Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted external content. This makes them a prime target for prompt injection attacks, in which an adversary injects malicious instructions in that content to hijack the model. Fine-tunin...
Xiaoxue Yang, Bozhidar Stevanoski, Matthieu Meeus et al.· 0 citations
Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics and lead to objective inconsistency, where the global model converges to an incorrect stationary point potentially far from the pursued opti...
Shudi Weng, Chao Ren, Ming Xiao et al.· 0 citations
Chronic wounds affect a large population, particularly the elderly and diabetic patients, who often exhibit limited mobility and co-existing health conditions. Automated wound monitoring via mobile image capture can reduce in-person physician visits by enabling remote tracking of wound size. Semantic segmentation is ke...
Vanessa Borst, Timo Dittus, Tassilo Dege et al.· 0 citations
Retrieval models for recommendation need to account for outcomes such as watch time while searching large item corpora efficiently. We present the Controllable Retrieval Model (CRM), an outcome-conditioned retrieval framework that adds watch time as an input to the user tower. During training, CRM learns to predict the...
Chi Liu, Jiangxia Cao, Rui Huang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Understanding the internal mechanisms of deep neural networks remains a central challenge in machine learning. In computer vision, one promising yet only preliminarily explored approach is feature inversion via inverse networks, which reconstructs images from intermediate representations using trained inverse networks....
Jan Rathjens, Shirin Reyhanian, David Kappel et al.· 0 citations
Generative models guided by text prompts are widely evaluated for fidelity and prompt alignment, yet their ability to produce diverse outputs remains underexplored. Existing diversity metrics such as Vendi and RKE, which are based on the von Neumann and R\'enyi entropies of kernel matrices, were developed for unconditi...
Mohammad Jalali, Azim Ospanov, Amin Gohari et al.· 0 citations
Originally introduced in game theory, Shapley values have emerged as a central tool in explainable machine learning, where they are used to attribute model predictions to specific input features. However, computing Shapley values exactly is expensive: for a general model with $n$ features, $O(2^n)$ model evaluations ar...
Large language models (LLMs) are increasingly used to simulate students at different mastery levels to generate synthetic training data and stress-test tutoring systems. Existing approaches primarily leverage an LLM to answer questions or perform tests while instructing it to simulate various skill levels. However, LLM...
Yuan An, Emily Wang, Benjamin Wang et al.· 0 citations
User feedback offers natural supervision for persistent LLM improvement, but a single message may support multiple behavioral changes with different scopes of generalization. We introduce SLIFT, a selective self-learning framework built on a task-relative view of user feedback. SLIFT decomposes each feedback message in...
Xuancheng Li, Haitao Li, Yujia Zhou et al.· 0 citations
In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy. Much of clinical reasoning relies on the patient encounter, a dialogue in which a clinician elicit...
Valentin Li\'evin, Samuel Schmidgall, Tim Strother et al.· 0 citations
Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler, making automated attribution increasingly important. We introduce Who&When Pro, a large-scale benchmark for automated failure attribution in agentic systems. Using a stri...
Jiale Liu, Huajun Xi, Shaokun Zhang et al.· 0 citations
Reusing evaluator-derived step rewards across evaluation channels raises a measurement question: does the assigned direction remain stable? We define Agent Step Value (ASV) as a channel-indexed before/after target-margin gain and identify the state-by-channel interaction from a matched 2x2 design. Across frozen PubMed...
