Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2608.22143v1 Announce Type: new Abstract: Qualitative mechanical problem-solving (QMPS) refers to solving qualitative problems from the mechanical domain. Qualitative problems can be solved wit...
arXiv:2608.21868v1 Announce Type: new Abstract: Depression assessment from multimodal clinical interviews requires integrating dispersed evidence from multiple symptoms into a coherent PHQ-8 profile....
arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visua...
arXiv:2608.05154v3 Announce Type: replace Abstract: Multimodal rotary positional encodings apply temporal, height, and width phases to interleaved text, image, and video tokens. This creates two ambi...
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 PM4Bench, a multimodal, multilingual, multi-task benchmark built on a strictly parallel 10‑language corpus, allowing fair cross‑lingual comparison of Large Vision‑Language Models (LVLMs). It also proposes a vision setting that embeds textual inputs directly into images to better mimic real deployment scenarios. Experiments show OCR performance drives cross‑lingual gaps, leading to an OCR‑centric GRPO training strategy that improves multilingual VQA and reduces disparities without costly supervision.
arXiv:2608.22174v1 Announce Type: new Abstract: Unified multimodal models (UMMs) can perform both understanding and generation, raising a central question: can visual generation improve understanding...
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.
The Cultural Moment Benchmark (CMB) evaluates video cultural reasoning in Southeast Asia by testing three distinct abilities: naming a cultural concept, visually recognizing it in a video, and locating its sub‑events in time. It contains 306 expert‑curated concepts from seven countries across five categories, with each concept assessed through three stages that use semantic‑similarity distractors, unlabeled video moments, and free‑form temporal localization. Experiments on six vision‑language models reveal varied failure modes, limited cascading between abilities, and differing impacts of audio and subtitles, while a human study shows even experts struggle with concepts from neighboring countries.
The paper introduces a framework that separates physical modeling from execution in physics reasoning tasks. It uses a two‑stage post‑training approach: supervised fine‑tuning to build structured models and reinforcement learning with rubric‑based feedback to refine them. Experiments on PhysReason, PhyX, and SeePhys show that this explicit modeling improves reasoning performance by about 3% on average for small LLMs.
The paper introduces TA-SPA, a black‑box jailbreak method for multimodal large language models that generates transferable perturbations in a text‑anchored semantic space. It combines Text‑Anchored Semantic Factorization (TASF) to separate cross‑modal semantic factors from modality‑specific residuals with Semantic‑Preserving Augmentation (SPA) to diversify harmful target anchors while maintaining semantic consistency. Experiments demonstrate strong attack effectiveness and transferability to commercial MLLMs, with competitive performance against representative defenses.
arXiv:2608.22071v1 Announce Type: cross Abstract: Turn-taking is a basic organizational feature of human conversation and remains difficult to model in natural, synchronous dialog systems. While exis...
arXiv:2608.21853v1 Announce Type: new Abstract: Large language models are increasingly moving beyond text processing, adding support for other modalities such as images and audio. While text understa...
The paper proposes a single diffusion model trained across multiple imaging domains to act as a reusable prior for computed tomography (CT) reconstruction. By keeping the model frozen, it is applied to three distinct datasets—flaw analysis in additively manufactured metal parts using cone‑beam X‑ray CT, and concrete microstructure imaging with parallel‑beam neutron CT—each differing in modality, geometry, material, and degradation. In all cases, the method outperforms analytic reconstructions, demonstrating its potential as a foundation plug‑and‑play prior for heterogeneous CT problems.
arXiv:2608.23268v1 Announce Type: new Abstract: Frontier multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning. Parameter-le...
arXiv:2608.22337v1 Announce Type: cross Abstract: Speech-guided referring video object segmentation aims to recover the mask tracks of objects specified by a spoken motion description. Here, speech c...
The paper introduces CloudEdgeVLA, a cloud‑edge policy for Vision‑Language‑Action models that treats temporal misalignment as a representation‑learning problem. It encodes delayed observations into slowly varying task features on the cloud while a lightweight edge head fuses the latest cloud feature with current local vision. Experiments on four LIBERO suites show that CloudEdgeVLA retains 63.8–78.0% success under a 40‑step delay window, far outperforming VLASH and single‑path baselines.
arXiv:2608.22232v1 Announce Type: new Abstract: Real-world situation appearances can deviate from their underlying physical states, challenging the reliability of multimodal large language models (ML...
arXiv:2608.21577v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fairness is a critical safety requirement. In practic...
arXiv:2608.22869v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-focused finetuning to achieve strong performance on long...