There is a fundamental contradiction between the desire for models that can generalize, and models that can continuously adapt to recent input with changing statistics. These conditions, captured in few-shot and continual learning settings, can bias or disrupt learned representations. This harms generalization to a bro...
Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries. We study this question through pain, using TAME-Pain, which contains pain-neutral Harvard sentences and spoken pain ratings recorded at different self-repor...
Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts. Existing work elicits assistant personas through persona prompting or finetuning on persona-conditioned generations. However, persona descriptions alone do not identify what to change or preserve in a particular respon...
Diffusion and flow matching models offer scalable approaches to generating crystalline materials, molecular conformers, and protein-ligand complexes. However, satisfying crystallographic symmetry, structural geometry, and accurate stereochemistry remains challenging. Satisfying these requirements calls for corrections...
Peng-Fei Cai, K. Jäger, Utkarsh Utkarsh et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Joint-embedding predictive architectures (JEPAs) learn to predict representations rather than pixels, offering a compact way to model how visual scenes evolve. We ask whether this predictive objective improves closed-loop control when a vision-language-action (VLA) policy already uses V-JEPA features. We call our JEPA-...
Rufeng Xiao (VLA Research Team, Synthoid.ai), Ruihao Xiao (VLA Research Team et al.· 0 citations
AI agents now install packages, call model APIs with their operators'keys and change code in repositories that deploy to production. The network, credentials and write access they need are also how they can leak data, steal a key or change a system nobody approved. Sandboxes contain an agent but leave little evidence o...
Decision models offered resource advantages alongside lower peak accuracy; generative large language model configurations offered resource advantages alongside lower peak accuracy; selecting models for medical workflows requires considering probability quality and repeatability together with accuracy and the resources...
O. Freyer, D. Glauert, M. Hofmann et al.· 0 citations
This work proposes user behaviour fuzzing, a guided search over plausible user behaviours that can lead a model to violate its role specification, and introduces RoleFUZZER, a framework that adapts coverage-guided fuzzing from software testing to operationalise the search.
Kshitish Ghate, Michael Stephen Saxon, Tadayoshi Kohno et al.· 0 citations
Machine unlearning aims to reproduce the behavior of a model trained without designated data. For probabilistic decision models, this target also depends on the candidate options supplied at inference. We introduce DecisionUnlearn-Bench, an empirical framework that compares full, unlearned, and retain-only models acros...
Analog layout remains largely manual and hard to automate. Generator frameworks such as gLayout express layouts as programs, producing layouts from parameterized, design-rule-aware generators; however, writing such generators still takes expert effort. Large language models (LLMs) could now write generator code, and fr...
Minxing Chu, Anhang Li, Martins Atilla et al.· 0 citations
To solve problems in 3D space rather than merely describe images, multimodal large language models (MLLMs) need 3D spatiotemporal reasoning: reconstructing 3D geometry from occluded 2D views, anticipating physical dynamics, and executing precise, closed-loop actions. Prior studies test passive VQA on static images or s...
Chenglong Shi, Zekai Yuan, Yue Song et al.· 0 citations
Judgment and response signals from open-weight LLMs captured difficulty-related information beyond text representations and offers a practical option for predicting the difficulty of unreleased or high-security test items.
Xiao-Meng Xiong, M. Walker, Yan-Lin Jiang· 0 citations
