Posters

DenseFormer enhances transformers by adding a depth-weighted averaging step, improving data efficiency and outperforming baselines in memory and inference time without increasing model size.

Boosting multimodal LLMs, the Dense Connector efficiently integrates multi-layer visual features for significantly enhanced performance.

Boost associative memory capacity without extra parameters! DrDAM uses random features to approximate Dense Associative Memories, enabling efficient memory addition and retrieval.

Denoising Diffusion Path (DDPath) uses diffusion models to dramatically reduce noise in attribution methods for deep neural networks, leading to clearer explanations and improved quantitative results.

DeNetDM uses network depth modulation to automatically debiase image classifiers without bias annotations or data augmentation, improving accuracy by 5%.

Biologically-inspired Dit-CNNs leverage quadratic neuron integration to capture data correlation, achieving state-of-the-art performance on image classification benchmarks.

Vision’s Mamba model demystified: Researchers unveil its surprising link to linear attention, improving efficiency and accuracy through design enhancements.

DeMo: Decoupling motion forecasting into directional intentions and dynamic states for improved autonomous driving.

Large language models struggle to generalize knowledge when facing seemingly simple reversals, a phenomenon termed the ‘reversal curse.’ This study reveals that this limitation is strongly linked to t…

DeltaDock: a novel two-stage framework revolutionizes molecular docking by improving accuracy and reliability, achieving a 300% increase in success rate compared to the prior state-of-the-art in blind…

DeltaDEQ accelerates deep equilibrium model inference by 73-84% via a novel ‘heterogeneous convergence’ exploitation technique, maintaining accuracy.

Delta-CoMe: Training-free mixed-precision delta compression boosts LLM deployment efficiency.

DEL: Learns 3D particle dynamics from 2D images via physics-informed neural rendering, exceeding existing methods’ accuracy and robustness.

Vision-language models (VLMs) memorize training data, impacting generalization. This paper introduces ‘déjà vu memorization,’ a novel method measuring this, revealing significant memorization even in…

DeiSAM uses large language models and differentiable logic to achieve highly accurate image segmentation using complex, context-dependent descriptions.

DEFT: A novel method efficiently fine-tunes diffusion models for conditional generation via a generalized h-transform, achieving state-of-the-art performance with significant speed improvements.

DeformableTST: a new Transformer model for time series forecasting that surpasses existing methods by reducing over-reliance on patching, enhancing performance and adaptability.

AdvUnlearn enhances diffusion model robustness against adversarial attacks during concept erasure by integrating adversarial training, improving the trade-off between robustness and model utility.

DeepStack: Stacking visual tokens boosts LMMs efficiency and performance!

DeepLag improves fluid prediction by uniquely combining Lagrangian and Eulerian perspectives, tracking key particles to reveal hidden dynamics and improve prediction accuracy.