Vision-language models (VLMs) are increasingly proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while avoiding unnecessary intervention on routine but superficially alarming activity, a distinction obscured by binary safety benchmark...
Siddhant Panpatil, Arth Singh, Mijin Koo et al.· 0 citations
Large generative models are known to memorize their training data, posing severe privacy risks. Yet, current methods to detect training membership typically rely on the weak signals of a single forward pass. In this work, we find that training samples and unseen (held-out) data follow visibly different trajectories und...
Wojciech {\L}apacz, Stanis{\l}aw Pawlak· 0 citations
Machine learning network intrusion detection systems (IDS) operate on aggregate flow statistics that discard the distributional structure of traffic, and although information-theoretic measures capture that structure, established entropy estimators require raw packet sequences that pre-aggregated flow datasets do not c...
Mohamed Aly Bouke, Md Shohel Sayeed, Swee-Huay Heng et al.· 0 citations
Behavior-cloned policies often learn multiple behavior modes from demonstration datasets, including modes that are unsafe or otherwise undesired at deployment. For example, a policy trained on diverse handover demonstrations may learn to pass a knife blade-first. Standard remedies such as data curation and inference-ti...
Hao Wang, Jiuzhou Lei, Dayou Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Ultra-fine entity typing (UFET) assigns highly specific types to entity mentions, but current approaches struggle with types in the long tail. We hypothesize that a key limitation is the reliance on sentence-level context, since disambiguating evidence is often spread across multiple sentences. Testing this has been di...
Mreedul Gupta, Advait Deshmukh, Ashwin Umadi et al.· 0 citations
Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on Video Question Answering (VideoQA). Nevertheless, existing benchmarks are predominantly evaluated through answer correctness, while the faithfulness of predicted evidence supporting those answers remains insufficiently eva...
Linpeng Huang, Weixing Chen, Zexin Chen et al.· 0 citations
Although pitch sequencing is a central topic in baseball analytics, previous studies have primarily focused on improving predictive performance for the final pitch or its outcome, leaving the role of preceding pitches insufficiently examined. To address this issue, this study conducted a machine learning-based analysis...
AdamW is a default optimizer for deep learning, but its moment states add two parameter-sized buffers to training memory, increasing the cost of large-scale pretraining. We propose Gefen, a memory-efficient optimizer that automatically shares second-moment estimates across parameter blocks and quantizes the first momen...
State-of-the-art GRPO-style methods for speech-aware large language model post-training suffer from coarse credit assignment, broadcasting the same terminal-reward advantage to every token in a response. This ignores useful structure within rollout batches, where speech-conditioned completions often share prefixes befo...
Argyrios Gerogiannis, Yekaterina Yegorova, Mark Hasegawa-Johnson et al.· 0 citations
As video generation models like Veo 3.1 and LTX-2 advance, their ability to accurately represent diverse global cultures remains a critical yet understudied frontier. Current metrics, such as VideoScore, only measure visual quality but offer no mechanism for assessing cultural faithfulness. Consequently, a model that r...
Anku Rani, Wei Dai, Shravan Nayak et al.· 0 citations
Synthetic histopathology image generation addresses patient-privacy concerns and the growing data demands of foundation models. Existing state-of-the-art histopathology generative models use pretrained Vision Foundation Models (VFMs) as conditioning signals. We show this yields conditioning-dominated diversity: on TCGA...
Won June Cho, Daeky Jeong, Hyeongyeol Lim et al.· 0 citations
Vision and language models (VLMs) hold immense promise to transform biomedical imaging workflows, from detecting lesions in chest X-rays to profiling cellular features in microscopy. Realizing this potential, however, requires robust and fine-grained visual perception. Models need to correctly interpret subtle features...
Ryan D'Cunha, Alejandro Lozano, Xiaoxiao Sun et al.· 0 citations
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
