Posters

Mecoin: a novel memory module for efficient graph few-shot class-incremental learning, tackles catastrophic forgetting by employing structured memory units and a memory representation adaptation modul…

New unbiased gradient estimator for high-dimensional SDEs drastically reduces computation time without sacrificing estimation accuracy.

This paper introduces a unified ITR estimation framework using covariate balancing weights, achieving significant gains in robustness and effectiveness compared to existing methods.

Autoencoder-like Nonnegative Matrix Co-Factorization (AE-NMCF) enhances student cognitive modeling by accurately estimating knowledge proficiency and predicting exercise performance, leveraging monoto…

This paper provides novel theoretical analyses of utility functions in MORL, characterizing preferences and functions guaranteeing optimal policies.

Elo rating system’s convergence rigorously analyzed via Markov chains under the Bradley-Terry-Luce model, demonstrating competitive learning rates and informing efficient tournament design.

Adaptive algorithm achieves tight regret bounds for infinitely many-armed bandits under generalized rotting constraints, addressing the challenge of decreasing rewards over time.

Accelerated Gradient Method for Bilevel Optimization (AGM-BiO) achieves state-of-the-art convergence rates for simple bilevel optimization problems, requiring fewer iterations than existing methods to…

AccBO: A new accelerated algorithm achieves O(ε⁻³) oracle complexity for stochastic bilevel optimization with unbounded smoothness, significantly improving upon existing O(ε⁻⁴) methods.

Amortized sampling from complex posteriors using diffusion models is achieved via a novel data-free learning objective, Relative Trajectory Balance (RTB). RTB’s asymptotic correctness is proven, offe…

Large-scale transformers achieve grandmaster-level chess play via supervised learning on a new 10M game benchmark dataset, demonstrating impressive generalization beyond memorization.

Amortized Fourier Neural Operators (AM-FNOs) dramatically improve efficiency in solving PDEs by using neural networks for kernel parameterization, achieving up to 31% better accuracy compared to exist…

Accelerate neural network training using ‘amortized eigendecomposition’ – a novel method replacing expensive eigendecomposition with faster QR decomposition while preserving accuracy.

Amortized Decision-Aware BED prioritizes maximizing downstream decision utility by instantly proposing informative experimental designs and inferring decisions, facilitating accurate decision-making.

CAASL: An amortized active intervention design policy trained via reinforcement learning, enabling adaptive, real-time causal graph inference without likelihood access.

AMOR: Adaptable Modular knowledge agent using LLMs, excels with FSM-based reasoning and process feedback, enabling human supervision and domain adaptation.

AmoebaLLM: Instantly create optimally-sized LLMs for any platform!

RFPAR: A novel reinforcement learning-based attack enhances black-box pixel attacks by minimizing randomness and patch dependency, achieving state-of-the-art results in both image classification and o…

AlterMOMA: A novel pruning framework significantly improves camera-LiDAR fusion models by identifying and removing redundant parameters through an alternative modality masking technique, achieving sta…

ALPS: An optimization-based framework achieves state-of-the-art one-shot LLM pruning, significantly reducing test perplexity and improving zero-shot performance.