CS Paper Radar

Weekly top 20

2026-W42 Oct 12 – Oct 18, 2026

Ranked from 5,357 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

Immersive Focus+Context Techniques to Assist in Interpretation of High Density Forest Point Clouds

cs.HC ·2026-10-16 ·Spencer O'Keeffe, Jan Rombouts, Bruce H Thomas, Michelle Balasso, Jim O'Hehir +1 more
top venuecode/datahighly cited
Abstract

Virtual Reality (VR) is changing how we interact with complex spatial datasets. VR has the potential within forestry to help analyse remotely sensed spatial data for inventory management. However, challenges of scale and legibility of dense forest point clouds must be addressed. To do so, we present three VR Focus+Context (F+C) techniques: Wedgelight, Remote Lantern, and Ray Lantern. These techniques present point cloud data using a constrained highdetail focus within a broader abstracted context representation, manipulated using egocentric and exocentric interactions. We conducted two user studies. The first informed the design of the F+C techniques. The results from the first study indicate that VR significantly outperforms desktop displays in basic analysis of forestry point clouds, with improvements to both time and accuracy. The second study evaluated the performance of the resulting F+C techniques in a task analogous to real-world forestry operations. Our F+C techniques significantly outperformed current approaches, confirming their viability for facilitating detailed and effective forest assessments. These findings indicate that VR has significant advantages for spatial data analysis tasks in forestry, making a strong argument for its adoption in future analytical frameworks. The F+C visualisation techniques we introduced show considerable promise for analysis of high density point clouds, opening new avenues for development in immersive analytics. Supplemental materials (code, scans, results) are available at https://osf.io/hqc9u.

0.82
2

Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data

cs.CL cs.CR ·2026-10-16 ·Zesheng Shi, Xue Li, Chenrui Dai, Jing Li
top venuepositioncode/data
Abstract

LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model must follow the former while rejecting the latter. Existing defenses suppress or trust all external instructions, collapsing the safety-utility frontier and forcing a choice between over-refusal and over-compliance. We argue the missing capability is \textbf{per-instruction credit attribution} and formalize it as External-Data Instruction Classification, an identify-classify-act decision over each embedded directive. We propose \textbf{EDIC}, a decomposed reward framework for per-instruction compliance. A scene-grounded pipeline injects mixed beneficial and harmful instructions with counterfactual filtering, while a generative judge is initialized by SFT and refined with GRPO to attribute compliance at the instruction level. The judge then produces a reward that separately encourages beneficial compliance and penalizes harmful compliance for RL training. Across two backbones and five benchmarks, EDIC improves both safety and utility over the strongest prior defense, lifting harmful-rejection by up to 7.7\% and Arena-Hard-Auto utility by 12.5\% on Qwen3-4B. The code repository is hosted at https://github.com/yingyingxia666/EDIC.

0.82
3

Measuring Data Diversity with Embeddings: A Taxonomy and Benchmark for Diversity Measures

cs.CL cs.LG ·2026-10-17 ·Cantao Su, Anna Wegmann, Esther Ploeger, Dong Nguyen
top venuebenchmarkcode/datahot direction
Abstract · Published in the Proceedings of EMNLP 2026 (Main), pages 11241-11271. Code and data: https://github.com/nlpsoc/EmbDivBench

Diversity is a critical property of text corpora, with direct implications for training data curation, test set design, and model generalization. However, its measurement remains fragmented and poorly understood. Existing embedding-based diversity measures vary widely in how they are computed and can yield substantially different diversity scores on the same data, yet no systematic comparison of their empirical behaviour exists. We make two contributions toward addressing this gap. First, we present a taxonomy of 21 embedding-based diversity measures, organizing them into four families based on their underlying computations. Second, we introduce EmbDivBench, a benchmark that evaluates these measures along three conceptually distinct components (variety, balance and disparity) on both simulated and natural text data. Although Mean Pairwise Distance is the most commonly used measure, our experiments show that it is outperformed by several alternatives on the three diversity components, with Graph Entropy being the best choice overall. Lastly, we distil these findings into practical recommendations for diversity measure selection.

0.80
4

ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts

cs.AI ·2026-10-12 ·Zhaoyu Fan, Bowen Han, Jincheng Ou, Yanwei Ren, Zehua He +6 more
top venuebenchmarkcode/data
Abstract · 42 pages, 5 figures, including appendix. Accepted by NeurIPS'26. Code and benchmark: https://github.com/ZyFanTJ/ProCARE

Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effects, monitor safety, and identify risk factors outside randomized trials. Automating RWS with large language model agents is appealing but brittle: valid analyses depend on dataset-specific clinical semantics, including index dates, follow-up windows, patient/event-level units, and outcome boundaries that are often implicit in observational data. This leads to schema mismatches, temporal errors, inconsistent analytical granularity, and unsupported clinical claims. We present ProCARE, a profile-grounded framework that reformulates RWS automation as constrained compilation. ProCARE converts heterogeneous data profiles into Evidence Contracts specifying available variables, temporal attributes, distributions, and evidentiary limits, and compiles study objectives into RWS-IR, a strongly typed intermediate representation for variables, time relations, analysis units, and statistical tasks. Deterministic validation and localized repair then check and revise generated workflows across schema mapping, cohort construction, variable derivation, analysis, and interpretation. On 36 EHR-based benchmark tasks, ProCARE outperforms strong LLM-agent baselines in code executability, semantic consistency, and conclusion traceability, with automated violation diagnoses showing moderate-to-substantial agreement with blinded expert review.

0.74
5

Geometric Hashing in MPC with Applications to Clustering and Stochastic Embeddings

cs.DS cs.CG ·2026-10-15 ·Sujoy Bhore, Arnold Filtser, Eunjin Oh, Hyeonjun Shin, Himanshi Singh
top venue
Abstract · To appear in SODA'27

In this paper we study consistent hashing (a.k.a. sparse partitions) for doubling metrics in the Massively Parallel Computation (MPC) model. A $(Γ,Λ)$-hash with diameter bound $Δ$ partitions a metric space into clusters of diameter at most $Δ$ such that every ball of radius $Δ/Γ$ intersects at most $Λ$ clusters in expectation. Consistent hashing has emerged as a central tool in geometric MPC algorithms. However, so far it has been solely used in Euclidean spaces, where it can be pre-computed. On the other hand, in cases where the metric space is received as input and unknown in advance, no previous parallel construction was known. We present the first fully scalable MPC algorithm over machines with local space $n^σ$, that given an $n$-point metric space with doubling dimension $d\leq O(σ\log n)$, samples a randomized $(Γ,2^{O(d/Γ)})$-hash in $O(d/σ^3)$ rounds. There is a dichotomy: if the doubling dimension is $d=Ω(σ\cdot\log n)$, a polynomial number of rounds is required to compute such a hash. We conclude by showing that this MPC primitive yields $O(d/σ^3)$-round fully scalable MPC algorithms for a broad class of fundamental geometric problems in doubling metrics, including stochastic tree embeddings with $O(\log n)$ expected distortion, constant factor approximation for facility location, bicriteria $(O(ε^{-2}),1+ε)$-approximation for $k$-median and $k$-means.

0.74
6

Multics: Generative Multi-Player World Model with Hierarchical Communication

cs.CV ·2026-10-12 ·Kaiyi Huang, Wangbo Yu, Yukun Huang, Jiwen Yu, Kunhao Liu +4 more
code/datahot directioncommunity pick
Abstract · Project page: https://karine-huang.github.io/Multics/

Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains challenging. Existing approaches that rely on fully-connected communication (e.g., Solaris) incur quadratic attention costs as the number of players grows, while centralized approaches (e.g., $γ$-World) suffer from interference between unrelated events in a shared global representation. To address these challenges, we present Multics, a multi-player video generation framework with hierarchical communication that structures information exchange across player, group, and global levels. This hierarchy introduces group tokens into self-attention as intermediate group-level representations that aggregate locally relevant player information. These tokens connect to global tokens for cross-group communication, while the hierarchical topology limits direct mixing between unrelated local events. Group-token parameters are shared across group slots, allowing the same communication module to accommodate varying numbers of players without introducing new group-specific parameters. We further propose budget-constrained dynamic grouping based on recent camera trajectories, which adaptively groups relevant players while limiting unnecessary communication. Experiments demonstrate that Multics achieves state-of-the-art performance in 4- and 6-player settings, with improved cross-player consistency, player-specific action and camera controllability, and interference robustness. Moreover, Multics generalizes from 4-player training to 6-, 8-, and 10-player inference without retraining, while reducing self-attention computation compared with fully-connected communication.

0.74
7

MissPath-FM: Flow Matching with Structured Priors for Partially Observed Time Series

cs.LG ·2026-10-13 ·Genpei Zhang
top venuecode/data
Abstract · Accepted at NeurIPS 2026. 24 pages. Project page: https://zgp110.github.io/misspath-fm/ Code: https://github.com/zgp110/misspath-fm

Flow matching has emerged as a powerful alternative to diffusion models for generative modeling, but standard conditional flow matching is fundamentally misaligned with partially observed time series: starting from an uninformed Gaussian source forces the model to transport even already-observed entries from noise to the target, wasting capacity on trivially known regions. We propose MissPath-FM, a partial-observation-aware flow matching framework that redesigns the source prior and probability path for incomplete time series. MissPath-FM employs structured source priors (interpolation priors and Gaussian process posterior priors) to initialize the flow close to the observed signal, paired with a missingness-aware smooth path that allocates transport asymmetrically between observed and missing regions. We evaluate systematically across four datasets, four missingness mechanisms (MCAR, block, MNAR, irregular), two missing ratios, and three sequence lengths (T in {24, 48, 96}), totaling 48 settings against eight baselines. MissPath-FM wins 29 of 32 settings at T=48 and 45 of 48 overall (93.8%). Our ablations reveal a regime-dependent design hierarchy in which no single component suffices: under random missingness the source prior yields a large initial gain, but under structured block missingness it can fail entirely and the learned flow becomes indispensable; the missingness-aware path contributes a further 12%-26% across all regimes. Mechanistically, structured priors shorten observed-region transport by up to 15x, concentrating the velocity field on genuinely uncertain entries. Project page: https://zgp110.github.io/misspath-fm/

0.74
8

Information Estimation with Discrete Diffusion

cs.LG cs.IT ·2026-10-16 ·Alberto Foresti, Giulio Franzese, Pietro Michiardi
top venuecode/datahighly cited
Abstract · Published as a conference paper at ICLR 2026 (Poster). ICLR Paper: https://proceedings.iclr.cc/paper_files/paper/2026/file/238747e153a84f50b…

Information-theoretic measures, such as Mutual Information (MI), play a crucial role in understanding non-linear relationships between random variables and are widely used across scientific disciplines. Yet, their use on real-world discrete data remains challenging. Existing methods typically rely on embedding discrete data into a continuous space and apply neural estimators originally designed for continuous distributions. This process requires careful engineering for both the embedding model and estimator architecture, but suffers from issues related to high data dimensionality. In this work, we introduce InfoSEDD, a discrete diffusion-based approach that bridges information-theoretic estimation and generative modeling such that they can be used to compute Kullback-Leibler divergences. Backed by Continuous Time Markov Chains theory principles, the design of InfoSEDD is lightweight and scalable and allows seamless integration with pretrained models. We showcase the versatility of our approach through applications on motif discovery in genetic promoter data, semantic-aware model selection in text summarization, and entropy estimation in Ising models. Finally, we construct consistency tests on real-world textual and genomics data. Our experiments demonstrate that InfoSEDD outperforms alternatives that rely on the "embedding trick". Our results position InfoSEDD as a robust and scalable tool for information-theoretic analysis of discrete data.

0.73
9

OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling

cs.CL ·2026-10-15 ·Bowei Liu, Xinchen Zhang, Xuhuan Li, Tianlin Zhang, Kaian Jiang +8 more
publishedcode/datacommunity pick
Abstract · NeurIPS 2026. Project: https://github.com/Cominclip/OmniVerifier

Generative visual verifiers play a crucial role in advancing multimodal intelligence. To enhance the robustness of visual verifiers in complex multimodal scenarios involving compositional requirements, we move beyond conventional binary verifiers that produce only True/False discrete judgments and introduce a verifier that automatically decomposes complex prompts or environmental rules into fine-grained components and assigns pointwise scores to provide a continuous and more informative critique signal. Our experiments further demonstrate that these structured and interpretable outputs improve the verifier's generalization to out-of-domain multimodal critic tasks. To train this verifier, we introduce a Decoupled RL training strategy that jointly optimizes sub-question-level binary judgment and global alignment scoring, using precise local feedback to develop fine-grained verification capabilities that provide a foundation for reliable continuous scoring at the global level. Under a general reinforcement learning framework, we first empirically demonstrate that the proposed pointwise graded verifier significantly outperforms binary verifiers in traditional text-to-image scenarios. We then extend our investigation to rule-governed generative world modeling where generative models are leveraged for world simulation and world reasoning under explicit rules. From a theoretical standpoint, we further show that a pairwise verification paradigm yields more accurate critiques than the pointwise formulation when ground-truth images are available, with empirical results on diverse structured world-modeling tasks such as Maze and Sudoku further validating the effectiveness of our approach. Overall, our findings suggest a key insight: the transition from generative models to structured world-modeling agents critically hinges on the availability of accurate pairwise graded visual verifiers.

0.73
10

Temporal Periodic Image Registration with Implicit Neural Representations

cs.CV cs.LG ·2026-10-15 ·Mathias Lowes, Kristine Aavild Sørensen, Maxime Sermesant, Rasmus R. Paulsen
top venuecode/data
Abstract · Published at MLMI@MICCAI 2025

Implicit Neural Representations (INRs) have recently gained popularity for their ability to model functions using simple and lightweight networks. These methods have also proven effective in deformable image registration. In this work, we extend INRs for deformable image registration to the domain of temporal image registration, focusing on periodic temporal image sequences. Our approach, Temporal-IDIR, optimizes a single INR to model deformations across all frames in a temporal image sequence simultaneously, allowing for self-regularization through its own deformation predictions. To achieve this, we introduce a temporal consistency loss that penalizes discrepancies between direct source-to-target transformations and those traversing intermediate frames. We evaluate our framework on the DIR-LAB dataset, using the target registration error (TRE) between annotated and moved landmarks as the metric. Here, we achieve a TRE of 1.03 mm, outperforming other INR-based registration methods. Additionally, our framework supports smooth interpolation between time frames by estimating deformations between the given input frames. Code is publicly available at https://github.com/MMLowes/Temporal_INR.

0.73
11

Unlocking Token Rewards via Training-Free Reward Attribution

cs.AI ·2026-10-13 ·Sitong Wu, Haoru Tan, Bin Xia, Xichen Zhang, Jingyao Li +4 more
top venuecode/data
Abstract · token-level reward, credit assignment, PRM, RL

In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model. Our core idea is to attribute the overall process reward to individual tokens by estimating each token's influence. This influence is defined as the change in the final macroscopic reward (e.g., the process reward) when a token is replaced with a semantically null token. Naively calculating this influence is computationally infeasible, requiring N forward passes through the PRM for an N-token sequence. We overcome this bottleneck by proposing a highly efficient gradient-based estimator. Specifically, we use a first-order Taylor approximation, which simplifies the influence calculation to the inner product of the difference between the token embedding and the null token embedding, and the gradient of the reward with respect to the token embedding. This requires only a single forward and backward pass. The resulting token-level rewards enable standard RL algorithms to perform precise credit assignment without requiring additional reward model training. Experiments on challenging reasoning benchmarks demonstrate that our method substantially improves policy optimization efficiency and enhances the generalization of LLM reasoning capabilities. Our P2T outperforms the outcome reward by +4.9% on MathVista for Qwen2.5-VL-7B-Instruct, and +11.5% on AIME24 for Qwen2.5-Math-7B. The code will be released via https://github.com/stonewst/P2T.

0.72
12

AdaBool: Sparse Boolean Matrix Processing with Adaptive Data Representation

cs.DB cs.DC ·2026-10-15 ·Xiangrui Yang, Yifan Lei, Jiawei Yang, Yekang Zhan, Yuxin Zheng +4 more
top venue
Abstract · Accepted to ACM SIGMOD 2027 (Proceedings of the ACM on Management of Data). 16 pages, 21 figures, 7 tables

Many data processing tasks revolve around determining whether logical relationships exist between two sets of entities, a pattern that can be naturally modeled as Sparse Boolean Matrix Multiplication (SpBMM). Under Boolean semantics, matrix representations no longer need to store numerical values and instead focus on encoding the positions of non-zero elements, making it highly amenable to data compression for substantially lower memory access overhead. The key challenge, however, is that the most effective compression depends heavily on sparsity distribution: different methods perform best at different sparsity levels, while real-world matrices often contain sharply varying sparsity across regions. Consequently, forcing the entire matrix into any fixed, monolithic representation leaves considerable optimization opportunities untapped. We present AdaBool, a SpBMM framework designed to reconcile this tension through an adaptive data representation. AdaBool partitions matrices into fine-grained element blocks and represents each block with the encoding best matched to its local sparsity. On top of this adaptive encoding, AdaBool introduces a heterogeneous GPU execution model that groups blocks by encoding type and maps them to matching processing paths, enabling efficient execution and scheduling across GPU resources. We implement AdaBool end to end with low-level system optimizations, evaluate it on both production and public workloads, and show that it outperforms representative baselines by over an order of magnitude.

0.72
13

Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations

cs.CL cs.LG ·2026-10-12 ·Bryce Grant, Peng Wang
publishedcode/data
Abstract · NeurIPS 2026 Poster, ICLR Unifying Concept Representation Learning

Prior research into interpretability does not test whether a representation stays consistent under paraphrasing. Each pair of paraphrases can be thought of as a local witness that two activations should be the same. From these local witnesses we can build a cellular sheaf on the paraphrase graph. The question of what is consistent under paraphrasing can be answered by the Laplacian $L_\mathcal{F}$ given a frozen model. No training required. Our kernel $H^0$ gives us a content subspace. We show that with only 20 dims the kernel outperforms the subspace that LEACE retains with all dims on held-out CounterFact fact retrieval by $+17.1$\,pp on average across 8 models. By constraining all paraphrases of a fact together we see an additional increase of $+6.5$\,pp. Our spectral complement shows us where the causal influence is concentrated. Ablating the coordinates that vary the most when paraphrased (which approximates ablating the spectral complement at the coordinate level) leads to $5.6$ to $26.5\times$ larger changes in model outputs compared to ablating coordinates with matched per-coordinate variability. We find this across 9 models from 124M to 13B params. By stacking layers we can create a grid which has $b_1 = N(L-1)$ algebraic 1-cycles. The harmonic mass derived from the model varies by nearly 3 orders of magnitude between the 6 architectures. It also tracks the order of steering fragility (Spearman's $ρ= 0.90$, exact one-sided permutation $p = 0.014$). The kernel, its spectral complement and the harmonic mass all come from the same paraphrase graph. Project page: https://cwru-aism.github.io/gluing-lc-page/.

0.71
14

Calibrated Disambiguation for Partial Multi-label Learning

cs.LG cs.CV ·2026-10-13 ·Zhuoming Li, Yuheng Jia, Mi Yu, Zicong Miao
top venuehighly cited
Abstract · The paper is accepted by AAAI 2025

Partial multi-label learning (PML) aims to train a classifier on datasets whose instances are over-annotated with not only relevant labels but also irrelevant labels, which is common when datasets are collected from crowd-sourcing platform. Existing works primarily approach it from a curriculum learning perspective, leveraging the memorization effect to disambiguate noisy labels and produce robust predictions. However, these methods are based on non-adaptive weighting functions and lack theoretical guidance for optimal weighting. To overcome these issues, a calibrated disambiguation model named PML-CD is proposed. We first formulate the optimal weighting function for curriculum-based disambiguation, which is equivalent to the calibration of the model's predicted confidences, thus providing guidance for curriculum designing. To obtain the optimal weighting function from PML dataset during the training, a transferable calibrator is designed, which takes the histogram of positive samples' confidences as input, and outputs the optimal curriculum weighting for training. Prototype alignment regularization is also proposed to promote the model's performance. Experiments conducted on Pascal VOC, MS-COCO, NUS-WIDE and CUB have verified that our method outperforms existing state-of-the-art PML methods.

0.71
15

A Novel Coexistence Scheme for OFDM and OTFS Waveforms for Uplink in 6G Networks

eess.SP ·2026-10-12 ·Badr Eddine Ouakouak, Salah Eddine Zegrar, Hüseyin Arslan
top venue
Abstract · Published in IEEE Transactions on Communications, Date 2025/7/10, Volume 73, Isse 11, Page range 12008-12022

The upcoming sixth generation (6G) wireless networks are designed to support advanced applications that the current air interface based on orthogonal frequency division multiplexing (OFDM) cannot accommodate, necessitating innovations in waveform design. Orthogonal time frequency space (OTFS) has emerged as a promising alternative, offering enhanced performance particularly in high-mobility channel environments. However, deploying fundamentally different waveforms over the same frequencies fails to exploit the mutual relationships between them. In this paper, a forward-compatible yet backward-compatible coexistence framework is proposed, where various OFDM waveform options are incorporated while seamlessly integrating OTFS within the same network. The proposed coexistence paradigm involves utilizing a specially designed spreading matrix in the delay-Doppler (DD) domain to process OTFS data. The matrix is tailored to establish orthogonality between OTFS and OFDM waveforms, effectively reducing cross-interference when both coexist within the same time-frequency (TF) resources. Our results demonstrate up to a 6 dB improvement in bit error rate (BER) performance for the OTFS waveform compared to other coexistence schemes. The proposed approach also shows greater interference resilience and approaches the upper bounds of achievable rates. By utilizing the full bandwidth and time duration, it enhances range and velocity resolutions, leading to improved sensing performance. These findings are supported by mathematical analysis and extensive simulations for uplink scenarios.

0.69
16

LEV: Thinking Fast and Deep with Looped Decision Models

cs.AI cs.CLcs.LG ·2026-10-14 ·Dingjie Song, Zhiling Yan, Yuxuan Zhang, Lichao Sun
code/datacommunity pick
Abstract · 28 pages. Code: https://github.com/OpenLAIR/lev

Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text. Like the fast System 1 of dual-process theory, they answer at once, but their depth is fixed at training time, so they spend the same computation on easy and hard questions. Models that reason in generated text can think longer, but they pay for every extra step in decoded tokens. We present LEV, a decision model that thinks deeper by rerunning its layers in a loop instead of generating tokens. LEV builds on a language model pretrained as a loop, reads the options after every loop step and trains all steps jointly, so one checkpoint can answer at any depth. On three looped backbones, accuracy rises with depth on the same weights, mostly on hard questions, and a 2.6B LEV goes from 63.2% at depth one to 76.2% at depth four on JevBench. On-demand depth, set per question by a small stopper with a threshold fitted on unlabelled requests, saves 15% to 24% of the computation at a cost of under one accuracy point, level with or slightly above a fixed mix of depths. On a locked test set, the 1.4B and 3B models are 5.4 to 8.8 points more accurate than dense (non-looped) models and cascades of the same latency below 50 ms.

0.68
17

BenchChecker: Assessing the Credibility of Bug-Fixing Benchmarks for LLMs

cs.SE ·2026-10-14 ·Di Wu, Xu He, Shu Wang, Kun Sun
top venuecode/data
Abstract · Published in USENIX Security 2026

While Large Language Models (LLMs) show promise for Automatic Program Repair (APR), existing benchmarks suffer from data contamination, in which test samples appear in training sets, artificially inflating performance. To address this, we propose BenchChecker, a framework compatible with both open-source and closed-source models that supports more credible evaluation by detecting such contamination. Grounded in the observation that persistent patches likely remain in recent repository snapshots used for training, BenchChecker employs a forensics-based two-stage detection process using only textual model outputs together with public repository history. The first stage conducts a repository presence test by probing the model with code prefixes to infer training inclusion; the second stage performs a patch presence test to verify patch persistence via similarity alignment and test-suite verification. Evaluations using StarCoder-15B, StarCoder2-15B, and CodeGen2-16B trained on The Stack v2 demonstrate that BenchChecker achieves robust detection with AUC scores around 0.9 across six benchmarks. Furthermore, applying BenchChecker to SWE-bench Verified and Multi-SWE-bench reveals that filtering contaminated samples reduces the reported resolution rates of most LLMs by more than 20% relative to the original rates on medium-difficulty tasks.

0.68
18

QIEN: Quantum-Inspired Energy-Neutral UAV Trajectory for WPT-Enabled Industrial HRLLC

eess.SY ·2026-10-16 ·Ali Ranjha, Georges Kaddoum, Halim Yanikomeroglu
publishedbenchmark
Abstract · 14 pages. Accepted for publication in IEEE Transactions on Vehicular Technology. This work was supported by the Postdoctoral Research Fellow…

This paper introduces Quantum-Inspired Energy-Neutral (QIEN) UAV Trajectory for WPT-Enabled Industrial HRLLC, a novel framework for mobility-integrated trajectory and resource optimization in solar-powered uncrewed aerial vehicle (UAV) relay systems supporting autonomous mining robots in post-disaster environments. We formulate a mixed-integer nonlinear program (MINLP) that jointly optimizes UAV trajectory, finite blocklength allocation, transmit power, and wireless power transfer (WPT) over discrete time horizons to maximize aggregate data throughput. The system operates under strict extreme hyper-reliable low-latency communication (HRLLC) constraints, energy sustainability requirements via solar harvesting, and continuous robot power delivery. To solve this large-scale optimization problem, QIEN employs a hybrid Cooperative Quantum-behaved Particle Swarm Optimization (Co-QPSO) algorithm using quantum tunneling mechanisms and a heterogeneous swarm architecture. Our simulation results demonstrate that the proposed QIEN framework significantly outperforms benchmark algorithms, achieving successful convergence while maintaining energy-neutral operation and satisfying all reliability, power, and mobility constraints.

0.65
19

NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models

cs.RO cs.LG ·2026-10-16 ·Guodong Du, Wanyu Lin
top venuecode/data
Abstract · Camera-ready version accepted at NeurIPS 2026. Updated to the final conference format and included the NeurIPS checklist. 30 pages, 3 figure…

Vision-language-action (VLA) models can learn a wide range of robotic skills, but combining separately trained skills remains challenging. The original training data may be unavailable for joint retraining, while directly merging model weights can cause interference. We propose NestedVLA, which consolidates independently fine-tuned VLA policies without access to their original training data. Instead of merging all updates into one checkpoint, a hypernetwork embedded in the VLA generates action-expert weight updates for a selected task. Each task's compressed vision-language model update is stored separately, and both updates are added to a frozen base VLA to instantiate the corresponding policy. We evaluate NestedVLA by consolidating three policies fine-tuned with reinforcement learning on MetaWorld, ManiSkill, and CALVIN. It achieves 66.7% average success, improving on the strongest model-merging baseline by 41.1 percentage points. It performs within 1 percentage point of per-task fine-tuning on ManiSkill and substantially narrows the gap on CALVIN. In this three-policy setting, total storage is 1.5x that of a single full checkpoint. Code is available at https://github.com/WanyuGroup/NeurIPS2026-NestedVLA.

0.65
20

Does Client Diversity Protect the Lightning Network? Evidence from the 2026 Core Lightning Shutdown

cs.CR ·2026-10-14 ·Saurabh Kumar
code/dataunusual
Abstract · v2: client inference rules v4 (CLN and Eclair separated by feature bit 5 instead of keysend) with a rules table; node shares and reachabilit…

Client diversity is often cited as the Lightning Network's defence against a bug in any one implementation, yet LND runs 80% of public nodes (84% counting one operator's fleet of about 2,000 tiny nodes) and holds 84% of public channel capacity, a capacity share that has barely moved since 2023. We test what diversity buys with a natural experiment. On 26 August 2026, amid security fixes in every implementation, Core Lightning (CLN) maintainers told operators who could not upgrade to disconnect their nodes. Using 805 daily gossip snapshots, 132,360 on-chain channel closes and a client classifier validated against self-identifying aliases and against the wallet that builds each node's funding transactions, we find that 22% of CLN nodes went dark overnight, ten times the usual rate, mostly Tor-reachable ones; a third were still dark five weeks later. The rest of the network barely noticed. Reachability among all node pairs fell by 7.8 percentage points, a loss exceeded in 4 of 94 ordinary two-day windows and half that of a Tor denial-of-service wave in July, while among CLN pairs it fell by 24.5 points, more than in any ordinary window. Calibrated failure scenarios explain the containment: the blast radius depends on whether a failure reaches the hubs, not on how many nodes run the failing software. Losing ACINQ's Eclair node alone costs the surviving network four times the reachability lost with all 619 routable CLN nodes, and minority clients' reliance on LND for connectivity is what their size implies; CLN nodes in fact peer with each other more than chance. Diversity statistics that count nodes mislead; the quantity to track is which software the hubs run.

0.61