Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.24813v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in multimodal tasks, yet they still exhibit poor ability in spatial reasoning....
arXiv:2609.22397v1 Announce Type: cross Abstract: Purpose: Contrast-enhanced breast MRI depends on intravenous gadolinium-based contrast agents, motivating methods that synthesise post-contrast appea...
arXiv:2609.22854v1 Announce Type: cross Abstract: Vision-language-action models often predict actions from only the current observation, which can leave tasks involving object occlusion or visually i...
arXiv:2609.23797v1 Announce Type: cross Abstract: Human motion is shaped by both external acoustic events and behavioral intent: spatial audio conveys environmental cues that elicit or guide a respon...
arXiv:2411.15921v3 Announce Type: replace Abstract: The removal of multiplicative Gamma noise is a critical research area in the application of synthetic aperture radar (SAR) imaging, where neural ne...
arXiv:2509.04276v3 Announce Type: replace Abstract: We present a method for modeling articulated objects from sparse images with unknown camera poses. Existing approaches require dense multi-view obs...
arXiv:2509.25998v4 Announce Type: replace Abstract: In light of recent progress in video editing, deep learning models focusing on both spatial and temporal dependencies have emerged as the primary m...
arXiv:2511.18921v2 Announce Type: replace Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously ac...
arXiv:2605.12072v3 Announce Type: replace Abstract: Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. E...
arXiv:2605.29655v4 Announce Type: replace Abstract: Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D t...
arXiv:2607.06023v2 Announce Type: replace Abstract: Visual SLAM is a well-established technology utilized in a wide range of real-world applications. However, its performance still degrades under cha...
arXiv:2607.12186v2 Announce Type: replace Abstract: In-loop filters have been comprehensively explored during the development of video coding standards due to their remarkable noise-reduction capabil...
arXiv:2607.27585v2 Announce Type: replace Abstract: As primary consumers in the marine food chain, zooplankton play a crucial role in maintaining marine ecological balance. However, the Segment Anyth...
arXiv:2609.02012v2 Announce Type: replace Abstract: Point-of-interest (POI) localization matches user-provided storefront close-ups to the same shops in wide, geo-tagged vehicle-mounted street views....
arXiv:2512.09201v2 Announce Type: replace-cross Abstract: We introduce a framework for converting 3D shapes into compact and editable assemblies of analytic primitives, directly addressing the persis...
arXiv:2607.06782v2 Announce Type: replace-cross Abstract: Under field-of-view (FOV) mismatch, pooling LiDAR features over unequal angular support can distort compact retrieval keys and exclude correc...
NAVIR is an end‑to‑end audio‑visual speech recognition system designed for the BrainChip Akida neuromorphic processor, which only supports sequential 2‑D convolutions. The architecture separates spatial and temporal encoding into three AkidaNet modules—per‑frame visual, temporal video, and spectrogram audio encoders—fused by a lightweight predictor and decoded with constrained beam search. Trained with CTC on noise‑augmented audio and fine‑tuned via quantization‑aware training, the quantized model achieves 14.0% WER on GRID’s unseen‑speaker split and 3.3% on overlapped‑speaker split, outperforming audio‑only baselines, and delivers 98.6% command accuracy at 1.5% WER on an industrial‑command corpus, while offering a 13‑fold energy advantage over conventional ANNs and roughly 5‑fold lower energy per inference than a Raspberry Pi CPU.
The paper investigates how stochastic reconfiguration (SR), the standard optimizer for neural quantum states (NQS), functions as a statistical filter in overparameterized regimes where parameters outnumber Monte Carlo samples. By interpreting SR as ridge regression on tangent features, the authors show that the diagonal shift balances useful update directions against variance from fitting finite-sample residuals, leading to a U-shaped validation risk curve. They introduce multi-shift SR (MS‑SR), which averages ridge solutions at data‑adaptive shifts, and demonstrate that it reduces validation risk and update variance compared to fixed‑shift SR in both small and large system experiments.
The study benchmarks Vision Transformers (ViTs) against convolutional neural networks (CNNs) for fine‑grained orchid genus identification in New Guinea’s species‑rich, data‑poor flora. Using a two‑stage system that first predicts genus and then retrieves similar species images, the authors fine‑tuned four pretrained backbones on 16,701 photographs from 120 genera and 1,350 species. The self‑supervised ViT DINOv2 achieved the highest genus accuracy (macro top‑1 66.9 %) and outperformed both CNNs and a domain‑matched pretrained ViT, demonstrating strong species retrieval and open‑set detection capabilities.
arXiv:2602. 09300v2 Announce Type: replace Abstract: We consider the policy evaluation and control in a finite horizon reinforcement learning (RL) setting under an expectile-based objective.