Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time. We study fixed-footprint continual adaptation: the deployed adaptation state is kept under a fixed memory budget, while the backbone model is left unchanged and task-specific updates are externalized.
We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning, task-specific fine-tuning, or stepwise hard denoising guidance, often suffer from artifacts and compromised global scene consistency.
Quantum machine learning has recently emerged as a promising paradigm that leverages the expressive power of quantum circuits to address complex learning tasks. In this work, we investigate the applicability of hybrid quantum-classical neural networks to sentiment analysis, a central problem in natural language processing.
This work introduces AIriskEval-edu-db2, a new dataset designed to train and evaluate auditors based on LLMs for an explainable pedagogical risk assessment in instructional content for grades K-12. The dataset comprises 1,639 explanations from 170 curated ScienceQA questions, covering science, language arts, and social sciences.
Large 3D foundation models such as MASt3R achieve state-of-the-art stereo reconstruction but are computationally demanding for deployment under strict hardware constraints -- a critical limitation in domains such as planetary exploration, where onboard computing is severely restricted. We study how far such models can be compressed through knowledge distillation, using lunar stereo reconstruction as a challenging and practically relevant case study.
Recent multimodal large language models (MLLMs) have substantially advanced video understanding, yet long-form video QA remains challenging under fixed input token budgets, where uniform sampling can be inefficient for evidence localization. We propose ReQuest , an uncertainty-driven, question-adaptive keyframe selection pipeline that aligns question intent with relevant video content through selective computation.
arXiv:2607. 00310v1 Announce Type: cross Abstract: Foundation video diffusion models are increasingly viewed as world simulators for embodied agents, yet their pretraining on internet-scale generic video leaves them poorly aligned with real-world deployment domains.
By Amirreza Rouhi, Rajat Aggarwal, Parikshit Sakurikar, Anoop M. Namboodiri, Sashi P. Reddi
arXiv:2607. 00434v1 Announce Type: cross Abstract: Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting after full-parameter instruction tuning.
By Guohao Sun, Xiaofang Wang, Yash Patel, Mengchen Liu, Zhiqiang Tao, Praveen Krishnan
arXiv:2607. 00924v1 Announce Type: new Abstract: Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning.
By Subhadeep Pal, Shashwat Sourav, Tirthankar Ghosal, Markus J. Buehler
arXiv:2607. 00358v1 Announce Type: new Abstract: Electroencephalogram (EEG) captures endogenous brain activity with high temporal fidelity and holds substantial promise for precise emotion decoding.
By Xin Zhou, Xiang Zhang, Hao Deng, Lijun Yin
arXiv:2604. 25421v2 Announce Type: replace-cross Abstract: Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data, yet in mobile deployments the training wall-clock is often bottlenecked by straggler-limited uplink communication under heterogeneous bandwidth and intermittent participation.
By Changyu Li, Shuanghong Huang, Jiashen Liu, Ming Lei, Jidu Xing, Kaishun Wu, Lu Wang, Fei Luo
arXiv:2604. 17289v2 Announce Type: replace Abstract: Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise.
By Sajjad Ghiasvand, Mark Beliaev, Mahnoosh Alizadeh, Ramtin Pedarsani
arXiv:2607. 01170v1 Announce Type: cross Abstract: Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces.
By Zhuoxuan Zhang (Yang), Kangqi Ni (Yang), Yuhang Chen (Yang), Mingfu Liang (Yang), Xiaohan Wei (Yang), Yunchen Pu (Yang), Fei Tian (Yang), Chonglin Sun (Yang), Frank Shyu (Yang), Adam (Yang), Song, Sandeep Pandey, Luke Simon, Tianlong Chen, Xi Liu
arXiv:2603. 10263v2 Announce Type: replace-cross Abstract: We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrained generative robot policies.
By Zhanyi Sun, Shuran Song
arXiv:2607. 00510v1 Announce Type: new Abstract: Knowing which training examples drive outputs is fundamental to auditing, correcting, and understanding language models, yet for modern LLMs this remains expensive, approximate, and largely post-hoc.
By Dan Ley, Giang Nguyen, Himabindu Lakkaraju, Julius Adebayo
arXiv:2604. 14669v2 Announce Type: replace Abstract: Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models, yet their optimization dynamics in deep learning remain underexplored.
By Minhak Song, Liang Zhang, Bingcong Li, Niao He, Michael Muehlebach, Sewoong Oh
arXiv:2607. 00572v1 Announce Type: new Abstract: Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies.
By Shei Pern Chua, Fangzhao Wu
arXiv:2603. 21048v2 Announce Type: replace-cross Abstract: The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions.
By Gia-Bao Doan, Nam-Khoa Huynh, Minh-Nhat-Huy Ho, Khanh-Thanh-Khoa Nguyen, Thi-Thu-Hien Pham, Thanh-Hai Le
arXiv:2607. 00661v1 Announce Type: cross Abstract: Explanations for emotion classifiers are usually produced post hoc, with no guarantee that they reflect the computation behind the label.
By Frank Xing, Erik Cambria
arXiv:2607. 00603v1 Announce Type: new Abstract: We give a descent-free, alignment-free measurement of singular structure on trained networks.
By Tejas Pradeep Shirodkar