The paper explores training a large language model solely on textual video descriptions to perform zero‑shot video temporal localization, eliminating the need for paired video‑text data during training. Using a 134K‑example corpus and adapting Qwen3‑8B with LoRA on CLIP or LLM2CLIP embeddings, the authors evaluate on Charades‑STA and QV‑Highlights, achieving modest performance when directly replacing text with frame embeddings. They introduce Nearest Entity Replacement (NER), a training‑free mapping that represents each video frame by the mean of its nearest text‑entity embeddings, which significantly improves results and narrows the modality gap.
By Divyanshu Mishra, Sabine Sternig, Rakshith Shetty, Erhan Gundogdu
CoSafe is a modular, ADS-agnostic framework that extends runtime safety assurance from ego-centric takeover to scene-level cooperative intervention in mixed-traffic autonomous driving. It uses vehicle-to-everything communication to allow roadside units to monitor hazards and jointly mitigate risks involving multiple vehicles. Evaluation on the InterDrive benchmark shows that CoSafe improves driving scores by 70.03%, reduces safety violations by 87.80%, and accurately identifies unsafe autonomous vehicles with an F3 score of 0.930 while meeting real-time constraints.
By Dingji Wang, You Lu, Haowen Jiang, Yanggang Chen, Yuyang Bi, Bihuan Chen, Shenglin Bao, Xin Peng
Rubric Curriculum RL (RcRL) is a reinforcement learning approach that leverages the generation‑verification gap in non‑verifiable domains by using pairwise preferences over rollouts and a curriculum over rubric criteria. Unlike traditional methods that rely on absolute scoring and stationary judges, RcRL provides a more discriminative, non‑stationary signal, allowing policies to maintain output entropy and continue improving beyond 1,000 training steps. In experiments on creative writing and HealthBench, RcRL outperforms baseline models, achieving a 70.5% human win rate and significant accuracy gains over the base model.
By Sumeet Ramesh Motwani, Tejas Krishnan, Alistair Letcher, Charles London, Suhaas Bhat, Huitian Jiao, Philip Torr, Riashat Islam, Christopher Summerfield, Jakob Foerster, Christian Schroeder de Witt, Qilong Gu, Shital Shah
arXiv:2611. 06418v1 Announce Type: cross Abstract: Brains and large language models need not be considered equivalent systems to reveal an interpretable commonality: both exhibit high-dimensional, nonlinear dynamics whose behavior can only be modeled imperfectly.
By Kasra Fallah, Rudramani Singha, Hannah Ghanei, Paul Sajda, James Anderson, Erfan Zabeh
The paper investigates how to predict which offspring in a Quality‑Diversity (QD) archive will be retained over time, rather than just entering the archive. By analyzing signals available before reproduction, the authors find that lineage depth is the most reliable indicator of long‑term persistence, though its predictive power varies with population size. Despite this insight, biasing parent selection toward these signals does not improve overall search performance and can even lower the QD‑score.
By Corrado Calamita, Matteo Mendicini, Luca Ferrari, Riccardo Bertamini
Trick-or-Treat is an adversarial multimodal medical benchmark that pairs real chest radiographs with synthetic clinical photographs to test cross‑modal reasoning. Each condition has matched pairs where the radiograph and photograph suggest the same disease, and mismatched pairs where the photograph shows an alternative finding. In tests of three frontier models, hallucinations of clinically significant findings rose from 25‑37.5% for single photographs to 45‑57.5% when mismatched pairs were presented, with models often ignoring mismatches and generating findings that better aligned with the radiograph.
By Oishi Banerjee, Eujin Lee, Sung Eun Kim, Alexandra N. Willauer, Christine Y. Zhou, Zhizhou Yang, Pranav Rajpurkar
The paper introduces Counterfactual Foreground Retrieval (CFR), an evidence‑aware evaluation protocol for automated individual animal identification. CFR assesses retrieval performance under three conditions: full images, foreground‑only, and shortcut‑only (background or silhouette). By comparing these views, CFR produces an evidence profile that reveals whether models rely on animal features or on identity‑correlated shortcuts, and the authors provide masks and code for 34 datasets to support this analysis.
By Ankit K. Upadhyay, Aleksandr Algasov, Ekaterina Nepovinnykh, Fedor Zolotarev, Tuomas Eerola, Heikki K\"alvi\"ainen, Charles V. Stewart, Lukas Picek
The paper introduces AutoMMemo, a framework that lets agents automatically design memory mechanisms for learning from multimodal experience. Each memory mechanism is represented as an executable memo program that specifies how past episodes are stored, organized, and retrieved. Through iterative evaluation, reflection-guided mutation, and budget-aware tree search, AutoMMemo learns effective memory designs that improve agent performance on GUI/Web navigation and multimodal visual reasoning tasks while keeping token and interaction costs reasonable.
By Xingyu Sui, Weixiang Zhao, Yongxin Tang, Yanyan Zhao, Yang Wu, Dandan Tu, Bing Qin
arXiv:2602.18874v2 Announce Type: replace-cross
Abstract: Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images. Achieving accu...
By Jie Li, Suorong Yang, Jian Zhao, Furao Shen
arXiv:2610.26826v2 Announce Type: replace-cross
Abstract: Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equally essential for applyin...
By Yuchi Wang, Rongyao Fang, Weihao Yu, Xilin Wei, Tiancheng Gu, Dingkang Yang, Hang Zhang, Dayiheng Liu, Hongsheng Li, Shuai Bai
arXiv:2611.05546v1 Announce Type: new
Abstract: Decentralized federated learning (DFL) eliminates the central aggregation server but remains vulnerable to data heterogeneity, Byzantine attacks, and c...
By Ojaswi Sinha, Amin Farajzadeh, Animesh Yadav, Melike Erol-Kantarci
arXiv:2611.05729v1 Announce Type: new
Abstract: With scalable Laplacian solvers now available, the next frontier is to exploit them more effectively for high-quality hypergraph partitioning. In this...
By Rongjian Liang, Zhuo Feng, Brucek Khailany
arXiv:2611.06158v1 Announce Type: new
Abstract: Many high-stakes regression decisions ask three things of a model at once: a point estimate to act on, an interval that bounds the risk of acting, and...
By Lidor Rubi, Gilad Katz
arXiv:2611.05801v1 Announce Type: cross
Abstract: Holistic perception for autonomous agents requires reliably segmenting and associating scene elements across time and camera views, including objects...
By Rohit Mohan, Maximilian Luz, Swarnava Chowdhury, Yao Lu, Florian Drews, Thomas N\"urnberg, Yakov Miron, Federico Tombari, Stefano Gasperini, Abhinav Valada
arXiv:2611.05916v1 Announce Type: cross
Abstract: We study the minimum-disagreement cluster editing problem that, from a complete edge-signed graph, where a positive edge represents two vertices agre...
By Cong Ma, Guangting Chen, Yong Chen, Guohui Lin, Jiaxuan Ma, Lusheng Wang
arXiv:2611.05994v1 Announce Type: cross
Abstract: Federated Prompt Learning (FPL) enables parameter-efficient adaptation of pre-trained Vision-Language Models across decentralized clients without exc...
By Xuanjing Zhang, Qi Guo, Yanan Qiao, Yong Han, Junge Bo
arXiv:2611.06633v1 Announce Type: cross
Abstract: Bayesian experimental design (BED) is a principled framework for intelligent data acquisition with applications across a wide range of scientific and...
By Gavin Kerrigan, Marcel Hedman, Sahel Iqbal, Tom Rainforth
arXiv:2611.06811v1 Announce Type: cross
Abstract: Structure property prediction is a classical task in machine learning, ranging from molecular activity and materials properties to local functional r...
By Aditya Raghavan, Sergei V Kalinin
arXiv:2611.06854v1 Announce Type: cross
Abstract: Computer-use agents (CUAs) have recently achieved superhuman performance on several long-horizon benchmarks. However, their computational cost limits...
By Pranjal Aggarwal, Sean Welleck
arXiv:2602.03201v4 Announce Type: replace
Abstract: Model-based reinforcement learning (MBRL) is sample-efficient but struggles in sparse reward settings. A critical bottleneck arises from the lack o...
By Yao-Hui Li, Zeyu Wang, Xin Li, Wei Pang, Yingfang Yuan, Zhengkun Chen, Boya Zhang, Riashat Islam, Alex Lamb, Yonggang Zhang