Posters

FIND, a lightweight transformer interface, seamlessly aligns foundation models’ embeddings for unified image and dataset-level understanding, enabling generalizable, interleaved performance on segment…

InterDreamer: Zero-shot text-guided 3D human-object interaction generation without paired data, achieved via decoupled semantic and dynamic modeling, using LLMs and a physics-based world model.

InterControl: Zero-shot multi-person interaction generation by precisely controlling every joint using only single-person data.

Interactive Deep Clustering (IDC) significantly boosts deep clustering performance by strategically incorporating minimal user interaction to resolve ambiguous sample classifications.

New gradient flow geometry improves MMD-based sampling by teleporting particle mass, guaranteeing global exponential convergence, and yielding superior empirical results.

Hierarchical Human Knowledge-guided MARL (hhk-MARL) framework accelerates large-scale multi-agent training by integrating suboptimal human knowledge, significantly improving performance and scalabilit…

Deep learning framework integrating GNNs and neural ODEs precisely estimates non-reciprocal two-body interactions in mixed-species collective motion, accurately replicating both individual and collect…

Deep metric learning and Coreset integration enables efficient slice-based active learning for 3D medical segmentation, surpassing existing methods in performance with low annotation budgets.

InstructMol, a novel semi-supervised learning algorithm, leverages unlabeled data and an instructor model to significantly improve the accuracy and robustness of molecular property prediction, even wi…

Instruction-Guided Visual Masking (IVM) boosts multimodal instruction following by precisely focusing models on relevant image regions via visual masking, achieving state-of-the-art results on multipl…

Boost LLM performance with INSTRUCTION MODELLING: a simple yet effective instruction tuning method that improves model outputs by over 100% in some cases by applying loss to both instructions and outp…

INSTRUCTG2I: a novel graph context-conditioned diffusion model, generates images from multimodal attributed graphs, addressing challenges in graph size, dependencies, and controllability.

New algorithm improves differentially private estimations by adapting to dataset hardness, enhancing accuracy for variance, classification, and regression tasks.

Instance-optimal private density estimation algorithms, adapting to data characteristics for improved accuracy in the Wasserstein distance, are introduced.

Instance-adaptive prompting significantly improves zero-shot Chain-of-Thought reasoning in LLMs by dynamically selecting prompts tailored to each instance, leading to consistent performance gains acro…

Researchers developed a novel method to inject undetectable backdoors into obfuscated neural networks and language models, even with white-box access, posing significant security risks.

LeTs: Learnable Transformation efficiently initializes variable-sized Vision Transformers by learning adaptable transformations from a compact learngene module, outperforming from-scratch training.

Adaptively initializing multi-service ML systems for diverse users using minimal data, this paper introduces a randomized algorithm achieving near-optimal loss with provable guarantees.

Transformer model initialization dramatically affects whether it reasons or memorizes, impacting performance on compositional tasks.

Deep Equilibrium Models (DEQs) infused into DFT Hamiltonian prediction achieves self-consistency, accelerating large-scale materials simulations.