The paper evaluates bias in phoneme-based automatic speech recognition (ASR) systems, focusing on WhisperIPA and ZIPA, which produce International Phonetic Alphabet (IPA) transcriptions. Using multilingual speech corpora and demographically annotated English datasets, the authors compare model-generated IPA against grapheme-to-phoneme (G2P) outputs with both standard phoneme error rate (PER) and a new Soft PER metric that allows linguistically similar substitutions. The study finds persistent disparities across language, gender, accent, ethnicity, and age, even when accounting for acceptable phonemic variation.
By Maneesha Rani Saha, Catherine Bao, Neal Patwari
The paper introduces a new benchmark for evaluating Multi‑Modal Large Language Models (MLLMs) on visual negation understanding, focusing on safety-critical scenarios. It defines the Scene Negation Understanding under Safety Cognition (SNUS) task and presents a high‑fidelity negative caption dataset that maps dense assertions of localized hazards. The authors also propose the Cognitive Expected Scene Graph (CESG) Score, a polarity‑aware, structure‑grounded metric that remains robust under semantic reversals, revealing that existing models and traditional metrics fail on this task.
By Zhiyun Jiang, Hanyong Wang, Binbin Liang, Yu Xie, Menglong Yang, Wei Li
MTVA-Bench is a new benchmark designed to evaluate the language model component of cascaded voice agents under realistic conditions. It simulates callers with an LLM, mocks backend tool responses, and scores both tool‑call correctness and conversational quality using two LLM judges, covering 49 agents, 490 scenarios, and 7 languages. The benchmark reveals that while models perform similarly on tool selection, they differ widely in argument handling, rule compliance, and dialogue quality, highlighting the nuanced challenges of real‑world voice interactions.
By Pritish Mishra, Ishaan Kumar, Akshat Mandoli, Sudarshan Kamath
The paper introduces ReaLMem, a benchmark built from authentic multi‑year personal visual archives with first‑person annotations, designed to evaluate AI systems on factual recall, persona inference, and predictive personalization. It also proposes ChronoProfiler, a temporal‑weighting module that calculates stability scores for user attributes to resolve preference conflicts and enhance personalized decision making. Experiments with multimodal large language models and memory systems show that predictive personalization remains the hardest task, highlight performance gaps, and demonstrate that temporally informed representations significantly improve personalization.
By Wenqi Zhou, Zhuorui Yu, Kaiao Wen, Hao Zheng, Xinyi Zheng, Peiran Wu, Enmin Zhou, Chi-Hao Wu, Junxiao Shen
Agile-WAM is a tactile World Action Model that jointly predicts future visual and tactile states and robot actions for contact‑rich manipulation. It encodes visual and tactile observations into a shared latent space and uses a vision‑tactile‑to‑action flow‑matching process to generate action chunks and future latents. The model introduces multi‑horizon multimodal prediction, leveraging the different timescales of vision and touch, and achieves a 29.4 % improvement in real‑world success rates with 11.9 ms inference latency across nine simulated and five real‑world tasks.
By Hanchu Zhou, Brendan Lynch, Raman Goyal, Dechen Gao, Begum Kasap, Boqi Zhao, Junshan Zhang
The paper introduces ProKDA, a progressive knowledge-to-decision alignment framework for explainable hateful meme detection. ProKDA separates explanation generation and label prediction into three sequential training stages—background knowledge learning, hatefulness detection learning, and hatefulness boundary alignment—reducing task interference. Experiments on three public benchmarks demonstrate that ProKDA achieves state‑of‑the‑art detection performance while providing accurate, evidence‑supported explanations for moderation decisions.
By Bo Xu, Chenyuan Wang, Xinyu Chen, Quanhao Zhu, Rui Lin, Liang Zhao, Hongfei Lin, Feng Xia
The paper introduces a phoneme-guided text-to-speech (TTS) augmentation pipeline for automatic speech recognition (ASR) that links multilingual speech generation with candidate-text selection and reference-speech quality control. It proposes phoneme-frequency-guided selection (PFGS), which prioritizes candidate texts containing common phonetic content based on real ASR training transcripts. Experiments across four languages and 13 test sets show that random text selection improves recognition on 11 test sets, while PFGS further improves nine test sets with relative word error rate reductions up to 19.3%, and reference-speech filtering also contributes to performance gains.
By Zhen Wang, TianRui Wu, RongQi Han, Hao Wu, Wei Liang, Wei Xu
SCOUT is a frozen‑encoder approach for sim‑to‑real text‑based person retrieval that predicts cross‑modal embeddings instead of fine‑tuning cross‑encoders. It uses a trainable predictor to map patch tokens from a frozen video encoder (V‑JEPA) into the embedding space of a frozen text encoder (EmbeddingGemma), guided by a bidirectional InfoNCE objective. The method achieves state‑of‑the‑art results on the AI City Challenge 2026 Track 4, with a full retrieve‑fuse‑rerank pipeline reaching 84.25 mAP@10 and a single frozen model alone scoring 60.63, while training costs are modest (≈95 GPU‑hours).
By Abdarahmane Traor\'e, Andy Couturier, \'Eric Hervet
CoMa introduces a contextual massing generation framework that leverages vision‑language models to produce building massings that fit a target parcel and align with surrounding urban morphology. The study uses a dataset of 12,845 Melbourne massings, incorporating parcel contours, 3D geometry, neighboring buildings, and multi‑view images, and proposes a learned relevance metric to assess morphological compatibility. Experiments with Qwen3‑VL models show that larger model size improves generation quality, multimodal training enhances the use of individual modalities, and multimodal inference yields a stronger contextual signal than isolated inputs.
By Evgenii Maslov, Alexandra Vabnits, Vladimir Vorona, Anastasia Antsiferova, Valentin Khrulkov, Anastasia Volkova, Anton Gusarov, Andrey Kuznetsov, Ivan Oseledets
The paper introduces a compression framework for the Whisper automatic speech recognition model that jointly optimizes six deployment dimensions—model size, temporal resolution, encoder token stride, low‑rank adaptation capacity, weight precision, and sparsity pattern—using NSGA‑III. The optimization targets three objectives: word error rate, inference FLOPs, and memory footprint. Evaluating 1,680 configurations, the study identifies compression combinations that outperform single‑axis scaling and notes that 1:4 structured sparsity cannot maintain acceptable accuracy within the tested budgets.
By Vyom Agarwal, Mokshda Gangrade, Siddharth Pal, Jerry Wu
VákQA is a new Telugu spoken factoid question answering benchmark comprising 2,001 question‑answer pairs across six domains, 2.53 hours of speech audio, bilingual transcriptions, and human‑verified reference answers. The study validates automatic evaluation methods against human judgments, finding that Gemini-as-a-judge best approximates human ratings but is unevenly strict, while open‑weight judges tend to penalize correct Telugu answers that differ in surface form. Using this validated setup, the authors benchmark proprietary and open‑weight models, highlighting challenges such as cultural specificity lost in translation, phonetic confusions from speech input, and cascading ASR‑MT errors.
By Bhavana Akkiraju, Ravi Sastry Kolluru, Sri Charan D, Srihari Bandarupalli, Santosh Kesiraju, Anil Vuppala
The paper introduces Data Journalist Agent (Data2Story), a multi‑agent framework that orchestrates specialized roles into a single virtual newsroom to produce evidence‑grounded, multimodal news stories. It ensures every claim is traceable to data, code, or external references via an Inspector, and generates interactive visualizations such as maps and audio to match reader interests. Evaluations on 18 articles show competitive performance in angle coverage, rubric scores, and verifiability, while human writers still lead in editorial angle and creative design.
By Kevin Qinghong Lin, Batu EI, Yuhong Shi, Pan Lu, Juil Sock, Djordje Padejski, Philip Torr, James Zou
The paper introduces a unified evaluation framework for assessing the trustworthiness of large language models, agentic AI, and multimodal systems. It connects output-level, trajectory-level, and cross-modal assessments across eight dimensions—capability, robustness, safety, fairness, transparency, governance, oversight, and efficiency—while preserving system-specific metrics and providing uncertainty estimates. A meta-evaluation layer checks the validity, reliability, and reproducibility of the evaluation itself, and the framework aligns with governance standards and regulatory requirements.
By Shaina Raza, Ahmed Y. Radwan, Imran Liaquat, Kathryn Hume
The paper introduces SOLAR, a multimodal generative model that jointly interprets visual and textual data to understand tomato leaf diseases across six question‑answering tasks. SOLAR aligns visual features with task‑aware language representations using a Fusion Expert module based on a mixture‑of‑experts, enabling it to generate contextually relevant answers for diverse diagnostic tasks. Evaluated on 41,677 images and 216,209 QA pairs, SOLAR outperforms state‑of‑the‑art vision‑only, vision‑language, and task‑specific models in both closed and open‑ended settings, demonstrating superior accuracy, robustness, and multimodal reasoning.
By Khang Nguyen Quoc, Minh-Phuoc Tran, Gia-Han Truong, Luyl-Da Quach
The paper introduces a discriminative adaptation for SpeechLLMs that reads the hidden state of the final prompt token via a simple classification head, enabling emotion recognition in a single forward pass without altering the backbone. This approach replaces the generative decoder, which can produce out‑of‑set labels and favor frequent classes, with a controlled comparison between generative and discriminative inference. Experiments on IEMOCAP show improved Macro F1 scores, elimination of hallucinations, and larger gains on realistic ASR transcripts, while revealing that emotion directions encode indirect associations reflecting web‑scale text biases.
By Hasindri Watawana, Sergio Burdisso, Esa\'u Villatoro-Tello, Manjunath K E, Kadri Hacioglu, Petr Motlicek, Andreas Stolcke
The paper introduces AttnPrint, a white‑box fingerprinting method that extracts low‑frequency components of cross‑modal attention distributions to identify multimodal large language models (MLLMs). It also presents DistillTrace, a black‑box auditing tool that uses hypothesis testing of MLLM outputs to detect potential model infringement. Experiments on 154 model instances across 19 architectures show that AttnPrint effectively detects derivative models and remains robust to downstream modifications, while DistillTrace reveals distillation relationships under various techniques.
By Chao Huang, Meng Tong, Kejiang Chen
FOCAL is a framework that aligns fine-grained ECG waveform segments with specific report tags using Optimal Transport, addressing the lack of localized representation in prior methods. It introduces a semantic similarity matrix to mitigate false negatives when reports share diagnoses, and a coarse‑to‑fine enrichment pipeline that employs Large Language Models to recover missing waveform semantics while filtering hallucinations. Experiments on six datasets show FOCAL achieves state‑of‑the‑art zero‑shot prediction and linear probing performance.
By Haitao Li, Che Liu, Zhengyao Ding, Ziyi Liu, Wenqi Shao, Zhengxing Huang
SAGG: Sample-Adaptive Gradient Gating for Robust Multimodal Learning under Heterogeneous Corruption proposes a new method for handling sample-heterogeneous corruption in multimodal training. The authors prove that batch-level, sample-agnostic linear estimators with a shared modulation parameter inevitably incur bias, and that a sample-level all-or-nothing gating strategy is the only unbiased approach within a natural estimator class. SAGG implements a binary retain-or-discard decision per sample using an online feature-norm quality test and a truncation mechanism for variance control, and demonstrates convergence to clean-loss stationary points while achieving superior performance over ten existing methods on Kinetics-Sounds and UCF-101 under various corruption scenarios.
By Wentao Zhang, Yifan Zhu, Yutong Zhang, Wentao Mo
The paper adapts the compact PP‑OCRv6 recognizer for historical text recognition and compares it to a conventional CRNN across various training regimes, including generalized pretraining, domain‑specific training, corpus‑level fine‑tuning, and manuscript‑specific few‑shot adaptation on multilingual Latin and Arabic scripts. While PP‑OCRv6 does not always beat the CRNN when trained from scratch, heterogeneous pretraining significantly improves its generalization. Additionally, fine‑tuned PP‑OCRv6 can surpass a large vision‑language model (Qwen3.5‑based Medusa) that is specifically tailored for historical Latin‑script handwriting recognition.
By Benjamin Kiessling (ALMAnaCH)
MTF‑Net is a Multi‑Modal Temporal Feature Fusion Network that jointly models kinematic, appearance, and contextual cues for pedestrian intention prediction. It fuses four modalities—bounding‑box dynamics, human pose keypoints, local context, and scene‑level semantics—within a recurrent framework enhanced by gated linear units (GLUs) and an attention‑guided fusion head. Evaluations on the PIE and JAAD benchmarks show that MTF‑Net outperforms recent transformer‑ and graph‑based models, achieving up to 0.95 AUC on PIE and 0.94 AUC on JAAD while maintaining real‑time performance.
By Md Mahfuzur Rahman, Pengzhan Zhou, A. F. M. Abdun Noor, Md Imam Ahasan, Md Mustafizur Rahman, Fang Qu