We propose a multimodal latent diffusion model that jointly synthesizes volumetric magnetic resonance imaging (MRI) and tabular clinical data within a shared latent space via cross-attention. This approach enables coherent joint representation learning of MRI and tabular modalities for generative modeling. Our model ut...
Daniel Mensing, Jan Kapar, Jochen G. Hirsch et al.· 0 citations
The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value across all states. State-dependent discounting is a natural way to adapt temporal credit assignment to local state structure, but naively learni...
Yaomin Wang, Jianting Pan, Ran Tian et al.· 0 citations
This work proposes Selective Successor Eligibility Traces (S-trace), an critic-free eligibility trace method that enables more effective credit assignment and establishes an upper bound on its discrepancy from the raw eligibility traces-based policy gradient estimator.
Chao-Li Mou, Xin-Ning Chen, Zhan Zhuang et al.· 5 citations
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench, a suite of 5,500 test case...
Dasol Choi, Eugenia Kim, Jaewon Noh et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Audio description (AD) narrates visual elements in video for blind and low-vision audiences. Recent work has shown that giving novice describers an AI-generated draft to start from helps produce higher-quality AD and lowers the barrier to entry. What remains an open question is how draft quality shapes the editing proc...
Lana Do, Shasta Ihorn, Charity M. Pitcher-Cooper et al.· 0 citations
Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-resource settings remains poorly understood. We evaluate four parsers---the Biaffine LSTM, Stack-Pointer Network, AfroXLMR-large, and RemBERT---across twelve typologica...
Kevin Guan, Happy Buzaaba, Christiane Fellbaum· 0 citations
Scientific discovery is an extended process of ideation -- surveying prior work, forming hypotheses, and refining reasoning -- yet existing LLM research agents treat this phase as a brief preamble despite its central role in research. We introduce SciSense, a sensemaking-grounded framework that operationalizes ideation...
James Mooney, Zae Myung Kim, Young-Jun Lee et al.· 0 citations
Distillation via reasoning traces exposes frontier models to adversarial third parties, who can bypass their guardrails and misappropriate their capabilities. Existing antidistillation defenses perturb the teacher's sampling distribution to hinder downstream student learning, but these perturbations also degrade the tr...
Max Hartman, Vidhata Jayaraman, Moulik Choraria et al.· 0 citations
Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning decisions should remain consistent with the model's own perception. We present a comparative study of cross-stage context passing on DriveLM-nuScenes using t...
Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pretraining Seeding (SPS), a threat model in which adversaries distribute small amounts of poisoned content across stealth w...
Harsh Kumar, Rahul Maity, Tanmay Joshi et al.· 0 citations
Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution-path information to guide prompt construction, which is often insufficient for complex software systems with rich inter-class dependencies,...
Guancheng Wang, Qinghua Xu, Lionel C. Briand et al.· 0 citations
