Posters

Diffusion-Inspired Truncated Sampler (DITS) revolutionizes text-video retrieval by progressively aligning embeddings and enhancing CLIP embedding space structure, achieving state-of-the-art results.

Diffusion-DICE: A novel offline RL method using in-sample diffusion guidance for optimal policy transformation, achieving state-of-the-art performance.

QVPO, a novel online RL algorithm, leverages diffusion models’ multimodality to boost performance in continuous control tasks, overcoming limitations of unimodal policies.

DiCuRL uses diffusion models to generate challenging yet achievable RL training curricula, outperforming nine state-of-the-art methods.

Unsupervised OOD detection gets a boost with a diffusion-based approach that leverages multi-layer semantic feature reconstruction for improved accuracy and speed.

Twigs: a novel score-based diffusion framework using multiple co-evolving flows and loop guidance for superior conditional graph generation.

Diff-Tuning: a simple yet effective approach transfers pre-trained diffusion models to various downstream tasks by leveraging the ‘chain of forgetting’ phenomenon, improving transferability and conver…

Diffusion Spectral Representation (Diff-SR) enables efficient reinforcement learning by extracting sufficient value function representations from diffusion models, bypassing slow sampling and facilita…

DP-Attacker unveils diffusion-based policy vulnerabilities by crafting effective adversarial attacks, significantly impacting robot safety and paving the way for more robust AI.

DiffusionPID unveils the secrets of text-to-image diffusion models by decomposing text prompts into unique, redundant, and synergistic components, providing insights into how individual words and thei…

Diffusion-of-Thought (DoT) boosts reasoning in diffusion language models by enabling parallel reasoning steps, outperforming larger autoregressive models in speed and accuracy.

Diffusion models are certifiably robust classifiers due to their inherent O(1) Lipschitzness, a property further enhanced by generalizing to noisy data, achieving over 80% certified robustness on CIFA…

Diffusion Forcing merges next-token prediction and full-sequence diffusion for superior sequence generation.

DACER, a novel online RL algorithm, uses diffusion models to learn complex policies and adaptively balances exploration-exploitation via entropy estimation, achieving state-of-the-art performance on M…

DiffuserLite: a super-fast diffusion planning framework achieving real-time performance (122Hz).

DiffuPac generates realistic adversarial network packets evading NIDS detection without requiring specific NIDS knowledge, outperforming existing methods.

DiffuLT uses a novel diffusion model to generate balanced training data from imbalanced datasets, achieving state-of-the-art results in long-tailed image recognition without external knowledge.

DiffuBox refines 3D object detection using a novel diffusion-based approach, significantly improving accuracy across various domains by refining bounding boxes based on surrounding LiDAR point clouds.

DiffPO: A causal diffusion model learns outcome distributions, offering reliable medical interventions.

DiffPhyCon uses diffusion models to generate near-optimal control sequences for complex physical systems, outperforming existing methods by simultaneously optimizing a generative energy function and c…