StructSynth is introduced, a framework that treats a dependency graph as a generation plan---determining the generation order, conditioning context, and scope of each black-box LLM call, and achieves state-of-the-art downstream utility and the best privacy-risk ranking among fourteen compared generators in low-data settings.
Si-Yi Liu, Yujian Zheng, Haoyang Li et al.· 0 citations
This work introduces multi-variate parallel attention (MVPA), a novel self-attention mechanism that disentangles content, temporal, and spatial attention, enabling flexible, generalizable, and efficient modeling of time-series data with varying channel counts and configurations.
F. Carzaniga, Michael Hersche, Abu Sebastian et al.· arXiv.org· 3 citations
This work proposes a novel framework that Recycles Few-shot examples to verify LLM outputs (ReFeri), which combines a forward confidence score with a backward reconstruction penalty to select candidates that follow few-shot guidance while avoiding demonstration-specific overfitting.
Dongseo Lee, Jimyung Hong, Dongyoung Kim et al.· arXiv.org· 6 citations
The strong association between BrainAGE, vascular risk factors, and post-stroke recovery highlights its potential for personalized prognostic modeling in stroke care.
Vincent Roca, Marc Tommasi, Paul Andrey et al.· NeuroImage· 3 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
EquiReg formalizes manifold-preferential equivariant functions that exhibit low equivariance error for on-manifold samples and high error for off-manifold ones, thereby guiding sampling toward symmetry-preserving regions of the solution space.
An attack is proposed, FAB (Finetuning-activated Adversarial Behaviors), which compromises an LLM via meta-learning techniques that simulate downstream finetuning, explicitly optimizing for the emergence of adversarial behaviors in the finetuned models.
Thibaud Gloaguen, Mark Vero, Robin Staab et al.· 4 citations
It is shown that RSPO with appropriate regularizers can substantially improve the length-controlled win rate on AlpacaEval-2 across a range of base models, while also achieving consistently superior performance on Arena-Hard, MT-Bench, ArmoRM, and response diversity.
Xiaohang Tang, Sangwoong Yoon, Seongho Son et al.· 6 citations· ⚡1
It is established that gradient-based training can induce an implicit regularization towards low rank for several neural network architectures, and it is demonstrated empirically that this phenomenon may facilitate an explanation of generalization over natural data.
This study unveils the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments, and proposes a novel black-box attack (SUB-PLAY) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability.
Oubo Ma, Yuwen Pu, L. Du et al.· Conference on Computer and C...· 16 citations
From an industrial code-generation improvement effort, a maintainer's perspective on why this work is hard in practice is offered, distilling three recurring challenges, zero-sum mixture design, yield as the binding metric, and end-to-end integration under uncertainty, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware.
Gopi Krishnan Rajbahadur, A. M. Ebrahimi, Boyuan Chen et al.· 0 citations
AutoSciRub is presented, an evaluation-first framework that induces a task-specific executable rubric before research execution and uses it to guide execution, criterion-level verification as well as iterative revision.
Xuehai Wang, Hao-Wei Qin, Tong-Xin Liu et al.· 0 citations
Experiments show that knowledge-aligned SFT can reduce factual hallucinations on WildHalu and Biography while largely preserving general capabilities and confirm that SFT targets beyond the base model's knowledge drive hallucination behavior.
AR Becker, Jakob Kemmler, David Thulke et al.· 0 citations
