Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2608.29092v1 Announce Type: new Abstract: Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is pri...
arXiv:2608.30521v1 Announce Type: new Abstract: Conventional algebraic triangulation solves 3D human pose estimation (HPE) from multi-view 2D keypoints. The typical approach, decoding 2D keypoints fr...
arXiv:2608.28762v1 Announce Type: new Abstract: Recent advances in visual question answering (VQA) and multimodal large language models (MLLMs) have enabled natural-language reasoning over traffic sc...
arXiv:2608.28699v1 Announce Type: new Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine...
arXiv:2608.30428v1 Announce Type: cross Abstract: Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern. Social-deduction games (where each player holds a...
arXiv:2608.29937v1 Announce Type: new Abstract: Latent world-action models avoid rendering future pixels by predicting an action-relevant visual subgoal in feature space. LaWAM established this formu...
CogEvol is a family of models designed to generate learning environments—structured JSON slides or interactive HTML pages—from course briefs in a single pass. In production, it completes a slide in a median of 17 seconds and an interactive page in 59 seconds, vastly faster than multi‑turn agent scaffolding. The system enforces reliability through a production‑grounded data pipeline that produces over 53,000 verified SFT samples and a hybrid rule‑plus‑VLM reward that guides GRPO‑based reinforcement learning, with a 27B model achieving high quality scores while using far fewer parameters than flagship coding models.
arXiv:2608.30475v1 Announce Type: cross Abstract: We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, cove...
arXiv:2608.28698v1 Announce Type: new Abstract: Compared with typical vision-language tasks, document parsing places stronger demands on fine-grained visual perception. Existing vision-language model...
RoboPhys-3D is a 3D‑grounded embodied world model benchmark built on RoboTwin 2.0, featuring 50 manipulation tasks, 5,000 episodes, and 25,000 multi‑view ground‑truth videos. It evaluates video world models by processing both generated and ground‑truth videos through the same 3D reconstruction pipeline, allowing the separation of reconstruction‑induced from generation‑induced errors. The benchmark defines 50 metrics across four sub‑dimensions—pixel fidelity, 3D geometry consistency, state understanding, and task completeness—and introduces the Average Full Score and RoboPhyscore for holistic assessment, with RoboPhyscore showing strong correlation with human judgments.
The study demonstrates that a simple, sequence-only approach using 330 interpretable descriptors and the TabPFN tabular foundation model can outperform complex multimodal deep learning methods for multi-label antimicrobial peptide activity prediction. On the ESCAPE benchmark (82,359 peptides, five labels), a label‑powerset TabPFN model achieved a mean average precision of 77.8%, surpassing the previous best of 72.1%. The approach also shows that predicted structure is unnecessary, that a small set of global physicochemical scalars can recover most performance, and that modeling label dependence benefits rare activities and informs assay prioritization.
The paper introduces a new framework for predicting grapevine cold hardiness that learns transferable latent representations capturing region-specific variation. By inferring embeddings from cultivar descriptions, growing region text, and limited historical data, the method supports zero‑shot and few‑shot transfer to unseen regions. Experiments across six North American regions show that this approach outperforms existing models, delivering more accurate predictions and better performance in data‑scarce areas.
The paper surveys Multimodal Code Intelligence, focusing on tasks where code is generated, edited, refined, or reasoned about under visually grounded inputs such as screenshots, charts, and videos. It categorizes the field by the role of code—rendered artifact, editable structure, intermediate reasoning trace, or executable tool interface—and organizes benchmarks into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. The authors argue that reliable evaluation must include evidence of semantics and interaction beyond visual fidelity, and propose four verification-centered research directions to advance the field toward evidence-grounded executable systems.
FRAMEWORKERS is a task‑centric, multi‑agent framework designed for end‑to‑end AI‑generated video production. It uses a central Director to dynamically manage a task stack and an Assistant to execute tasks within a shared Workspace, leveraging modular sub‑agents that can be added without redesigning the workflow. The system is fine‑tuned with supervised learning and policy optimization, outperforming existing LLM planners and fixed pipelines in routing accuracy, failure recovery, and overall video quality.
arXiv:2608.30935v1 Announce Type: cross Abstract: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embod...
arXiv:2605.30117v2 Announce Type: replace Abstract: Understanding how Vision-Language-Action (VLA) models transform multimodal knowledge into embodied control remains an open challenge. We present VL...
arXiv:2510.22588v2 Announce Type: replace-cross Abstract: Spoken dialogue models currently lack the ability for fine-grained speech style control, a critical capability for human-like interaction tha...
arXiv:2608.07742v2 Announce Type: replace Abstract: Visual-language models (VLMs) frequently struggle with robustness issues in real-world situations due to low- or varying-quality input images. In t...
arXiv:2606.00232v2 Announce Type: replace Abstract: We study fact-level repair for multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existin...
arXiv:2505.03654v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models have shown strong performance across multimodal tasks, and recent personalized MLLMs can recognize user-spec...