Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2609.36082v1 Announce Type: new Abstract: We introduce GeoOutageBench, a benchmark for assessing LLM-based geospatiotemporal KGQA for multimodal outage and resilience analysis. Unlike existing...
arXiv:2609.36503v1 Announce Type: new Abstract: Adding or removing a sounding object requires coordinated changes to visual content and sound while preserving the surrounding scene. Yet paired superv...
arXiv:2609.36828v1 Announce Type: new Abstract: Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences wi...
arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that ag...
arXiv:2609.36838v1 Announce Type: cross Abstract: Visual agents solve problems by interleaving reasoning with image operations, and on-policy distillation (OPD) provides guidance from a strong teache...
arXiv:2609.37011v1 Announce Type: cross Abstract: Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into...
arXiv:2609.37196v1 Announce Type: cross Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allow...
arXiv:2609.37264v1 Announce Type: cross Abstract: Affordance perception aims to localize actionable regions supporting embodied interaction, yet 2D and 3D affordance grounding have evolved as separat...
arXiv:2609.37810v1 Announce Type: cross Abstract: Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains chal...
arXiv:2609.37195v1 Announce Type: new Abstract: Handwritten Text Recognition (HTR) systems have become an indispensable tool for the digitization of historical documents. Not only do they cut down ti...
arXiv:2604.15086v3 Announce Type: replace-cross Abstract: Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-gra...
arXiv:2609.36593v1 Announce Type: cross Abstract: Creating diverse physical simulations remains labor-intensive because assets, layout, physical parameters, motion, control, and rendering must be des...
arXiv:2609.35800v1 Announce Type: new Abstract: Low-bit key-value (KV) cache quantization saves storage but can sharply degrade vision-language model (VLM) accuracy. We introduce HeadGuard, a composa...
arXiv:2609.36215v1 Announce Type: new Abstract: Power-grid digital twins must combine data-driven prediction with physically meaningful state evolution while preserving the provenance of environmenta...
arXiv:2609.37148v1 Announce Type: new Abstract: Many of the qualities that matter most in how people learn and grow, how someone regulates their emotions, reflects on a setback, or stays aware of oth...
arXiv:2609.37384v1 Announce Type: new Abstract: Molecular representation learning is central to computer-aided drug discovery. Molecular graphs, SMILES strings, and 3D conformations provide complemen...
arXiv:2609.37515v1 Announce Type: cross Abstract: Thorough evaluation of vision-language models (VLMs) has become prohibitively expensive, as benchmarks span an ever-broader spectrum of capabilities...
arXiv:2609.35898v1 Announce Type: cross Abstract: This paper proposes Wasserstein Causal Forests (WCF) for settings in which each unit's outcome is itself a probability distribution. This study also...
arXiv:2609.35922v1 Announce Type: cross Abstract: A voice agent can handle almost every call on the words alone and still fail the few its sector's rules were written for. Emergency-call standards, f...
PreviewDiff is a test‑time search method that uses multimodal critics to guide diffusion model sampling. By decoding partial previews at selected denoising checkpoints, scoring them with a multimodal judge, and branching over semantic prompt edits, it allows the generation process to be edited and rerouted before completion. The approach consistently outperforms budget‑matched Best‑of‑N sampling and scalar‑search baselines on image and video benchmarks, with early interventions and wider search yielding the biggest gains.