The paper presents SEAR, a system for Task 2 of the second Multilingual Conversational Speech Language Model Challenge. It adapts Qwen3-Omni-30B-A3B-Instruct with a segment‑evidence‑aware pipeline that converts timestamped ASR into event spans, expands and crops them, and then generates both semantic and acoustic multiple‑choice questions using Qwen3.6-27B and Gemini 3.1 Flash‑Lite. After rigorous checks, 359,825 verified MCQs across 21 languages and accents are produced, and the system achieves 90.92% accuracy on the official evaluation set.
By Huy Hoang Le, Long-Bao Nguyen, Minh Tri Dao
The paper introduces a framework to evaluate and diagnose the robustness of low‑resource multilingual text‑to‑speech systems when faced with complex text inputs such as numbers, dates, named entities, long sentences, code‑switched expressions, and punctuation structures. It assesses robustness across content consistency, language consistency, and generation stability, and proposes automatic metrics (character error rate, language ID accuracy, duration abnormal rate) along with a lightweight Text Risk Score (TRS) that predicts synthesis risk from interpretable text features. Experiments on Thai, Vietnamese, Swahili, and Indonesian TTS systems reveal distinct failure patterns and show that TRS correlates positively with content and duration errors, offering a low‑cost pre‑synthesis risk indicator.
By Tianlun Zuo, Ziyu Zhang, Tingzhi Mao, Zhonghua Fu, Lei Xie
The Eloquence team presents three methods for the Interspeech 2026 MLC‑SLM Task 2, a multilingual MCQA challenge covering 21 languages. They fine‑tune Voxtral‑Mini‑3B with LoRA and data augmentation, achieving 0.72 macro‑accuracy; they use multimodal in‑context learning on Voxtral‑24B to correct label bias, reaching 0.81; and they deploy a training‑free retrieval system with a voice‑anchored memory, scoring 0.68. All approaches surpass the official baseline.
By Jordi Luque, Lorenzo Concina, Marco Matassoni, Alessio Brutti, Filippo Vella
RetroThinker is a multi-stage post‑training framework that enhances SpeechLLMs by enabling them to self‑verify and forward‑correct Chain‑of‑Thought reasoning steps during inference. It combines supervised fine‑tuning on curated retrospective thinking data with length‑based direct preference optimization to improve reasoning while the user speaks. On the GSM8K benchmark, RetroThinker achieves an 11% absolute accuracy gain over non‑retrospective baselines while maintaining comparable latency.
By Yi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed, David Harwath
The paper explores using a large language model (LLM) to generate background context for social media posts and tests four ways to integrate this context into a Sentence-BERT (SBERT) hate‑speech detection classifier. The methods include text concatenation, embedding concatenation, hierarchical transformer fusion, and LLM‑driven text enhancement. Experiments on the Latent Hatred dataset of implicitly hateful tweets and the MAMI dataset of misogynous memes show that adding generated context can raise F1 scores by up to 3 points in textual and 6 points in multimodal settings compared to a zero‑context baseline, with embedding concatenation yielding the best results.
By Joshua Wolfe Brook, Ilia Markov
The paper evaluates a multilingual ASR model (MMS‑1B‑all) on a Garrusi Kurdish dataset using a common‑reference staged normalization approach. By normalizing both reference and hypothesis, the authors show that raw Arabic‑script hypotheses yield a 111.70 % WER, which drops to 97.85 % after folding into a reduced orthography, highlighting the impact of orthographic differences on error measurement. A Southern Kurdish fine‑tuned system performs worse, and residual errors are partly due to scoring‑pipeline limitations rather than recognition failures.
By Hiwa Asadpour
HiPerViT is a compact vision-only architecture that injects an explicit second-order statistical prior into a transformer-based pipeline for texture recognition. It combines global and local image views with a compact bilinear descriptor encoded as a statistical token, and integrates this token with first-order spatial representations through Perceiver-style latent distillation. Across six texture recognition benchmarks, HiPerViT consistently outperforms strong vision-only baselines, achieving notable gains on DTD, GTOS-Mobile, and 1200Tex, and the improvements are largely independent of backbone depth or fusion topology.
By Jo\~ao Pedro C. A. de S\'a, Odemir Martinez Bruno
The paper presents M2Heat, a physics-inspired framework for fusing hyperspectral and LiDAR data in land‑cover classification. It introduces a visual heat conduction module (vHeat) and Frequency Value Embeddings (FVEs) to model anisotropic information flow, capturing global dependencies with sub‑quadratic complexity. Combined with a Cross‑Frequency Fusion (CFF) module, M2Heat delivers discriminative, robust features and achieves competitive performance on Trento, Houston2013, and Augsburg benchmarks while offering an interpretable heat‑conduction perspective.
By Kan Wei, Jiahui Cui, Jing Yao, Xinyu Zhao, Lei Wang, Pedram Ghamisi
The paper introduces VWG-Bench, a benchmark covering nine reasoning dimensions and 38 tasks to evaluate video generative models on symbolic reasoning, physical laws, and goal pursuit. It also presents Vid-PRE, a prompt-rewriting framework that offloads reasoning to a VLM, improving logical performance without changing the generator architecture. Experiments show that current models excel at visual quality but struggle with logic-heavy tasks, while Vid-PRE significantly boosts reasoning across multiple generators.
By Meng Luo, Yicheng Liu, Jiahao Wang, Yuanxing Zhang, Xin Tao, Pengfei Wan, Kun Gai, Hao Fei
The paper introduces MOCO, a diffusion-based framework that generates 3D avatar motions from concurrent multimodal inputs such as speech audio, text descriptions, and trajectory data. MOCO decouples motion generation by independently producing modality-specific motions at each denoising step and then assembling them according to spatial rules, iteratively refining the combined motion. This approach yields coherent, lifelike, and synchronized movements, outperforming existing baselines on a multimodal benchmark.
By Yifei Liu, Qiong Cao, Hongwei Yi, Huaiguang Jiang, Changxing Ding
OmniKVQuant introduces a training‑free framework for quantizing the key‑value (KV) cache of omni‑modal large language models (Omni‑LLMs) that process audio, video, and text simultaneously. The method addresses two identified problems—temporal key drift and heterogeneous value geometry—by setting key quantization ranges over short input windows and rotating values separately for each modality. Applied to Qwen2.5‑Omni and Qwen3‑Omni, OmniKVQuant achieves 2‑bit KV caches while largely preserving performance across seven audio‑visual benchmarks, and includes a fused Triton decode kernel that eliminates the need for a dense FP16 cache.
By Suho Yoo, Hyunjong Ok, Jongmin Choi, Jihoo Jung, Joon Son Chung
SenseNova-U1.5 is an 8B‑MoT native unified multimodal model that can understand, reason about, and generate visual content without using an encoder or VAE. It improves visual fidelity and text rendering through spatially coherent patch reconstruction, large‑scale training on curated generation and editing data, and native resolutions up to 4K. Post‑training, specialized experts for visual aesthetics, bilingual text rendering, infographic generation, and image editing are optimized and distilled into a multi‑expert framework, yielding advances in image fidelity, complex composition, multi‑reference editing, and instruction following.
By Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu, Zhengqi Bai, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Bo Yang, Chen Feng, Chengguang Lv, Guangjia Liu, Guanlin Wang, Hanyu Zhang, Haojia Yu, Hongcan Xiao, Hongli Wang, Huan Wu, Huaping Zhong, Jian Fang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jing Zuo, Jingcheng Ni, Junxiang Xu, Linjun Dai, Mutian Xu, Peishen Yan, Penghao Wu, Ruijie Mao, Ruisi Wang, Shihao Bai, Shuang Yang, Shuya Yang, Shuyan Zheng, Silei Wu, Siying Li, Tao Chu, Tianbo Zhong, Tongxi Zhou, Weichao Luo, Weichen Fan, Wenhao Jia, Wenjie Gao, Xiangli Kong, Yan Li, Yang Yong, Zimo Wen, Zixuan Qian, Wenxiu Sun, Ruihao Gong, Quan Wang, Lewei Lu, Lei Yang, Ziwei Liu, Dahua Lin
IMLE‑VLA replaces the iterative action head in vision‑language‑action policies with a single‑step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). This eliminates multi‑step sampling, boosting inference frequency by 3.67× (55 Hz vs. 15 Hz) and achieving the highest average success rate (98.0 %) on the 40‑task LIBERO benchmark while maintaining robustness under perturbations. Real‑world tests on a Franka Emika Panda show smoother, faster motions and a 3.9×–6.6× reduction in inference time per episode.
By Kian Hosseinkhani (Simon Fraser University), Qinhe Peng (University of Pennsylvania), George Shramko (Simon Fraser University), Mehran Aghabozorgi (Simon Fraser University), Jianing Qian (University of Pennsylvania), Tristan Engst (Simon Fraser University), Alireza Moazeni (Simon Fraser University), Dinesh Jayaraman (University of Pennsylvania), Ke Li (Simon Fraser University, Canada CIFAR AI Chair)
MedGEN-Bench is a new benchmark for open‑ended multimodal medical generation that addresses limitations in current medical visual benchmarks, such as query‑image misalignment, closed‑ended answer spaces, and text‑centric outputs. The dataset contains 6,422 image‑text pairs across six imaging modalities, 15 clinical tasks, and 27 subtasks, including VQA, image editing, and contextual multimodal generation pairs. Evaluation combines reference‑based fidelity metrics with a structured, checklist‑guided assessment by a medical VLM judge, and preliminary results show that image‑output tasks remain unsaturated while contextual augmentation improves image‑instruction similarity.
By Junjie Yang, Yuhao Yan, Gang Wu, Rui Qian, Zhisheng Chen, Haijiang Li, Yuhe Wu, Qichao Zhao, Dawen Tian, Xiang Wan, Fenglei Fan, Wenjian Qin, Yongquan Zhang, Feiwei Qin, Changmiao Wang
The paper investigates how to combine synthetic and real historical images to improve OCR for the endangered Manchu language. Using 60,000 synthetic and 20,306 real word images, the authors evaluate three vision‑language models and a compact CRNN across synthetic‑only, real‑only, joint, and sequential training regimes. Adding real data boosts word accuracy to 95–96%, and ensembling the best recognizers raises it to 98.27% without further training.
By Yan Hon Michael Chung, Hanlin Wang
The paper introduces MUC-FL, a block‑wise marginal utility contribution framework that selectively transmits only the most impactful data blocks in federated learning to reduce communication overhead. Applied to a multimodal dataset derived from multiple MIMIC clinical datasets, the method identifies 24 out of 1,135 candidate blocks (1.76%) as carrying meaningful improvement signals, potentially cutting communication by 45‑50% while preserving or enhancing model quality. The deduplication‑based block selection achieves a macro F1 score of 0.8566 versus 0.8155 for standard federated optimization, showing improved performance especially for underrepresented classes.
By Akshay Mhatre, Vikram Karthick, Deepti Gupta, Jia Zou
CS-Guard is a new benchmark that systematically evaluates guardrails for code generation security, covering 1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) for text-to-code generation, as well as 331 code prompts for code-to-code generation. The study empirically tests nine guardrails across seven large language models, finding that many guardrails fail to prevent malicious code generation, with attack success rates reaching about 50% for text-to-code and up to nearly 100% for code-to-code and FSA scenarios. CS-Guard introduces a modular three-layer guardrail taxonomy and releases its benchmark and data to support future research.
By Jinyang Li, Mingyu Guo, Hung X. Nguyen
The paper introduces SolCloudLLM, a large language model–based framework that fuses sky‑image patches with time‑series data through bidirectional multimodal fusion for short‑term solar forecasting. Experiments on the SIRTA and SKIPP'D datasets show that SolCloudLLM outperforms existing baselines, achieving up to a 25.4% reduction in mean squared error, especially under cloudy conditions and in few‑shot scenarios.
By Ken Chen, Maneesha Perera, Wei Wang, Sachith Seneviratne, Hansani Weeratunge, Saman Halgamuge
TeleOCR is a unified framework for document parsing that tackles challenges in both decoupled and end-to-end Vision‑Language Models. It introduces deformation‑aware learning to handle geometric distortions, an adaptive sampling mechanism for complex layouts, and a content‑structure decoupled strategy to model formula grammars and table structures. The approach achieves state‑of‑the‑art results on multiple benchmarks, including top placement in the ICDAR 2026 Sci‑ImageMiner Challenge.
By Peng Cai, Zhaofan Zou, Shifa Liu, Yikun Wang, Jiawei Tang, Kaicheng Yang, Meng Tong, MingKun Jiang, Zhongjiang He, Hao Sun
RelayS2S is a hybrid real‑time dialogue system that runs a fast duplex speech‑to‑speech path and a slow ASR‑to‑LLM path in parallel. The fast path speculatively drafts a short response prefix and streams it to TTS, while the slow path generates a higher‑quality continuation conditioned on that prefix. A lightweight verifier decides whether to commit the prefix or fall back to the cascaded pipeline, achieving much lower latency (81 ms P90 first‑chunk) while preserving 99% of the cascaded pipeline’s textual quality.
By Long Mai, Junli Liang