MIST is a multimodal survival prediction framework that fuses whole-slide images and genomic profiles by representing genomic features as tokens that query histology context tokens derived from a foundation model. The architecture enriches molecular information with histology context before survival prediction, avoiding late-stage merging of separately encoded modalities. Training incorporates discrete-time survival prediction, genomic feature masking, WSI dropout, and contrastive alignment, and demonstrates improved external C-index across colon, renal, lung, and glioblastoma cohorts compared to standard fusion baselines.
By Muhammet Sami Yavuz, Sabri Mustafa Kahya, Richard R. Chen, Jana Lipkova, Benedikt Wiestler
arXiv:2609.21216v1 Announce Type: cross
Abstract: Vision-language-action (VLA) policies based on flow matching generate action chunks through repeated evaluations of an action expert. Increasing the...
By Zhipeng Tang, Xinda Chen, Weining Rao, Xiao Li, Wenting Tan, Yuning Wang, Xiao Shi, Xiaofang Zhao
FOCAL‑VLA is a framework that improves vision‑language‑action models by combining subtask‑guided geometry distillation with implicit world modeling. It transfers geometric knowledge from VGGT to focus on subtask‑relevant image regions and uses Track4World features to capture future 3D evolution, guiding action generation without running these models at inference time. Experiments demonstrate that FOCAL‑VLA outperforms baselines on both simulation benchmarks and real‑world manipulation tasks.
By Zhiyuan Gao, Di Wen, Yanxiang Zhan, Mohammad Khoshnazar, Jeroen Sch\"afer, Kunyu Peng, Michael Beetz
KnowDemo is a framework that generates diverse robot demonstrations from human videos by leveraging structured manipulation knowledge. It uses a vision‑language model to extract task requirements and permissible execution variations, then resolves these against target‑scene entities to guide candidate generation and screening before motion planning. The resulting demonstrations feature multimodal behavior, alternative contact strategies, and valid subtask orders, and have been shown to improve planning success and enable sim‑to‑real policy transfer across three tasks.
By Zhiyuan Gao, Yanxiang Zhan, Mohammad Khoshnazar, Jeroen Sch\"afer, Michael Beetz
VLA-Scope is a two‑stage framework designed to predict failures in vision‑language‑action models under distribution shifts. The first stage detects out‑of‑distribution inputs and classifies their shift categories using pooled image and language representations. For OOD inputs, the second stage updates failure risk during execution by combining shift category, action‑prefix features, and execution progress, achieving a ROC‑AUC of 0.8497 after 60 actions and outperforming baseline methods.
By Kaiwen Zhu, Dongfang Liu, Liangkai Liu
AgentVidBench is a new multi‑hop video question‑answering benchmark designed to evaluate spatial, temporal, and causal reasoning in multimodal large language models (MLLMs). Unlike existing tests that focus on simple scene queries or global summaries, AgentVidBench includes step‑by‑step solution traces to assess whether agents gather the necessary evidence to justify their answers. Experiments with 12 MLLMs show limited single‑turn performance, but integrating these models into agentic workflows improves both accuracy and trajectory scores, establishing AgentVidBench as a comprehensive testbed for future research on agentic video understanding.
By Seoyeon An, Hyeonseo Jang, Minsu Kim, Chanho Lee, Younghan Park, Kangwook Lee
SynthDemo‑RL introduces a teacher‑student framework that uses an automated teacher to generate successful manipulation trajectories from simulator‑privileged state, which are then distilled into a Vision‑Language‑Action (VLA) student via supervised fine‑tuning. The student is further refined with PPO using binary task‑success rewards. On the LIBERO‑PRO benchmark, SynthDemo‑RL rescues all 27 previously unsolvable tasks and achieves near‑perfect success rates, matching performance that would otherwise require human demonstrations.
By Hiroaki Kingetsu, Hiroaki Kurihara, Kaoru Yokoo, Kenji Fukumizu, Manohar Kaul
arXiv:2609.21743v1 Announce Type: cross
Abstract: Entropy minimization is a standard objective for test-time adaptation (TTA), but it can fail in imbalanced binary segmentation. Unlike image classifi...
By Zhengshan Wang, Joshua Charles Webster-Ford, Yifei Tian, Xinxin Wang, Long Chen, Weiping Ding
arXiv:2609.21942v1 Announce Type: cross
Abstract: A robot that fails at a task faces the first decision in corrective dialogue: act on its own diagnosis, consult another onboard sensor, or interrupt...
By Eshika Pathak, Leela Krishna
MemeLens is a unified multilingual, multitask Vision‑Language Model designed to improve meme understanding across a wide range of tasks such as hate, misogyny, propaganda, sentiment, and humour. The authors consolidated 38 public meme datasets, mapping their labels into a shared taxonomy of 20 tasks covering harm, targets, figurative intent, and affect, and conducted extensive experiments to show that multimodal training and a unified approach outperform fine‑tuning on individual datasets. All experimental resources, the model, and the datasets are released publicly for community use.
By Ali Ezzat Shahroor, Mohamed Bayan Kmainasi, Abul Hasnat, Dimitar Dimitrov, Giovanni Da San Martino, Preslav Nakov, Firoj Alam
CRYSTAL is a diagnostic benchmark comprising 6,372 multimodal reasoning instances that assess models through verifiable intermediate steps. It introduces two metrics—Match F1 and Ordered Match F1—to evaluate step-level precision, recall, and order. The benchmark, built via a Delphi-inspired pipeline with four independent MLLMs, reveals systematic failures in current models, such as cherry‑picking and disordered reasoning, and proposes a Causal Process Reward and CPR‑Curriculum to improve reasoning performance.
By Wayner Barrios, SouYoung Jin
LiteMedCoT-VL is a parameter‑efficient pipeline that transfers chain‑of‑thought reasoning from a 235B teacher model to a 2B student model using LoRA fine‑tuning on explanation‑enriched data. The approach enables a compact vision‑language model to perform medical visual question answering without relying on image captions, achieving 64.9% accuracy on the PMC‑VQA benchmark—an 11‑point improvement over the zero‑shot Qwen3‑VL‑4B baseline. Visual grounding analysis confirms that the model bases its predictions on image content rather than textual priors.
By Runze Ma, Shunbo Jia, Haonan Lyu, Guo Liu, Caizhi Liao
arXiv:2606.03963v4 Announce Type: replace-cross
Abstract: Deep reinforcement learning enables autonomous robots to learn complex navigation tasks, but still relies heavily on time consuming manual re...
By Roohan Ahmed Khan, Yasheerah Yaqoot, Amir Atef Habel, Muhammad Ahsan Mustafa, Dzmitry Tsetserukou
The study examines how different vision‑language‑action (VLA) policies execute a manipulation task by comparing the geometry of their end‑effectors across 15,000 closed‑loop LIBERO rollouts. By pairing 3,600 configuration‑matched policy executions, the authors find that when both policies succeed, their end‑effector trajectories are much closer (median DTW distance 0.0120 m) than when only one succeeds (0.0380 m), a pattern consistent across all tasks, policy pairs, and nine representations. Even successful executions remain as far from same‑task demonstrations as the demonstrations are from each other, indicating that task‑associated geometry, rather than training data overlap, drives these differences.
By Xingyu Lin, Zhuang Li, Zhongrun Wu, Shouquan Zhou, Dehui Du
The Spoken Wikipedia Presentation Corpus extends the existing Spoken Wikipedia Corpora by adding LLM-generated slide decks for multimodal automatic speech recognition (ASR). Slides are produced through a hybrid pipeline that combines LLM-based content planning with rule-based design, generating titles, bullet points, takeaway messages, and visual descriptions for illustrations. The corpus is evaluated with multiple ASR and spoken language models, achieving a best micro-WER of 10.23% and micro-CER of 6.48% on audio-only inputs, with English performing best and lower-resource languages showing higher error rates.
By Thomas Ranzenberger, Steffen Freisinger, Tobias Bocklet, Korbinian Riedhammer
OmniVChat defines a native audio‑visual dialogue task where models receive raw audio and video from a user and produce text responses, eliminating the need for separate text queries or speech recognition. To address data scarcity and evaluation challenges, the authors introduce OmniVChat‑Studio, a multi‑agent engine that synthesizes single‑ and multi‑turn dialogues, and OmniVChat‑Bench, a benchmark assessing models across five dialogue ability categories. They also propose OmniVChat‑RL, a reinforcement‑learning reward that balances reply correctness, efficiency, and style, and demonstrate that training Qwen3‑Omni‑Instruct with this reward on synthesized data improves performance on both synthetic and human‑recorded benchmarks.
By Haolin He, Yunfei Chu, Qi Chen, Wen Huang, Yuan Feng, Muzhi Zhu, Zheqi Dai, Haoning Xu, Dongchao Yang, Chunyat Wu, Zining Liang, Zhengxi Liu, Xiquan Li, Xie Chen, Xize Cheng, Qize Yang, Jin Xu, Qiuqiang Kong
Samsone is a family of small audio language models (SALMs) designed for on‑device inference, with the flagship Samsone‑134M setting a new state‑of‑the‑art for its size class across multiple benchmarks. The paper also presents Samsone‑99M and Samsone‑356M to study scaling laws, showing that these compact models achieve performance competitive with much larger counterparts. The authors train the models on publicly available data and release training code, weights, mobile‑optimized checkpoints, and an open‑source Android app for real‑time inference.
By Piotr Masztalski, Micha{\l} K. Grzeszczyk, Olaf Sikorski
XCalib is an unsupervised dense registration framework that aligns thermal and visible video streams by optimizing virtual pinhole camera parameters and predicted monocular depth, thereby restricting spatial displacements to physically valid projection geometries. It introduces a novel registration paradigm using camera parameterization as an implicit regularizer, a robust Normalized Edges Correlation (NEC) metric for cross‑spectral alignment, and demonstrates superior temporal stability and alignment accuracy on public ADAS datasets compared to unconstrained dense flow baselines.
By Aurelien Godet, Gabriel Jobert, Mauro Dalla Mura
The paper introduces a three‑stage pipeline to improve accented conversational ASR for speakers from India, Indonesia, and Latin America. It uses heuristic SQL filters to curate entity‑rich training data, regional LoRA adapters fine‑tuned on Qwen2.5‑Omni‑3B to generate both verbatim and corrected transcripts, and a six‑category error taxonomy validated by an LLM judge. The approach raises entity recall to 80‑85% and filler recall to 76‑86%, while keeping WER low (6‑10%) and outperforming Whisper and a commercial ASR on entity recall.
By Fiza Husain, Ankit Pandey, Yash Singh
VISPATH is a visual‑intent‑guided path reasoning framework designed for multimodal knowledge graph question answering (MM‑KGQA). It first identifies a reliable starting entity by fusing multimodal grounding with graph‑structural cues, then iteratively discovers and refines reasoning paths using hop‑specific multimodal intent and a reasoning‑chain pruning step. The framework is evaluated on the newly introduced VISPATH‑Bench, which tests two‑to‑four‑hop reasoning, and demonstrates consistent improvements over strong baselines, even surpassing GPT‑5.4 when using GPT‑4o as the backbone.
By Jinke Wu, Zhengpin Li, Mengzhe Jia, Yang Li, Wentao Zhang