Posters

MUN: a novel goal-directed exploration algorithm significantly improves world model reliability and policy generalization in sparse-reward goal-conditioned RL, enabling efficient navigation across div…

Tighter losses than Fenchel-Young losses are presented, refining Fenchel-Young inequalities using the Fitzpatrick function to improve model accuracy while preserving prediction link functions.

Meta-learning a hypernetwork on CutMix-augmented data enables data-efficient and precise correction of vision transformer errors by identifying optimal parameters for fine-tuning.

Surrogate PAC-Bayes Learning (SuPAC) efficiently optimizes generalization bounds by iteratively optimizing surrogate training objectives, enabling faster and more scalable learning for complex models.

CurrMask: a novel curriculum masking paradigm for offline RL, achieving superior zero-shot and fine-tuning performance by dynamically adjusting masking schemes during pretraining, enabling versatile s…

TURTLE: a novel video restoration framework that learns a truncated causal history model for efficient and high-performing video restoration, achieving state-of-the-art results on various benchmark ta…

STRAINER: A new framework enabling faster, higher-quality INR fitting by leveraging transferable features across similar signals, significantly boosting INR performance.

Unlocking complex models’ secrets: New algorithm identifies input interactions using the Möbius Transform, boosting interpretability with surprising speed and accuracy.

Deterministically shaping in-distribution feature space solves OOD detection’s distributional assumption challenge, leading to superior performance.

Language models excel at generating programs for algorithmic tasks, but struggle with soft reasoning. COGEX leverages pseudo-programs and program emulation to tackle these tasks, while COTACS searches…

Boosting complex visual reasoning, a new Iterative and Parallel Reasoning Mechanism (IPRM) outperforms existing methods by combining step-by-step and simultaneous computations, improving accuracy and …

This paper develops efficient algorithms for pricing homogeneous data in online settings, achieving low regret using novel discretization schemes that scale well with data size and number of buyer typ…

Deep learning predicts structural vibrations faster than traditional methods, reducing noise in airplanes, cars, and buildings, as shown by a new benchmark and frequency-query operator network.

Decoupled Token Embedding for Merging (DTEM) significantly improves Vision Transformer efficiency by using a decoupled embedding module for relaxed token merging, achieving consistent performance gain…

Proactive Infeasibility Prevention (PIP) framework significantly improves neural methods for solving complex Vehicle Routing Problems by proactively preventing infeasible solutions and enhancing const…

Learn optimal data-dependent distribution kernels via Maximum Kernel Entropy, eliminating manual kernel selection and boosting performance on various downstream tasks.

AI learns to edit visual programs more accurately using a self-supervised method that combines one-shot program generation with iterative local edits, significantly boosting performance, especially wi…

RL-instructed language models excel at strategic communication in One Night Ultimate Werewolf, demonstrating the importance of discussion tactics in complex games.

Researchers developed Light Decoupling, a novel approach to model 3D facial textures under complex illumination, achieving more realistic and accurate results by decoupling unnatural lighting into mul…

Generative Agent Modeling for Multi-agent Adaptation (GAMMA) improves human-AI cooperation by training AI agents against diverse partners generated from a latent model, enhancing zero-shot coordinatio…