Posters

Linear transformers efficiently learn sparse contextual bigrams by leveraging both in-context and global information, achieving polynomial sample complexity.

Actionable AI agents are trained efficiently via a novel framework, VPDD, which uses discrete diffusion to pre-train on massive human videos, and fine-tunes on limited robot data for superior multi-ta…

This work presents a computationally efficient algorithm that robustly learns a single neuron despite adversarial label noise and distributional shifts, providing provable approximation guarantees.

Animates diverse garments realistically from a single cloth’s trajectory using a disentangled learning approach and Energy Unit Network (EUNet).

3D surface reconstruction revolutionized: PEIF leverages patch-level pose-invariant representations and 3D patch-level equivariance for state-of-the-art accuracy, even with varied poses and datasets!

De-focus Attention Networks achieve comparable performance to 2D non-causal models using 1D causal visual representation, solving the ‘over-focus’ issue in existing 1D causal vision models.

Two-parameter models can surprisingly learn high-dimensional targets with near-perfect accuracy using gradient flow, challenging the need for high-dimensional models.

Active learning for video captioning is enhanced by a novel algorithm that prioritizes ’learnability’, diversity, and uncertainty to address annotation inconsistency.

LB-CL: A novel parameter-efficient continual learning method for LLMs that boosts performance and reduces forgetting by leveraging parametric knowledge transfer and maintaining orthogonal low-rank sub…

LCM: a novel, locally constrained, compact point cloud model surpasses Transformer-based methods by significantly improving performance and efficiency in various downstream tasks.

LCGen: A novel method for view-consistent text-to-3D generation, resolving the ‘Janus Problem’ by strategically using low-certainty priors to align viewpoints and optimize the generation process.

Layer-Adaptive STate pruning (LAST) optimizes deep state space models by efficiently reducing state dimensions, improving performance and scalability without retraining.

AI now draws almost as well as humans, thanks to novel latent diffusion model regularizations that mimic human cognitive biases.

Latent Plan Transformer (LPT) solves long-term planning challenges in reinforcement learning by using latent variables to connect trajectory generation with final returns, achieving competitive result…

LaPael improves LLM knowledge injection by applying learned noise to early layers, enabling diverse and efficient knowledge updates without repeated external model usage.

Latent Neural Operator (LNO) dramatically improves solving PDEs by using a latent space, boosting accuracy and reducing computation costs.

Humans autonomously select goals based on both observed and latent learning progress, impacting goal-conditioned policy learning.

Latent Functional Maps (LFM) offers a novel spectral framework for comparing, aligning, and transferring neural network representations, boosting downstream task performance and interpretability.

New CRL algorithms guarantee global convergence, handle multiple constraints and various risk measures, improving safety and robustness in AI.

Generalized Frank-Wolfe algorithm achieves fast last-iterate convergence for constrained monotone variational inequalities, even with noisy data.