Analysis of the pre-trained embedding geometry of a small sentence transformer (SBERT) and classic SLM reveals that pre-trained embedding geometry is associated with classification performance and reveals a counterintuitive finding that a structured input that would help a human reader does not improve the SLM performa...
Emma Ceccherini, Daniel Lawson, Anjulika Salhan· 0 citations
This work formalizes the hybrid LLM-planner and RL-controller architecture as a Goal-Augmented Markov Decision Process and shows that when the LLM per-state progress score is used as a bounded potential function, the resulting shaping term preserves the optimal policy set even when the LLM scores are inaccurate.
Christophe D. Hounwanou, John Emeka Eze, Yaé Ulrich Gaba· 1 citation
This paper investigates how multilingual medical adaptation reshapes the internal representations of Whisper models through layer-wise encoder analysis, and shows that English medical fine-tuning produces the dominant encoder shift, whereas multilingual continuation largely preserves the adapted representation space.
Souranil Kahali, Rituparna Bose, Abner Hernandez et al.· 0 citations
Verifiable Latent Alignments (VLA), an activation-aware framework for monitoring and steering these private communication channels, is introduced and shows that the evaluated private channel attacks can be monitored without training the primary monitor on attack examples and mitigated when matched counterfactual access...
Ramneet Kaur, Pradyumna Chari, Ramesh Raskar et al.· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
To efficiently generate adversarial examples, a gradient-based attack method is proposed that performs optimization exclusively on the vision encoder of the VLM rather than on the entire multimodal architecture, which significantly reduces the computational cost and resource requirements of the attack while maintaining...
Ilan Zini, B. Addad, Katarzyna Kapusta· 1 citation
TestifAI, a deep learning testing framework for efficient and accurate estimation of robustness against combinations of perturbations, is proposed and partial model tomography is introduced, a novel approach to reconstructing model behaviour in a multi-perturbation space from tests that apply only a small number of per...
Arooj Arif, T. Hartung, E. Botoeva et al.· Proceedings of the 2026 IEEE...· 1 citation
SDDL is introduced, a neuro-symbolic framework that translates natural-language scheduling problems into compact, solver-aligned representations of tasks, resources, constraints, and objectives, while delegating low-level modeling and search to a deterministic compiler and external solver.
The Membership Decoding method is a plug-and-play replacement for standard decoding that requires only black-box token probabilities, and a new token-level membership inference method is proposed by leveraging likelihood from reference models, shifting the generation from the original token distribution to the member t...
Zi-Tai Chen, Reza Shokri· Proceedings on Privacy Enhan...· 0 citations
