Posters

Yo’LLaVA personalizes Large Multimodal Models (LMMs) to converse about specific subjects using just a few images, embedding concepts into latent tokens for efficient and effective personalized convers…

xMIL-LRP: Enhanced explainable AI for multiple instance learning in histopathology, boosting model transparency and enabling new knowledge discovery.

XMask3D uses cross-modal mask reasoning to achieve state-of-the-art open vocabulary 3D semantic segmentation by aligning 2D and 3D features at the mask level, resulting in precise segmentation boundar…

Worst-case offline RL guarantees near-optimal policy performance without data support assumptions, achieving a sample complexity bound of O(ε⁻²).

WorldCoder: an LLM agent builds world models via code generation and interaction, proving highly sample-efficient and enabling knowledge transfer.

WizardArena simulates offline chatbot arena battles to efficiently post-train LLMs, dramatically reducing costs and improving model performance.

WISE, a novel dual-memory architecture, solves the impossible triangle of reliability, generalization, and locality in lifelong LLM editing by employing a side memory for knowledge updates and a route…

WINGS: A novel multimodal LLM combats ’text-only forgetting’ by using complementary visual and textual learners, achieving superior performance on text-only and visual tasks.

WildGaussians enhances 3D Gaussian splatting for real-time rendering of photorealistic 3D scenes from in-the-wild images featuring occlusions and appearance changes.

Wild-GS achieves real-time novel view synthesis from unconstrained photos by efficiently adapting 3D Gaussian Splatting, significantly improving speed and quality over existing methods.

Wide two-layer neural networks can generalize well from mislabeled adversarial examples because adversarial perturbations surprisingly contain sufficient class-specific features.

Deep learning’s learning rate warmup improves performance by allowing larger learning rates, pushing networks to better-conditioned loss landscape areas.

Adam’s superiority over SGD in Transformer training is explained by the ‘block heterogeneity’ of the Hessian matrix, highlighting the need for adaptive learning rates.

Metric backbone graph sparsification surprisingly preserves community structure, offering an efficient and robust method for analyzing large networks.

FedPart boosts federated learning by updating only parts of the network, solving the layer mismatch problem, and achieving faster convergence with higher accuracy.

Weight decay’s role in modern deep learning is surprisingly multifaceted, impacting optimization dynamics rather than solely regularization, improving generalization and training stability.

Visually-grounded Language Models (VLMs) surprisingly underperform in image classification. This study reveals that this is primarily due to a lack of sufficient classification data during VLM trainin…

Researchers developed a causally-motivated approach for ranking agents based on their gaming propensity, addressing the challenge of identifying ‘worst offenders’ in strategic classification settings.

Unlocking personalized image retrieval and segmentation, a novel approach uses pre-trained text-to-image diffusion models to surpass supervised methods, addressing limitations of existing self-supervi…

LLMs learn tasks via in-context learning, but the task recognition location is unknown. This paper reveals that LLMs transition from task recognition to task performance at specific layers, enabling s…