Posters

Federated Hardware-Prompt Learning (FedHP) enables robust cross-hardware SCI training by aligning inconsistent data distributions using a hardware-conditioned prompter, outperforming existing FL metho…

LLMs struggle to cooperate sustainably; GOVSIM reveals this, showing communication and ‘universalization’ reasoning improve outcomes.

This paper accelerates second-order optimization in CNNs by 4.5x, using a novel tensor network representation that simplifies convolutions and reduces memory overhead.

In symmetric zero-sum games, no-swap-regret dynamics guarantee strong convergence to Nash Equilibrium under symmetric initial conditions, but this advantage disappears when constraints are relaxed.

Gradient-based methods for solving large zero-sum games achieve polynomial smoothed complexity, demonstrating efficiency even in high-precision scenarios without condition number dependence.

Split Federated Learning (SFL) convergence is analyzed for heterogeneous data, achieving O(1/T) and O(1/√T) rates for strongly convex and general convex objectives respectively. The study also extend…

ControlSynth Neural ODEs (CSODEs) guarantee convergence in complex dynamical systems via tractable linear inequalities, improving neural ODE modeling.

ControlMLLM: Inject visual prompts into MLLMs via learnable latent variable optimization for training-free referring abilities, supporting box, mask, scribble, and point prompts.

New PAC-Bayes bound controls multiple error types simultaneously, providing richer generalization guarantees.

AI decision support systems can unintentionally harm users; this paper introduces a novel framework to design systems that minimize this counterfactual harm, balancing accuracy and user well-being.

Continuous Relaxation Annealing (CRA) significantly boosts unsupervised learning-based solvers for combinatorial optimization by dynamically shifting from continuous to discrete solutions, eliminating…

NeuroMOP, a novel neural principle, maximizes neural variability while ensuring reliable performance in recurrent neural networks, offering new insights into brain function and artificial intelligence…

Self-supervised learning models can now better predict primate IT neural responses by preserving structured variability to input transformations, improving alignment with biological visual perception.

Contrastive losses unlock efficient fitness function modeling by leveraging the ranking information inherent in global epistasis, significantly improving accuracy and data efficiency in protein engine…

This research introduces a hypothesis test and a contrastive dimension estimator to identify unique foreground information in contrastive datasets, advancing the field of dimension reduction.

Symile: A simple model-agnostic approach for learning representations from unlimited modalities, outperforming pairwise CLIP by capturing higher-order information.

CONTRAST efficiently adapts multiple source models to dynamic data distributions by optimally weighting models and selectively updating only the most relevant ones, achieving robust performance withou…

Repeated contracts with learning agents are optimized by a simple dynamic contract: initially linear, then switching to zero-cost, causing the agent’s actions to ‘free-fall’ and yield non-zero rewards…

LeapAD, a novel autonomous driving paradigm, uses a dual-process architecture mirroring human cognition to achieve continuous learning and improved adaptability. Employing a VLM for efficient scene u…

Koodos: a novel Koopman operator-driven framework that tackles Continuous Temporal Domain Generalization (CTDG) by modeling continuous data dynamics and learning model evolution across irregular time …