Posters

AdaptiveISP uses reinforcement learning to create a scene-adaptive ISP pipeline that dynamically optimizes for object detection, surpassing existing methods in accuracy and efficiency.

Adaptive STORM achieves optimal convergence rates for stochastic optimization of non-convex functions under weaker assumptions, eliminating the need for bounded gradients or function values and removi…

AdaptiveSoftmax: Achieve 10x+ speedup in softmax computation via adaptive sampling!

Adaptive gradient descent methods are improved by leveraging local curvature information for entirely adaptive algorithms without added computational cost, proving convergence with only local Lipschit…

Adaptive Preference Scaling boosts Reinforcement Learning from Human Feedback by using a novel loss function that adapts to varying preference strengths, resulting in improved policy performance and s…

Adaptive Passive-Aggressive framework with Side information (APAS) significantly boosts online regression accuracy by dynamically adjusting thresholds and integrating side information, leading to supe…

Adaptive Layer Sparsity (ALS) revolutionizes large language model (LLM) compression by intelligently pruning less important layers, achieving significant size reduction without performance loss. It o…

Adaptive labeling minimizes uncertainty in out-of-distribution model evaluation by strategically selecting which data points to label, leading to more efficient and reliable assessments.

AIRS framework, guided by Evidential Q-learning, dynamically balances exploration and exploitation to achieve superior dense object detection accuracy by adaptively selecting important regions.

GVFExplorer: An adaptive behavior policy efficiently learns multiple GVFs by minimizing return variance, optimizing data usage and reducing prediction errors.

Adaptive experimentation tackles confounding in online A/B tests using encouragement designs and a novel linear bandit approach, achieving near-optimal sample complexity.

Adaptive Domain Learning (ADL) efficiently trains a cross-domain RAW image denoising model using limited target data and existing source data by intelligently discarding harmful source data and levera…

Adaptive Depth Networks with Skippable Sub-Paths: Train once, deploy efficiently! This paper proposes a novel training method to create adaptive-depth networks, enabling on-demand model depth selectio…

New adaptive second-order optimistic methods for minimax optimization achieve optimal convergence without line search, simplifying updates and improving efficiency.

Q-Aided Conditional Supervised Learning (QCS) effectively combines the stability of return-conditioned supervised learning with the stitching ability of Q-functions, achieving superior offline reinfor…

Score-based diffusion models are improved by a novel coefficient design, enabling efficient adaptation to unknown low-dimensional data structures and achieving a convergence rate of O(k²/√T).

FG-DMs revolutionize image synthesis by jointly modeling image and condition distributions, achieving higher object recall and enabling flexible editing.

Ctrl-G: A neuro-symbolic framework enables adaptable control of LLM generation by combining any LLM with a Hidden Markov Model (HMM), ensuring outputs adhere to logical constraints specified as determ…

AdaPKC upgrades PeakConv for superior radar semantic segmentation by dynamically adjusting its receptive field, outperforming current state-of-the-art methods.

AdaNovo tackles data biases in de novo peptide sequencing by using Conditional Mutual Information, significantly improving PTM identification and overall accuracy.