Posters

PepGLAD, a novel generative model, revolutionizes full-atom peptide design by leveraging geometric latent diffusion to significantly enhance peptide diversity and binding affinity.

FUGAL: a groundbreaking graph alignment method surpassing state-of-the-art accuracy without compromising efficiency by directly aligning adjacency matrices.

FUG: A new graph contrastive pre-training strategy solves GNN transferability issues across datasets with diverse node features, achieving comparable performance to retraining while significantly impr…

FSP-LAPLACE efficiently integrates interpretable function-space priors into Bayesian deep learning via a novel Laplace approximation, significantly improving uncertainty estimates and model performanc…

Boost VLM performance with ZERO: a simple, fast Test-Time Adaptation method requiring only a single forward pass and exceeding state-of-the-art accuracy!

Frozen-DETR boosts object detection accuracy by integrating frozen foundation models as feature enhancers, achieving significant performance gains without the computational cost of fine-tuning.

LLMs’ in-context learning surprisingly arises from simple co-occurrence patterns in unstructured data, but positional information is key for complex tasks; ICL fails when patterns are unseen or fixed.

Diffusion models, while excelling in image generation, are vulnerable to data poisoning. This paper demonstrates a BadNets-like attack’s effectiveness against diffusion models, causing image misalign…

α-NeuS: A novel method for neural implicit surface reconstruction that accurately reconstructs both transparent and opaque objects simultaneously by leveraging the unique properties of distance fields…

TTCT translates natural language constraints into effective training signals for safe reinforcement learning, enabling agents to learn safer policies with lower violation rates and zero-shot transfer …

Channel Clustering Module (CCM) boosts time series forecasting accuracy by intelligently grouping similar channels, improving model performance and generalization.

Boost time series forecasting accuracy by integrating news data and LLM-based agents!

A novel framework extends optimization algorithms from linear/quadratic functions to a broader class of ‘upper-linearizable’ functions, providing a unified approach for concave and DR-submodular optim…

TAGI, a novel method, generates task-specific adapters from instructions, enhancing LLM cross-task generalization by using knowledge distillation and a two-stage hypernetwork training process.

STONE, a novel multi-view subspace clustering framework, enhances scalability and accuracy by introducing an anchor dictionary learning mechanism and triple information enhancement.

Researchers developed a self-supervised learning framework to create high-dynamic-range 3D Gaussian Splatting (3DGS) models from noisy raw images, significantly improving reconstruction quality and sp…

This paper introduces a novel geometric approach to concept-based representation learning, provably recovering interpretable concepts from diverse data without strict causal assumptions or many interv…

Learn unbiased molecular dynamics from limited biased data using a novel infinitesimal generator approach; accurately estimating eigenfunctions and eigenvalues even with suboptimal biasing.

ODIN, trained on a million 360° videos (360-1M), generates realistic novel views and reconstructs 3D scenes from single images.

FRIEREN: a novel video-to-audio generation network using rectified flow matching achieves state-of-the-art performance by improving audio quality, temporal alignment, and generation efficiency.