing Device Locations and Access Points for Routing-Aware Analog Placement

cs.AR ·2026-10-29 ·Bingyang Liu, Xiaohan Gao, Souradip Poddar, David Z. Pan
top venuecode/data
Abstract · Accepted to ASP-DAC 2027. 8 pages, 6 figures, 4 tables. Code: https://github.com/bingyang1132/applace

Analog layout automation remains challenging in Analog/Mixed-Signal circuit design, because parasitics and mismatches introduced during layout strongly affect circuit performance. Placement is especially critical among the layout stages, as it constrains the routing solution space and the achievable post-layout performance. Existing analytical placement methods optimize device coordinates under center-based wirelength proxies and leave access point (AP) selection to routing. In analog circuits, however, a routing pin is an extended piece of terminal metal rather than a fixed point, and the best AP on it depends on where the other connected devices are placed, so a coordinate-only placement optimizes for connection points that the router will not use. We present APPlace, a routing-aware analog placement framework that co-optimizes device locations and AP selections during global placement, followed by a legalization stage that preserves the structure established by global placement. Experimental results on four real-world analog benchmarks show that APPlace achieves better overall post-layout performance than representative baselines at comparable layout area. Ablation studies further show that removing AP co-optimization causes up to a 13 dB CMRR loss among the OTA benchmarks and a 23% increase in comparator delay.

0.87
3

Visual-Inertial RGB-D SLAM with Encoders for a Differential Wheeled Robot

cs.RO ·2026-10-30 ·Zhanghao Zhu, Yutaka Kaizu, Kenichi Furuhashi, Kenji Imou
publishedcode/datahighly cited
Abstract · 11 pages. Author-accepted manuscript of the article published in IEEE Sensors Journal, 2022

Recent years have seen multiple impressive results in visual-inertial odometry (VIO) techniques, by which accurate state estimation can be achieved via the extended Kalman filter (EKF) or nonlinear optimization. However, these approaches are rarely open source, and they tend to fail in real experiments due to the temporary lack of feature points and fast motion. Therefore, in this study, we used encoders to overcome the temporary failure of purely vision-based simultaneous localization and mapping (SLAM). Here, we propose a generative measurement model for encoders and derive an expression for the maximum a posteriori (MAP) estimate and necessary Jacobians for optimization. We use our theory to present a novel tightly coupled visual-inertial encoder RGB-Depth (RGB-D) SLAM system. Tests on our system on an in-house dataset confirmed that our modeling effort led to accurate (with a root mean squared error (RMSE) of approximately 2-7 cm) and robust state estimation in real time. The source code and our dataset containing the encoder information have been published for verification.

0.74
4

FairSplit: Decomposing the Embedding Space for Fair Classification

cs.LG ·2026-10-28 ·Andrii Shkabrii, Anna Beer, Ylli Sadikaj, Claudia Plant
top venuecode/datahot direction
Abstract · Accepted at NeurIPS 2026

Fair classification faces a twofold challenge: maintaining high classification accuracy while limiting reliance on sensitive information. Our method FairSplit achieves this by learning a decomposition of the embedding space into a Fair Space used for prediction and a Sensitive Space that isolates sensitive information. During training, the model must simultaneously learn the classification task and separate fair from sensitive information. The Sensitive Space gives sensitive attributes a destination, so the Fair Space can be used for prediction without relying on them. This decomposition is guided via a learnable mask and the Hilbert-Schmidt Independence Criterion (HSIC) as a measure of statistical dependence. We provide theoretical guarantees showing that the demographic parity gap is upper-bounded by both (i) the learned dimensionality of the Fair Space and (ii) the HSIC between the Fair Space and sensitive attributes. FairSplit effectively handles multiclass tasks and non-binary sensitive attributes, overcoming key limitations of existing fair classification methods. Experiments on established fairness benchmarks show that FairSplit achieves competitive accuracy-fairness trade-offs. Code is available at https://github.com/shkabrii/fairsplit.

0.74
5

Lossless Compression of Proximity Graph Indexes for Efficient Approximate Nearest Neighbors Search

cs.IR ·2026-10-27 ·Francesco Benocci, Leonard Dahlmann, Francesco Gargiulo, Tobias Heuer, Silvio Martinico +3 more
top venuecode/data
Abstract · 7 pages, 5 figures, Accepted at CIKM 2026. Code: https://github.com/TusKANNy/kannolo. Reproducibility: https://github.com/tusKANNy/papers_re…

Graph-based Approximate Nearest Neighbor (ANN) indexes, such as HNSW, are the backbone of modern vector search. However, their massive memory footprint creates a severe infrastructure bottleneck. While vector quantization is widely adopted to reduce the memory required to store data vectors, the graph's edge structure increasingly dominates total memory usage. Compressing these adjacency lists for online search presents a critical system challenge: because decompression occurs during query processing, i.e., while navigating the graph, memory savings cannot come at the expense of query latency. In this paper, we present a compression technique explicitly tailored for live HNSW routing. By applying offline graph permutations to artificially induce structural locality, we enable the use of SIMD-accelerated integer compressors, such as Stream VByte, for rapid on-the-fly decompression. Evaluated across diverse real-world workloads, we significantly outperform the current state of the art in both compression ratio and query latency. Our experimental results show that we achieve compression ratios up to 52.7% with negligible penalties in latency compared to the uncompressed baseline. Furthermore, our technique has been effectively deployed in production at eBay, achieving up to 44.3% reduction in edge storage with no degradation in query latency.

0.73
6

On the complexity of isomorphism problems for tensors, groups, and polynomials V: over commutative rings

cs.CC math.ACmath.NT ·2026-10-31 ·Joshua A. Grochow, Youming Qiao, Katherine E. Stange, Xiaorui Sun
top venuehighly cited
Abstract · 74 pages, extended abstract appeared at STOC'25, abstract shortened to meet arXiv requirement

Tensors over commutative rings naturally appear in number theory, geometry, and group theory. For example, $2\times 2\times 2$ tensors over $\mathbb{Z}$ form the starting point of Bhargava's celebrated works generalising Gauss's composition law (Bhargava, Ann. Math., 2004). Symmetric tensors over $\mathbb{Z}$ are central to the classification of Calabi--Yau threefolds (Yau, Commun. Pure Appl. Math., 1978; Wall, Invent. Math., 1966), geometric objects of significance in string theory. Additionally, tensors over finite commutative rings closely correspond to finite nilpotent groups of class 2 (Baer, Trans. Am. Math. Soc., 1938). In this work, we study isomorphism testing of tensors over commutative rings from a complexity-theoretic viewpoint, and its applications. Some of our main results are: 1. Let $\mathrm{R}$ be a commutative ring. We introduce two complexity classes: $\mathsf{3TI}_\mathrm{R}$ consisting of problems that are polynomial-time reducible to isomorphism problems of tensor products of three modules over $\mathrm{R}$, and $\mathsf{3FTI}_\mathrm{R}$ consisting of problems that are polynomial-time reducible to isomorphism problems of tensor products of three free modules over $\mathrm{R}$. 2. We show that some classical problems considered by Grunewald and Segal (ibid.), and the problem of classifying Calabi--Yau threefolds, are $\mathsf{3FTI}_\mathbb{Z}$-complete. We also show that many natural problems are complete for $\mathsf{3TI}_{\mathbb{Z}/p^e\mathbb{Z}}$. 3. We show that testing isomorphism of tensors in $\mathbb{Z}^2\otimes\mathbb{Z}^2\otimes\mathbb{Z}^2$ is polynomial-time equivalent to the principal ideal problem in algorithmic number theory. 4. We present an $N^{O((\log N)^{8/9})}$-time algorithm for testing isomorphism of finite nilpotent groups of class $2$ and odd order $N$.

0.73
7

FedAvgIm: Federated Learning for Multi-Site Impedance Identification of Inverter-Based Resources

eess.SY ·2026-10-26 ·Quang Manh Hoang, Guilherme Vieira Hollweg, Akhtar Hussain, Wencong Su, Van-Hai Bui
top venue
Abstract · Author-accepted manuscript (not the IEEE version of record)

With the increasing integration of inverter-based resources (IBRs) into power systems, assessing small-signal interaction stability has become essential. Impedance/admittance models enable frequency-domain characterization of IBR dynamics without requiring access to proprietary internal control details, but measurement-based identification is time-consuming and must be repeated across operating points. This paper proposes FedAvgIm, a privacy-aware federated-learning framework for multi-site dq-admittance identification under severe local data scarcity and raw-data-locality constraints. Each IBR site trains a local feed-forward neural network using a small set of operating-point-frequency samples, while only model parameters are shared with a cloud aggregator that performs sample-size-weighted FedAvg to update a global model and broadcast it back to all sites. To demonstrate effectiveness, EMT measurement-based admittance datasets are constructed for nine grid-following IBRs with different parameters, architectures, measurement-noise levels, and non-IID settings, where each client has only 40-390 training samples. Results show that FedAvgIm achieves performance close to centralized training and consistently outperforms local-only learning and raw-data-locality-preserving transfer-learning baselines. Additional studies show that FedAvgIm maintains stable learning behavior under measurement noise and remains beneficial under moderate non-IID conditions. The estimated dq-admittance models are further applied to generalized Nyquist stability analysis and validated against EMT time-domain simulations under multiple operating points and grid-strength conditions.

0.72
8

Bilinear Hulls for Support Splitting: Characterization, Optimization, and Applications

cs.CR cs.IT ·2026-10-31 ·Yusuke Aikawa, Keita Ishizuka, Tomoki Moriya
publishedtheory
Abstract · 25 pages. Accepted to SAC 2026; to appear in Lecture Notes in Computer Science (Springer). Author's accepted manuscript

Sendrier's Support Splitting Algorithm (SSA) is the standard solver for the Permutation Equivalence Problem (PEP); its cost is dominated by a term that grows exponentially in the hull dimension. We study, mathematically, how much this cost can be lowered by replacing the standard inner product, on which the hull is defined, with an alternative bilinear form. Two structural results give a complete answer: only a narrow two-parameter family of bilinear forms produces a hull on which SSA can still operate, namely those whose matrix in the standard basis is a linear combination of the identity and the all-ones matrix; and even within this family the hull dimension drops by at most one (with the reduction achieved on every self-dual code whose length is coprime to the field characteristic). Together, these results give a tight upper bound: since SSA on a code with hull dimension $h$ has cost dominated by $q^h$, replacing the standard hull with $\mathrm{Hull}_M$ lowers this dominant term from $q^h$ to at best $q^{h-1}$, so no bilinear-form generalization of the inner product can reduce the SSA cost by more than a factor of $q$, the field size. Going beyond this requires invariants outside the bilinear framework. As an application, we verify that PEP-based SPECK admits the factor-$q$ cost reduction, while LEP-based LESS and PKP-based PERK lie outside our framework. A SageMath implementation of the bilinear-hull preprocessing confirms feasibility at SPECK's recommended length $n = 252$.

0.72
9

Is Newborn Wiring Special? Separating Wiring from Weight Placement in Connectome Reservoirs

cs.NE ·2026-10-31 ·Riccardo Bertamini, Corrado Calamita, Ramiro Pascual, Alisia Picciano, Niccolò Pagano
publishedcode/dataunusual
Abstract · Accepted at the NeurIPS 2026 Workshop on Developmental Perspectives on AI (DevAI). 17 pages, 5 figures, 2 tables. Code: https://github.com/R…

Reservoir computing offers a way to study the brain's wiring before it is even trained. The recurrent network remains fixed, while only a linear readout is trained. The human connectome is found to perform better than randomly rewired versions of itself, suggesting that biological wiring is special. To understand the source of this advantage, a mathematical graph-theoretic decomposition is introduced. Rewiring a weighted network changes both the regions that are connected and the weights assigned to those connections. The observed advantage therefore combines an effect of wiring with an effect of weight placement. These effects are separated by averaging the wiring term over the null model's weight rule, as a single draw introduces about one z-unit of noise. Adult and infant connectomes are then considered separately. In adult Human Connectome Project graphs, weight placement explains most of the reported effect, leaving a small but consistent wiring effect. Across the full dHCP release, a large wiring effect is found at every measured gestational age at birth, while gestational age explains almost none of its variance. The connectomes are also compared with non-brain networks. A Watts-Strogatz graph matched in size, edge count, weights, and strength performs as well as or better than the connectome. The newborn connectome's advantage is therefore real across all measured gestational ages, but it is not unique to the brain. The same separation can be applied whenever a weighted network is compared with rewired nulls.

0.72
10

Micro-Edits: Computational Support for Fine-Scale Edits in Film

cs.HC cs.CV ·2026-10-29 ·Nhan Tran, Hijung Valentina Shin, Abe Davis, Mackenzie Leake
top venuecode/data
Abstract · UIST 2026 Best Paper Honorable Mention. Project page: https://microedits.github.io/

In film editing, every frame matters. While macro, content-level edits shape the high-level narrative of a film, small local edits often control timing and direct visual attention. For example, editors can adjust the precise timing of clips to control the length of a meaningful silence, or cut to shots that highlight a specific character's reactions to important moments. These small, detailed edits are slow and tedious to make in standard editing tools because users have to map high-level narrative goals to low-level frame-by-frame adjustments. At the same time, these fine-scale adjustments, which we call micro-edits, can be nuanced and expressive, with different choices serving different creative goals. In this work, we start by conducting a formative study with professional editors to understand the structure of micro-edits and how they are used. We then derive a mathematical formalization for this structure to develop tools that leverage AI and optimization to make exploring micro-edits simpler and more efficient for users. Finally, we validate our tools in multiple user studies and a wide range of video examples.

0.72
11

Assessing feature scorer results on high-dimensional datasets with t-SNE

cs.LG cs.AI ·2026-10-28 ·Bruno Iochins Grisci, Mario Inostroza-Ponta, Márcio Dorn
publishedcode/dataunusualhighly cited
Abstract

While vast literature on high-dimensional data visualization is available, there are not many works regarding the visualization of feature scorers and their results. Feature scorers are algorithms that assign numerical importance to each feature of multi-dimensional datasets. These importance scores can be used in several applications, such as feature selection, knowledge discovery, and machine learning interpretability. There are several feature scorers to choose from, and often no single metric or ground truth is available to guarantee the quality of their results. In this scenario, visualization can become valuable to support the decision of which method to choose and how good its results are. For this goal, this work presents "weighted t-SNE." It modifies the relationship between data points in the embedded 2D space to reflect the importance of each dimension of the original datasets as assessed by a feature scorer. This research discusses how to implement weighted t-SNE, proposes the silhouette coefficient as a numerical evaluation of the results, and shows several examples of its use in practice. Synthetic and real-world tabular datasets are used in the experiments together with nine feature scorers, ranging from Mutual Information to neural networks. Each feature scorer produces unique visualizations, and weighted t-SNE can be used to compare and choose the one that better suits a given dataset and task. Weighted t-SNE can also visually show the importance of features learned by machine learning models and help us see how they are organizing the data, increasing their interpretability.

0.71
12

Batching the Reflective Optimization Loop: Parallel Proposals Make GEPA Faster and Better

cs.AI cs.CLcs.LG ·2026-10-27 ·Jialin Zhang, Lakshya A Agrawal, Shangyin Tan, Donghyun Lee, Lutfi Eren Erdogan +4 more
publishedcode/data
Abstract · NeurIPS 2026 Workshop on Resource-Aware Agentic AI. 9 pages, 7 figures. First four authors contributed equally. Code: https://github.com/gep…

Reflective text optimization makes agentic systems better, but the optimization loop is itself a resource-hungry workload whose sequential structure leaves parallel evaluation capacity idle. We extend the open-source GEPA optimizer to propose and evaluate a batch of candidates on each optimization step instead of one candidate at a time. In our sweep on two tasks, most batched runs finished in half the wall-clock time or less, and the fastest in about a quarter to a third. Batched settings also achieved higher held-out test scores, from 68.9% to 72.1% on LiveBench-Math (with $2\times2$) and from 49.0% to 60.0% on HoVer (with $8\times1$). A simple runtime model explains the measured speedups under a finite worker pool, and batched settings also spend their metric-call and dollar budgets more efficiently. We frame the axes along which a reflective optimization step can scale in parallel, a first look at allocating a fixed optimization budget across them.

0.71
13

AK_QMUL at ArGuard Shared Tasks: A Single Fine-Tuned JAIS for Arabic Harmful-Prompt Detection

cs.CL ·2026-10-26 ·Ali Khairallah, Arkaitz Zubiaga
publishedhot direction
Abstract · Published at ArabicNLP 2026 (Shared Tasks), co-located with EMNLP 2026. ACL Anthology: https://aclanthology.org/2026.arabicnlp-sharedtasks.4…

We present AK_QMUL's submissions to the ArGuard-2026 shared tasks on Arabic harmful-prompt detection: a binary safe/unsafe task (B1) and a seven-way harm-domain task (B2). Both submissions use one backbone -- JAIS-6.7B fine-tuned with 4-bit QLoRA and a linear classification head over its last-token representation. For B1 we train a four-way head that factors the label by dialect register {safe, unsafe} x {MSA, other}, we augment the training fold with MSA prompts from AraSafe, and decode with a plain argmax to score safe/unsafe. For B2 we fine-tune the same backbone as a seven-way classifier and average the softmax outputs of five random seeds. Both submissions ranked first on their track, with macro-F1 0.984 on B1 and 0.790 on B2. We report results by dialect and by class: on B1 the model is accurate across all six dialects (93.6--99.8%) and its predicted unsafe rate tracks the true rate closely; on B2 six of the seven classes reach F1 between 0.73 and 0.98, with the residual error concentrated in the Bully class, which overlaps semantically with harassment and harm-to-others.

0.70
14

Saidzoda-Tajik-LFM-2.6B: Adapting a 2.6B Hybrid Model to Tajik Tool Calling, and What Continued Pretraining Takes Away

cs.CL ·2026-10-30 ·Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov, Abubakr Abdullozoda, Amin Jalilov +3 more
benchmarkcode/dataunusual
Abstract · 12 pages, 9 tables, 3 figures. Technical report. Model: https://huggingface.co/Tohirju/Saidzoda-Tajik-LFM-2.6B

We release Saidzoda-Tajik-LFM-2.6B, a Tajik adaptation of the 2.6B-parameter hybrid model LFM2.5-2.6B-Base, built for tool calling in Tajik on modest hardware. The recipe has two stages: LoRA continued pretraining (CPT) on 1,485,319 cleaned Tajik web documents for 3 epochs, then one epoch of supervised fine-tuning (SFT) on a mix of machine-translated Tajik tool calls, English tool calls kept as replay, and Tajik instructions. On a 174-item tool-calling test set built from BFCL v3 and machine-translated to Tajik, strict full-call accuracy on Tajik prompts rises from 20.69 for the base model to 64.14 (paired difference +43.45 points, 95% interval +35.2 to +51.7); a lenient parser that also accepts the base model's own call formats puts the base at 31.72. English shows no detectable change (76.55 and 77.24). Every CPT checkpoint scores zero: CPT removes the native tool-call format and, as the lenient re-scoring shows, part of the skill itself. Outside tool calling, accuracy on a Tajik knowledge benchmark rises from 28.0 to 35.0, Belebele Tajik shows no significant change, and English MMLU falls from 60.8 to 52.5. The model is not a general Tajik assistant. It almost never declines when no tool fits (6.9% correct on Tajik, against 31.0% for the base under the lenient parser), it is weak at multi-turn calls, and its calls should be checked before they are executed. We describe the data, the training settings and every evaluation in enough detail to repeat them.

0.70
15

Multi-criteria Rating and Review based Recommendation Model

cs.IR ·2026-11-01 ·Emrul Hasan, Chen Ding, Alfredo Cuzzocrea
publishedpositionhighly cited
Abstract · 10 pages. Accepted version of the paper published in the 2022 IEEE International Conference on Big Data (Big Data). (c) 2022 IEEE

These days, due to the advancement of information technology, recommendation system has become one of the key tools for e-commerce business. E-commerce platforms allow users to provide feedback in both written comments and numerical ratings. Recommendation systems are utilized to recommend users to new or unseen items based on these previously collected comments or ratings. In recent years, multi-aspect or multi-criteria based recommendation systems have been studied a lot by the recommendation research community. However, these research works are conducted either with reviews or ratings, not with both. In this project, we argue that integrating both textual reviews (with multiple aspects) and numerical multi-criteria ratings can further enhance the overall rating prediction accuracy. We propose a Multi-criteria Rating and Review based Recommendation model (MRRRec). We show that incorporating multi-criteria ratings into multi-aspect ratings from reviews has a great impact on performance. Our proposed model outperforms several state-of-the-art models such as ANR, DeepCoNN, and Deep Multi-criteria Recommendation System in terms of MSE, MAE, precision, recall, and F1. We show that our proposed model achieves an average of 19% and 23.0% lower MSE and MAE respectively and 7.0%, 1.0% and 3.8% higher precision, recall, and F1 score respectively. We further show that our model performs significantly better with Word2Vec word embedding than the GloVe word embedding method.

0.68
16

Cyber-physical attack detection approaches in the wide-area measurement system

cs.LG ·2026-10-30 ·Zakaria El Mrabet, Prakash Ranganathan
published
Abstract

Improving situational awareness within the Smart Grid is an effective preventive measure to detect potential anomalies, and avoid their adverse consequences. A wide area measurement system (WAMS) based Phasor Measurement Unit (PMU) can assist in improving visibility within the grid by collecting relevant measurements including magnitude, phase angle, frequency, voltage, and current, with a precise GPS-based timestamp. So far, there are more than 2500 PMUs deployed in the North American power grid, where each of which generates between 30 and 60 samples/s, roughly 1.5 TB/month of streamed data. Thus, processing such large PMU streams requires expensive computational resources and faster algorithms. This paper provides state-of-the-art cyber and physical anomalies in the WAMS and analyses their impact on the integrity and availability of the system. Next, it investigates the current anomaly detection approach in historical and streaming PMU data, including conventional machine learning and hybrid approaches, and assesses their advantages and main drawbacks. Lastly, it sheds light on the importance of handling missing PMU data and concept drifts.

0.68
17

Exploring perceptual straightness in learned visual representations

cs.LG cs.CV ·2026-10-26 ·Anne Harrington, Vasha DuTell, Ayush Tewari, Mark Hamilton, Simon Stent +2 more
top venuehighly cited
Abstract · Published at ICLR 2023

Humans have been shown to use a "straightened" encoding to represent the natural visual world as it evolves in time (Hénaff et al. 2019). In the context of discrete video sequences, "straightened" means that changes between frames follow a more linear path in representation space at progressively deeper levels of processing. While deep convolutional networks are often proposed as models of human visual processing, many do not straighten natural videos. In this paper, we explore the relationship between network architecture, differing types of robustness, biologically-inspired filtering mechanisms, and representational straightness in response to time-varying input; we identify strengths and limitations of straightness as a useful way of evaluating neural network representations. We find that (1) adversarial training leads to straighter representations in both CNN and transformer-based architectures but (2) this effect is task-dependent, not generalizing to tasks such as segmentation and frame-prediction, where straight representations are not favorable for predictions; and nor to other types of robustness. In addition, (3) straighter representations impart temporal stability to class predictions, even for out-of-distribution data. Finally, (4) biologically-inspired elements increase straightness in the early stages of a network, but do not guarantee increased straightness in downstream layers of CNNs. We show that straightness is an easily computed measure of representational robustness and stability, as well as a hallmark of human representations with benefits for computer vision models.

0.68
18

[Re] Pure Noise to the Rescue of Insufficient Data

cs.CV cs.LG ·2026-10-31 ·Seungjae Ryan Lee, Seungmin Brian Lee
publishedcode/data
Abstract · Reproducibility study of Zada et al. (arXiv:2112.08810). Published in ReScience C 9(2), #45 (2023), ML Reproducibility Challenge 2022. 15 pa…

We examine the main claims of Zada, Benou, and Irani (2021), which states that in an image classification task with imbalanced training data, (i) using pure noise to augment minority-class images encourages generalization by improving minority-class accuracy. This method is paired with (ii) a new batch normalization layer that normalizes noise images using affine parameters learned from natural images, which improves the model's performance. Moreover, (iii) this improvement is robust to varying levels of data augmentation. Finally, the authors propose that (iv) adding pure noise images can improve classification even on balanced training data. We implemented the training pipeline from the description of the paper using PyTorch and integrated authors' code snippets for sampling pure noise images and batch normalizing noise and natural images separately. We reproduced the main claims that (i) oversampling with pure noise improves generalization by improving the minority-class accuracy, (ii) the proposed batch normalization (BN) method outperforms baselines, (iii) and this improvement is robust across data augmentations. Our results also support that (iv) adding pure noise images can improve classification on balanced training data. However, additional experiments suggest that the performance improvement from OPeN may be more orthogonal to the improvement caused by a bigger network or more complex data augmentation.

0.67
19

BEACON: Distilled Begin/End-Aware Structured Decoding for Continuous Sign Language Segmentation

cs.CV ·2026-10-29 ·Guohou Zhang, Kalin Stefanov
published
Abstract · Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2027. 12 pages, 4 figures, including supplementary mate…

In segmentation-based continuous sign language recognition, an untrimmed video is first partitioned into lexical units; segmentation is therefore a means to an end---downstream recognition. However, segmenters are usually judged by local boundary detection rather than by the quality of the lexical segments and the recognition they enable. We present BEACON, a begin/end-aware segmenter that combines four-class Outside/Begin/Inside/End (BIOE) labeling, constrained Viterbi decoding over eight legal transitions, and boundary knowledge distilled from a binary teacher into a shared student. Under strict no-cut evaluation with validation-based model selection, BEACON improves segment-F1 by 14.58/14.59 points and boundary-F1 by 2.17/1.22 points, and reduces the downstream word error rate (WER) by 9.10/4.15 points relative to the state-of-the-art in the PHOENIX-14/BSL Corpus. To examine which segmentation metric better reflects downstream recognition, we evaluated five distinct architecture families. Segment-F1 aligns more consistently with lower WER than boundary-F1 in both corpora (Spearman $ρ=-1.0/-0.9$ versus $-0.9/-0.8$). These results support evaluating sign language segmentation in terms of segment quality and downstream recognition utility rather than local boundary accuracy alone.

0.66
20

PR4Code: A Pull Requests Dataset for AI Code Generation

cs.SE ·2026-10-29 ·Benedetta Donato, Leonardo Mariani, Daniela Micucci, Oliviero Riganelli
publisheddataset
Abstract · Published in IEEE Access

AI-driven code generation is evolving from handling small, localized code-completion tasks toward supporting the implementation of full software features. To support this transition, this paper introduces PR4Code, a dataset of 4,508 Java and 8,831 Python curated Pull Requests (PRs) collected from GitHub, each enriched with metadata, commit histories, and detailed code changes. Unlike resources focused on isolated code fragments, PR4Code captures the feature implementation process, delivering a large and diverse collection of real-world development tasks that can be used to assess AI-driven solutions. Our analysis reveals substantial variability in PR structure, commit granularity, and textual content. In addition, we release scripts to regenerate and update the dataset, ensuring reproducibility and maintainability.

0.63