Posters

DrilDICE robustly tackles covariate shift in offline imitation learning by using a stationary distribution correction and a distributionally robust objective, significantly improving performance.

Researchers propose a simple yet effective clustering-based adaptive margin loss to mitigate biases inherited by black-box feature extractors in image classification tasks.

Proactive Defensive Backdoor (PDB) thwarts malicious backdoors by injecting a hidden defensive backdoor during training, suppressing attacks while maintaining model utility.

MiSO: a novel closed-loop brain stimulation framework optimizes stimulation parameters to achieve desired neural population activity states, overcoming limitations of current methods by merging data a…

INTEGER: a novel unsupervised point cloud registration method leveraging feature-geometry coherence for reliable pseudo-label mining and density-invariant feature learning, achieving state-of-the-art …

MinUCB and LA-MinUCB, novel local Bayesian optimization algorithms, replace gradient descent with UCB minimization for efficient, theoretically-sound local search.

Minimax-optimal, computationally efficient algorithms are proposed for distributionally robust offline reinforcement learning, addressing challenges posed by function approximation and model uncertain…

MiniCache: A novel approach to drastically reduce LLM KV cache memory footprint.

MINI-SEQUENCE TRANSFORMER (MST) drastically reduces memory usage in LLM training by processing mini-sequences iteratively, enabling training with 12-24x longer sequences than conventional methods with…

MindMerger efficiently boosts LLM reasoning in non-English languages by merging LLMs with external multilingual language understanding capabilities, achieving significant accuracy improvements, especi…

LLMs’ spatial reasoning abilities are boosted by visualizing their thought processes via ‘Visualization-of-Thought’ prompting, significantly improving performance on navigation and tiling tasks.

Data balancing in machine learning can hurt fairness and robustness; this paper reveals when and why, offering solutions for safer AI.

AI bias amplification in decision-making is uncovered, showing how fair prediction scores can become discriminatory after thresholding, urging stronger regulatory oversight.

CoPA improves cross-domain few-shot learning by adapting separate transformations for prototype and image embeddings, significantly enhancing performance and revealing better representation clusters.

MimicTalk generates realistic, expressive talking videos in minutes using a pre-trained model adapted to individual identities.

IMAX-PPO: A novel multi-agent RL algorithm leveraging imitation learning to predict opponent actions, achieving superior performance in complex games.

MILP-StuDio generates high-quality mixed-integer linear programming instances by preserving crucial block structures, significantly improving learning-based solver performance.

MIDGARD: Generate high-quality, simulatable 3D articulated assets with enhanced control and interpretability using a novel diffusion-based framework.

LLMs struggle with graph recall, exhibiting biases like favoring triangles and underperforming compared to humans; advanced models show striking domain dependence.

MICROADAM: A new Adam optimizer variant dramatically cuts memory usage for training large language models without compromising accuracy or provable convergence.