Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2608.22449v1 Announce Type: cross Abstract: Forecasting dexterous hand motions from egocentric observations is fundamental to intelligent interactive systems. Existing VLM-based methods typical...
The paper introduces LoG, a localization‑infused vision‑language fusion framework for text‑guided medical image segmentation. LoG jointly performs multi‑scale target localization to explicitly capture target‑oriented semantics and employs three levels of localization‑infused fusion—feature, attention, and loss—to integrate spatial information into segmentation. Experiments on three benchmark datasets across three imaging modalities show that LoG consistently outperforms state‑of‑the‑art methods.
arXiv:2608.23302v1 Announce Type: new Abstract: Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural mul...
arXiv:2608.21497v1 Announce Type: cross Abstract: Biochemical recurrence (BCR), defined as any detectable prostate-specific antigen level after prostatectomy with confirmatory elevation, is widely us...
arXiv:2608.23531v1 Announce Type: new Abstract: Older adults recovering after lower-limb fracture or hip replacement may experience complex recovery trajectories. Most of the time, these clinical asp...
DRAgent introduces a discriminative reasoning framework for Referring Expression Segmentation that replaces direct coordinate prediction with a two‑stage selection process. First, a detector generates candidate boxes; then a multimodal large language model (MLLM) discriminates the correct target through high‑recall screening and instance‑wise verification. The chosen box serves as a spatial prompt for a foundation segmentation model, and a self‑consistency‑filtered data pipeline is used for LoRA‑based fine‑tuning, yielding competitive results on RefCOCO, RefCOCO+, and RefCOCOg.
arXiv:2608.21595v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning ability of vision-language models (VLMs), and diversifying the rollouts wi...
The paper introduces VERDICT, a method for validating optical chemical structure recognition (OCSR) outputs by leveraging agreement among multiple recognizers rather than pixel‑space re‑rendering. On 263 ACS journal images, agreement achieved an AUROC of 0.916, far surpassing the 0.547 AUROC of re‑rendering similarity. VERDICT was applied to PMC Open Access, yielding over 6,000 high‑precision structure labels, and is integrated into SES AI’s Molecular Universe platform for image‑based molecular search.
arXiv:2604.08884v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on RGB image understanding, yet their ability to use spectral evide...
arXiv:2608.21487v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) exhibit strong zero-shot capabilities, making them an attractive solution for continual learning across diverse tasks....
arXiv:2608.21440v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have advanced end-to-end autonomous driving by leveraging foundation models for semantic reasoning and long-tail...
arXiv:2509.23928v3 Announce Type: replace-cross Abstract: Speculative decoding has proven effective for accelerating inference in Large Language Models (LLMs), yet its extension to Vision-Language Mo...
The paper introduces RACO, a reliability‑aware adaptive coarse‑to‑fine navigation framework for inspection‑oriented UAV vision‑language navigation. It treats the coarse goal as a runtime hypothesis, using object‑level anchors to correct localization before and at the transition to the fine stage, and applies scale‑adaptive terminal refinement for near‑miss cases. RACO is evaluated on the new LG‑UVI inspection setting and outperforms the HETT baseline by 9.53 and 7.98 percentage points on validation‑unseen and test‑unseen, respectively, while improving inspection‑region arrival and reducing false verification risk.
arXiv:2608.22785v1 Announce Type: new Abstract: Spatial multi-omics technologies jointly profile gene expression, surface proteins, and histology at each tissue spot, yet most spatial domain discover...
arXiv:2605.17610v2 Announce Type: replace-cross Abstract: The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-wo...
The paper introduces a training‑free method for personalizing vision‑language models by using calibrated residual decoding. It constructs three evidence conditions—positive, counterfactual, and empty profiles—to isolate the true contribution of personalization. Normalized‑entropy calibration adjusts the influence of this residual signal based on its uncertainty, improving identity‑sensitive visual personalization without fine‑tuning.
The paper presents a scalable approach to harmful content moderation on social media by leveraging large language models (LLMs) for few-shot, in-context learning. Experiments across multiple LLMs show that this method outperforms proprietary baselines such as Perspective and OpenAI Moderation, as well as prior few-shot learning techniques, in detecting harmful content. The study also explores the addition of visual cues like video thumbnails to assess multimodal improvements, highlighting the advantages of LLM-based moderation for dynamic and large-scale content filtering.
MetaCaster is a meta-harness-optimized multi-agent framework that enables few-shot learning for lightweight time series forecasters. It uses agentic data generation to automatically train specialized forecasters from only a few examples and textual contexts, positioning agents as intermediary engineers rather than direct forecasters. Experiments on 18 datasets and 23 lightweight forecasters show that MetaCaster achieves data and computational efficiency while maintaining high forecasting quality.
arXiv:2608.21832v1 Announce Type: new Abstract: Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing benchmarks do not isolate whether mo...
The paper introduces MemeMind, a large-scale dataset for detecting harmful memes that includes a detailed taxonomy and Chain-of-Thought reasoning annotations. It also proposes MemeGuard, a multimodal framework that uses a three-stage training strategy to improve visual understanding, reasoning, and discrimination of harmful content. Experiments show MemeGuard surpasses current state-of-the-art methods on MemeMind, advancing detection accuracy and interpretability.