Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.22264v1 Announce Type: cross Abstract: State-of-the-art models for audio-driven digital human generation have achieved photo-realistic results in talking-head synthesis. However, extending...
arXiv:2609.22398v1 Announce Type: cross Abstract: Accurate delineation of bi-atrial structures from late gadolinium enhancement MRI (LGE-MRI) is an important prerequisite for structural analysis and...
arXiv:2609.23417v1 Announce Type: cross Abstract: Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor trajec...
arXiv:2404.06135v4 Announce Type: replace Abstract: The Transformer architecture has achieved remarkable success in natural language processing and high-level vision tasks over the past few years. Ho...
arXiv:2505.02393v3 Announce Type: replace Abstract: Most existing video anomaly detectors rely on RGB frames alone, which limit their ability to capture abrupt or transient motion cues that are criti...
arXiv:2508.01661v2 Announce Type: replace Abstract: Amodal segmentation aims to recover complete object shapes, including occluded regions, serving as an essential technique for user-centric multimed...
arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...
arXiv:2604.15281v2 Announce Type: replace Abstract: 3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and sev...
arXiv:2605.04515v2 Announce Type: replace Abstract: Video Large Language Models (Video-LLMs) excel in general video understanding but often base physical judgments on event expectations rather than o...
arXiv:2608.08381v2 Announce Type: replace Abstract: Motivated by the IEEE 802.11bf effort to standardize advanced WLAN sensing, interest in Wi-Fi Channel State Information (CSI) for passive, device-f...
arXiv:2609.15795v2 Announce Type: replace Abstract: Streaming geometric foundation models are emerging as a compelling alternative to SLAM systems. Yet this streaming nature introduces a fundamental...
arXiv:2607.11099v2 Announce Type: replace-cross Abstract: Reliable visual data association is fundamental to visual SLAM (V-SLAM), as it directly determines the quality of the camera pose estimation...
The paper introduces MFP, a reaction yield prediction method that uses role-aware Morgan fingerprints. It computes count-based circular fingerprints for each reaction component, aggregates them by chemical role, and combines them with transformation-sensitive difference features into a fixed-length descriptor for a feed-forward neural regressor. On the Suzuki‑Miyaura and Buchwald‑Hartwig benchmarks, MFP achieves R² scores of 0.878 and 0.969 respectively, while training an order of magnitude faster than graph or Transformer-based alternatives.
UniGIO is a generative framework that models global in‑situ weather dynamics directly from incomplete GIO data, unifying forecasting, imputation, and generation across arbitrary missing ratios. It employs an Observation Mixer, Event Aligner, Adaptive Temporal Mixer, and a Mixture‑of‑Experts structure to capture station‑level complementarity, temporal dependencies, and extreme events, refining outputs with a Local Refiner. Experiments on the Weather‑5K dataset show state‑of‑the‑art performance, improving accuracy, fidelity, and extreme event capture by 11%, 12%, and 5% respectively.
The paper introduces mutation analysis as a metric for evaluating GPU‑kernel benchmark oracles, injecting over ten thousand faults into verified CUDA implementations of 188 KernelBench problems. It shows that the current official checkers miss 16.9% of faults, with precision faults being especially problematic, and demonstrates that optimized test suites can achieve 98% detection with only two inputs per problem. The study also reveals flaws in existing patches and a fuzzing recipe that incorrectly rejects correct kernels 107 times.
The study evaluates six deep learning architectures for predictive maintenance in Industry 4.0, focusing on Recurrent Neural Networks (RNNs) and Transformers. It finds that Transformers perform well on stable, slow-moving data but overreact to noisy, chaotic data, whereas a hybrid model combining an LSTM layer with a Transformer layer better filters noise and delivers more consistent predictions. The hybrid approach improves accuracy and reliability across varying levels of data volatility.
The paper introduces paired, mechanism‑controlled stress tests that decompose changes in expected squared error for time‑series forecasting into environmental risk and forecast‑oracle distance. Using an origin‑conditioned predictive oracle, the authors validate three end‑to‑end controls and apply the benchmark to 24 forecasters, revealing that many models exhibit higher realized MSE yet lower oracle distance under frequent switching, and that environmental risk dominates in most scenarios. The study also demonstrates that visually compelling discovery profiles often fail to replicate on independent data‑generating process realizations, underscoring the importance of component‑wise diagnosis and held‑out stability audits.
The paper investigates whether the stable GAN architecture R3GAN can improve time‑series imputation when adapted to 1‑D temporal data. Using a coarse‑to‑fine refinement framework and a frequency‑domain discriminator, the authors evaluate 14 saved configurations across three datasets and find a negative result: most configurations either show negligible improvement or degrade performance compared to baseline methods. The study highlights that the usual argument—GANs optimize distributional objectives rather than point‑wise ones—does not fully explain the lack of benefit, and it poses an open problem regarding why a learned discriminator fails to provide useful refinement gradients while diffusion denoisers succeed, offering practical guidance on when adversarial refinement may be worthwhile.
The paper introduces OmicsBench, a new reasoning benchmark for multi‑omics sequences that includes 1,160 expert‑validated questions across DNA regulation, RNA processing, and protein function tasks, requiring traceable evidence chains. Evaluation of 17 large language models shows that scientific LLMs, while more accurate in classification, often lack valid evidence, suggesting shortcut learning. To address this, the authors propose tool‑augmented on‑policy distillation (TA‑OPD), a post‑training method that improves both evidence grounding and predictive performance across five Qwen3.5 models of varying sizes.
arXiv:2609. 23529v1 Announce Type: new Abstract: Neural operators have emerged as powerful surrogates for solving partial differential equations (PDEs), yet their reliability under distribution shift remains a critical barrier to deployment.