Omni-Decision is an omni-modal agent that uses evidence-ledger planning to manage noisy multimodal observations. It replaces the growing dialogue history with a compact evidence ledger that tracks missing, confirmed, and conflicting evidence, allowing the planner to operate on a streamlined context. The system achieves state‑of‑the‑art accuracy on OmniGAIA and WorldSense while operating at a fraction of the cost of larger models.
By Ming Ma, Yi Zhu, Yiran Zhong, Feida Zhu, Yuhao Wang, Junhan Shi, Lingrui Mei, Tianming Yang, Steven Hoi
The paper discusses how active learning (AL) can alleviate the expert annotation bottleneck in biodiversity monitoring by selecting the most informative samples under a fixed budget. It highlights that while AL reduces labeling effort, its non-random sample selection complicates model validation, calibration, and ecological inference, issues often overlooked in current studies. The authors review existing AL research across acoustic and image data, identify gaps such as limited species coverage and lack of real-world deployments, and propose a tutorial framework and roadmap for developing AL methods that support efficient training, reliable validation, and trustworthy ecological conclusions.
By Ben McEwen, Shiqi Zhang, Dan Stowell
The paper introduces FFM-CP, a framework that fuses multiple pathology vision‑language foundation models for few‑shot learning. It aligns heterogeneous representations with an Orthogonal Procrustes transformation, then uses a unified graph to refine support‑image features and class prototypes across backbones. Experiments on six histopathology datasets show that FFM‑CP outperforms the best single adapted model in 50 of 54 few‑shot comparisons.
By Anh-Tien Nguyen, Trung DQ. Dang, Nghiem Tuong Diep, Bui Ngoc Han Nguyen, Tan-Ha Mai, Miriam Cindy Maurer, Phuong Hoa Nguyen, Thi Thuy Uyen Nguyen, Youngjun Park, Daniel Sonntag, Duy Minh Ho Nguyen, Anne-Christin Hauschild
The paper introduces a method to prune six layers from the encoder of OpenAI’s Whisper ASR model, reducing the encoder stack by 18.5% without requiring custom inference code. Layers are selected based on their minimal impact on Word Error Rate when removed. After pruning, the model’s WER rises from 18.2% to 21.9%, but distillation with unlabeled monolingual speech data lowers it to 20.1%.
"whyItMatters":"The approach offers a straightforward way to accelerate Whisper inference by simplifying the encoder while maintaining acceptable accuracy, and the released code and model enable immediate adoption by the community."
By Rasmus Aagaard, Nicki Skafte Detlefsen
The paper introduces PIECE, a Parameter Importance-Driven Continual Learning method that selectively updates only 0.1% of core parameters to preserve general abilities while learning new domain knowledge. PIECE employs two importance estimators—PIECE‑F using Fisher Information and PIECE‑S combining gradient and curvature information—to guide updates. Experiments on three language models and two multimodal models demonstrate that PIECE maintains general capabilities and achieves state‑of‑the‑art continual learning performance without accessing prior training data or adding parameter overhead.
By Lingxiang Wang, Hainan Zhang, Zhiming Zheng
The paper introduces WebMRE, an offline benchmark comprising 541 tasks and 5,293 steps extracted from WebArena trajectories, designed to provide deterministic scoring for web agents without live environments. It enables the first systematic study of how guide sentences and grounded actions reinforce each other, showing that jointly decoding a guide improves element selection accuracy and that the guide acts as a causal instruction channel. The authors fine‑tune models that outperform leading zero‑shot baselines on all offline metrics.
By Chengguang Gan, Yunhao Liang, QingHao Zhang, Shiwen Ni
RapidUn is a parameter reweighting framework that uses influence estimates to guide LoRA-only updates for efficient unlearning of targeted behaviors in large language models. It operates in a practical PEFT setting with a small forget set and limited retain buffer, converting cross-sample influence into fixed sample-specific weights for weighted LoRA unlearning. Experiments on Llama‑3‑8B with Dolly‑15k and Alpaca‑57k datasets show RapidUn achieves lower trigger ASR than Fisher, GA, and LoReUn while preserving clean utility, and delivers a 77× wall‑clock speedup over clean‑corpus LoRA retraining, with additional evaluations supporting its effectiveness.
By Guoshenghui Zhao, Huawei Lin, Weijie Zhao
The paper introduces MAD2, a synthetic benchmark of 1,000 two‑speaker dialogues with about 10 hours of audio and 1,230 check‑worthy sentence annotations for spoken claim verification. It proposes a calibrated multimodal fusion approach that combines a context‑aware audio encoder with a dialogue‑aware text model. Experiments show that adding dialogue context improves verification performance, though the gains differ across scenarios, and that fusion offers the largest advantage when full‑dialogue context is available, though it does not consistently outperform text alone.
By Chaewan Chun, Delvin Ce Zhang, Dongwon Lee
The paper presents a data‑centric approach to improve automatic speech recognition for non‑verbal vocalizations (NVVs) in the ISCSLP NVVSpeech Challenge. It introduces cross‑dataset label harmonization and a two‑stage sampling schedule—first square‑root category sampling to address long‑tailed distributions, then uniform‑category fine‑tuning—to jointly transcribe lexical content and 16 NVV categories. The final system achieved an official score of 63.86, ranking fourth in Track 1.
By Shangyue Jia, Jingru Ma, Yangzhuo Li, Daoping Luo, Bowen Tian, Hanchen Lu, Wenze Ren, Yunxiang Chen, Houdun Liu, Su Feng, Lei Xie, Liumeng Xue
The paper investigates when vision‑language models (VLMs) can independently analyze human‑centered video and when human oversight is still needed. By reviewing 1,702 CHI 2026 papers, the authors develop a five‑dimensional taxonomy of video annotation tasks and build a benchmark of 15 representative tasks. Experiments show that VLMs alone achieve near‑human accuracy (HNS = 97.0), while human verification of VLM outputs yields the highest accuracy (HNS = 121.5) and significantly reduces annotation time and cost.
By Xiyuan Shen, Jiuyang Lyu, Seokhyun Hwang, Huanfen Yao, Shwetak Patel, Zhihan Zhang, Jacob O. Wobbrock
The paper introduces S2A, a semantic-to-spatial alignment framework designed for alignment‑free RGB‑T salient object detection. It employs a global‑guided hierarchical fusion module to refine intra‑modal features, an alignment‑free cross‑modal channel attention module to exchange semantic information, and a spatial deformable cross‑attention module to recover local spatial correspondence. These components collectively reduce misalignment‑induced feature contamination and achieve competitive performance on public benchmarks without additional bells and whistles.
By Qiangqiang Zhou, Yang Luo, Yong Chen, Jiawei Xu
The paper introduces a modular perception framework that uses vision‑language models (VLMs) to annotate object‑level regions from a single RGB‑D observation, then grounds these annotations with depth data to build an object‑centric representation. Experiments on 151 tabletop scenes demonstrate that this decomposition maintains strong semantic performance while significantly improving localization and depth estimation compared to direct VLM inference. The resulting representation is integrated into a task‑planning system for robotic manipulation.
By Enrico Saccon, Tommaso Faraci, I\~{n}igo De La Ossa Zarzuelo, Luigi Palopoli, Marco Roveri, Matteo Saveriano
arXiv:2606.27264v3 Announce Type: replace
Abstract: Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form tex...
By Hashmat Shadab Malik, Anees Ur Rehman Hashmi, Numan Saeed, Muzammal Naseer, Salman Khan, Christoph Lippert
arXiv:2605.23137v3 Announce Type: replace-cross
Abstract: Electroencephalography (EEG) visual decoding remains challenging due to the modality gap between low-SNR neural signals and highly structured...
By Jiahe Meng, Weiming Zeng, Yueyang Li, Bo Chai, Hongjie Yan, Zhiguo Zhang, Wai Ting Siok, Nizhuan Wang
arXiv:2609.27382v1 Announce Type: cross
Abstract: Speech technology penalizes some voices: recognition errs nearly twice as often for Black speakers, and accuracy declines for second-language accents...
By Kian Shamsaie, Iman Modarressi
arXiv:2603.16932v2 Announce Type: replace-cross
Abstract: Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational ef...
By Nimrod Shabtay, Moshe Kimhi, Artem Spector, Sivan Haray, Ehud Rivlin, Chaim Baskin, Raja Giryes, Eli Schwartz
NV-Reason-CT is a generative vision‑language model designed for chest and abdominal CT analysis that preserves native 3D visual encoding and incorporates radiologist‑guided reasoning. The system couples a 3D vision transformer with a language model, feeding all visual tokens and their 3D coordinates directly into language decoding to maintain volumetric spatial information. Trained on a curated corpus of about 550,000 multimodal instruction examples, the model supports abnormality classification, report generation, and interactive reasoning, achieving strong performance on CT benchmarks and reducing expert interpretation time by 50%.
By Andriy Myronenko, Dong Yang, Yucheng Tang, Baris Turkbey, Benjamin Simon, Stephanie Harmon, Rikhil Makwana, Mariam Aboian, Sena Azamat, Ibrahim Ethem Hamamci, Sezgin Er, Bjoern Menze, Marc Edgar, Yufan He, Pengfei Guo, Daguang Xu
arXiv:2609.27901v1 Announce Type: new
Abstract: Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution. Other modalities, such as 3D body m...
By Ohad Rahamim, Dvir Samuel, Idan Schwartz, Gal Chechik
arXiv:2609.27869v1 Announce Type: new
Abstract: Long-horizon multimodal agents rely on specialized capabilities for perception, retrieval, reasoning, verification, and execution. Existing designs typ...
By Wenhao Yuan, Chenchen Lin, Jian Chen, Jinfeng Xu, Shuo Yang, Edith Cheuk-Han Ngai
DreamAvoid introduces a test‑time dreaming framework for Vision‑Language‑Action models to anticipate and avoid failures during critical manipulation phases. It uses a Dream Trigger to detect critical phases, samples candidate action chunks via an Action Proposer, and evaluates short‑horizon futures with a Dream Evaluator trained on success, failure, and boundary data. Experiments on real‑world and simulated tasks show DreamAvoid improves task success rates, achieving 72.5% success versus 48.8% for the base policy and 54.4% for GPC‑RANK.
By Xianzhe Fan, Yuxiang Lu, Shenyuan Gao, Xiaoyang Wu, Ruihua Han, Manling Li, Hengshuang Zhao