Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2609.24075v1 Announce Type: new Abstract: Computer-vision systems used for construction monitoring can degrade under adverse environmental and visual conditions, yet such conditions remain unde...
arXiv:2609.24172v1 Announce Type: new Abstract: Legends are fundamental to chart understanding, as reliable interpretation requires correctly binding legend entries to corresponding visual marks. Whi...
arXiv:2609.24210v1 Announce Type: new Abstract: Building strong chart-to-code systems increasingly relies on reinforcement learning, whose effectiveness depends critically on the quality of the rewar...
arXiv:2609.24220v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presen...
arXiv:2609.24276v1 Announce Type: new Abstract: Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstr...
arXiv:2609.24531v1 Announce Type: new Abstract: Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temper...
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:2609.22854v1 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:2511.18028v2 Announce Type: replace Abstract: Image super-resolution (SR) is a critical technology for overcoming the inherent hardware limitations of sensors. However, existing approaches main...
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:2605.29655v4 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:2411.00527v5 Announce Type: replace-cross Abstract: Utilizing the complementary strengths of wavelength-specific range or depth sensors is crucial for robust computer-assisted tasks such as aut...
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 whether the layer that yields the highest probing accuracy in omni‑modal large language models is also the most effective for steering interventions. Across three independently developed models, the authors find that the best probing layers differ widely, whereas the most steerable layers consistently lie in a narrow mid‑to‑late range of the network. Using emotion as a testbed, they demonstrate a significant causal gap between probing and steering, and propose a two‑factor account linking readability and downstream plasticity to steering effectiveness.
ShearFuse-UNet is a lightweight deep learning model designed for next‑day wildfire spread prediction using multi‑modal satellite data. It incorporates three transform‑domain branches—Fast Walsh‑Hadamard Transform, Discrete Cosine Transform, and a cone‑adapted digital Shearlet residual—within each encoder block of a U‑Net backbone, fusing spectral representations via a learned SpectralFusion gate and adding Shearlet reconstruction as a residual. On the WildfireSpreadTS dataset, the model achieves an F1 score of 0.596 with only 267k parameters, outperforming a larger ResNet18‑based U‑Net and demonstrating a favorable accuracy‑efficiency trade‑off, with additional validation on the Google Next‑Day Wildfire Spread dataset.
arXiv:2609. 22752v1 Announce Type: new Abstract: Diffusion models have demonstrated strong power in generative modeling tasks across multiple domains, exhibiting a remarkable capability of learning complex distributions from samples.
Prioritized Rollouts for Efficient World Model-based Vision-Language-Action Policy Optimization introduces U‑GROW, a lightweight sampling layer that directs more model rollouts toward states with high policy uncertainty, identified as decision‑sensitive stages where small action differences can alter task outcomes. By modifying only the branched‑start distribution, U‑GROW can be integrated into existing model‑based reinforcement learning pipelines without changing the policy optimization objective. Experiments on simulated and real‑world manipulation tasks demonstrate that U‑GROW improves the efficiency and effectiveness of policy optimization for Vision‑Language‑Action models.
arXiv:2609.24057v1 Announce Type: cross Abstract: Medical image interpretation is central to diagnosis and care, yet adapting general-purpose multimodal large language models (MLLMs) often requires r...
arXiv:2609.24198v1 Announce Type: cross Abstract: This paper describes the SKstars submission to SHROOM-Visions 2026, a shared task on fine-grained hallucination detection in large vision-language mo...
The paper introduces DPTM‑DT, a dual‑pretrained Transformer framework that integrates GROVER molecular graph embeddings, ESM protein language‑model embeddings, and CTD physicochemical descriptors for drug‑target prediction. It employs bidirectional cross‑modal attention to share drug‑target information and uses a single pair representation for continuous affinity regression, high‑affinity binary classification, and six‑level affinity classification. Experiments on Davis and KIBA datasets show that DPTM‑DT outperforms existing methods across regression, binary, and multiclass tasks, with ablation studies confirming the contributions of dual target representation, gated fusion, and cross‑modal attention.