Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2609.13280v1 Announce Type: new Abstract: Prescription transcription errors are not interchangeable. A model that fabricates a drug and a model that misreads a legible dose pose very different...
arXiv:2609.14823v1 Announce Type: new Abstract: Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiol...
arXiv:2609.15313v1 Announce Type: cross Abstract: Autoregressive generation of interleaved text and acoustic tokens is a common approach to spoken-response generation in speech large language models....
arXiv:2609.13258v1 Announce Type: cross Abstract: We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyp...
arXiv:2605.12225v3 Announce Type: replace Abstract: While deep transformer-based models have advanced rapidly, their internal mechanisms remain largely a mystery. Recent work has prioritized understa...
The article surveys hallucination issues in Large Vision‑Language Models (LVLMs), a type of multimodal foundation model that blends visual data with large language models. It categorizes hallucination causes into model architecture and data quality, presents a taxonomy of mitigation strategies, and critically evaluates existing evaluation benchmarks from both discriminative and generative viewpoints. The survey also outlines open challenges and future research directions to improve LVLM reliability and trustworthiness.
The paper introduces TTIQ, a test‑time reinforcement learning framework that improves vision‑language model (VLM) adaptation by explicitly measuring image‑question dependence. By teacher‑forcing responses on the original and ablated image‑question pairs, TTIQ derives token‑level likelihood changes to estimate how much each input contributes, then uses these signals to construct a reward that favors jointly grounded, confident responses. Experiments on eight VQA datasets and various VLM sizes show that TTIQ consistently outperforms prior consensus‑based methods and generalizes across model families and unseen datasets.
arXiv:2609.07474v2 Announce Type: replace Abstract: Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should...
arXiv:2609.13815v1 Announce Type: new Abstract: Text-centric Visual Question Answering (VQA) requires reading and reasoning over text embedded in images, a task made substantially harder when images...
The paper investigates how multi‑modal world models can produce inconsistent outputs across different modalities, such as a video showing a ball not rebounding while a text description indicates it should. It defines two types of misalignment—internal (between modalities) and external (against a physical environment)—and introduces a physics‑grounded pipeline to measure these discrepancies. Experiments across multiple settings reveal that while the model’s language output matches the true environment, its video output frequently disagrees, indicating current unified backbones struggle with simultaneous reasoning, consistency, and physical fidelity.
arXiv:2609.14080v1 Announce Type: new Abstract: Promptable models such as microSAM segment electron microscopy (EM) images from point prompts, but automation requires generating prompts without user...
The paper presents a system for the MedReason 2026 challenge that tackles both multiple‑choice and open‑ended medical visual question answering using offline, containerized inference. Key findings include that comparing answer semantics rather than labels boosts retrieval‑only accuracy from 20.0 % to 57.5 % on a 200‑case holdout, and that varying the number of in‑prompt retrieved examples has minimal impact on final accuracy (93.5 %–94.0 %). The final system achieves 94.0 % MCQ accuracy on the development set and 93.20 % on the official pre‑evaluation, far surpassing the off‑the‑shelf baseline. "whyItMatters":"The results demonstrate that semantic‑aware retrieval and careful adapter tuning can dramatically improve medical VQA performance, offering a practical approach for high‑accuracy, offline inference in clinical settings."
The paper introduces an exploration-guided prompt scaffolding framework for multimodal large language models, dynamically adjusting the prompt distribution during reinforcement learning post-training. It uses an Exploration Potential Score (EPS) derived from KL-regularized policy improvement to assess prompt utility without extra overhead, and a teacher model rewrites low-utility prompts to preserve intent while improving informativeness. Experiments on Geo3K, MMK12, MathVision, and MMMU-Pro show consistent performance gains, up to 9.7% in-domain and over 11% on out-of-distribution benchmarks.
The paper evaluates five training‑free, plug‑and‑play keyframe selection methods for multimodal large language models (MLLMs) on long‑video understanding tasks. It compares these methods across three different MLLMs and three video question‑answering benchmarks, finding that QAaF performs best in 13 of 15 settings while FOCUS ranks second. The study offers a unified benchmark for assessing MLLM‑agnostic keyframe selection techniques.
The study investigates whether multimodal large language models (MLLMs) report bistable images, like the duck‑rabbit, in a manner similar to humans. Using the LLaVA family, researchers examined two dimensions: modulability (the influence of visual cues and linguistic priors) and exclusivity (whether responses commit to a single interpretation). Results show that both visual and linguistic manipulations shift reports in human‑consistent ways while maintaining predominantly exclusive responses, driven by competing image‑token representations and distinct bottom‑up and top‑down pathways.
The paper introduces a multimodal foundation model for lunar remote sensing, trained from scratch on SomBench—a dataset of nearly two million co‑registered tile bundles across 11 modalities at 1 m and 100 m resolutions. The model extends the TerraMind masked‑token architecture with lunar‑specific features such as explicit acquisition geometry and joint training of two spatial scales, and employs FlexiViT patch embeddings for adaptable patch sizes. Evaluation on crater detection, irregular mare patch segmentation, and polar ice prospectivity regression shows that the pretrained model matches or surpasses ImageNet‑pretrained baselines, with notable label efficiency and effective adaptation via LoRA.
The paper introduces AdaConRed, a label‑free post‑conformal decision rule that transforms ambiguous conformal prediction sets into single class assignments for medical image classification. It employs a five‑stage pipeline—vision‑language generative augmentation, a frozen DermFoundation encoder, a lightweight MLP classifier, an entropy‑modulated margin‑aware nonconformity score, and a reassignment step for transitional samples—to improve accuracy on OSCC and ISIC benchmarks. Results show notable gains in malignant class accuracy while maintaining overall performance.
The paper introduces a ROS-Agent architecture that enhances task reliability and execution efficiency for open‑source LLM‑powered robotic agents. It adds a MetaTool that forces the LLM to produce a structured pseudo‑code plan before any action, storing this plan in a scratchpad to separate planning from execution. Experiments on a custom mobile robot show up to ~24% improvement in complex task completion and contextual consistency compared to the baseline.
The paper details a multi‑month engineering effort to build Sophea, a production Greek‑English automatic speech recognition system. It evaluates the system against nine production gates—including word error rate, language identification, and hallucinations—across twenty‑three training iterations and two model architectures, finding that no single training‑data composition satisfies all gates. The authors describe a six‑stage data pipeline that dramatically reduces discarded Greek audio, isolate a hallucination defect to a specific training package, and demonstrate that a three‑model ROVER ensemble achieves full gate coverage and a 29 % relative WER improvement. A separate learned arbiter model is released on the Open ASR Leaderboard with 4.26 % average WER on English tests and 25.88 % on live Greek noisy traffic.
arXiv:2609.13845v1 Announce Type: cross Abstract: World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet pl...