Posters

ZoDiac: a novel image watermarking framework leveraging pre-trained stable diffusion models for robust, invisible watermarks resistant to state-of-the-art attacks.

Boosting machine learning model accuracy in privacy-preserving applications, this research introduces novel noise calibration methods directly targeting desired attack risk levels, bypassing conventio…

Atlas3D enhances text-to-3D generation by integrating physics-based simulations, producing self-supporting 3D models for seamless real-world applications.

APM: Asynchronous Perception Machine, a computationally-efficient architecture for test-time training (TTT), processes image patches asynchronously, encoding semantic awareness without pre-training, a…

AsyncDiff accelerates diffusion model inference by 2.8x using asynchronous denoising and model parallelism, maintaining near-perfect image quality.

This paper rigorously analyzes alpha-divergence variational inference, proving its convergence and providing convergence rates, thereby advancing the theoretical foundations of this increasingly impor…

Pattern-BERP, a novel method, boosts biological entity relationship prediction accuracy by 4-23% using association pattern-aware fusion, enhancing interpretability for real-world applications.

Hypergraph-Based Assembly Fuzzy Representation (HAFR) excels at open-set 3D object retrieval by using part-level shapes and fuzzy representations to overcome challenges posed by unseen object categori…

This paper introduces AAA, a novel three-stage decision-based black-box targeted attack against image-to-text models. AAA efficiently generates semantically consistent adversarial examples by asking …

AsCAN, a novel hybrid architecture, achieves superior efficiency and performance in image recognition and generation by asymmetrically combining convolutional and transformer blocks.

Reinforcement learning agents achieve emergent cultural accumulation by balancing social and independent learning, outperforming single-lifetime agents.

Unsupervised Articulated Object Modeling using Conditional View Synthesis learns pose and part segmentation from only two object observations, achieving significantly better performance than previous …

Artemis: A new MLLM excels at video-based referential understanding, accurately describing targets within complex videos using natural language questions and bounding boxes, surpassing existing models…

ART: A novel automatic red-teaming framework reveals safety vulnerabilities in popular text-to-image models by identifying unsafe outputs even from seemingly harmless prompts.

AROMA: Attentive Reduced Order Model with Attention enhances PDE modeling with local neural fields, offering efficient processing of diverse geometries and superior performance in simulating 1D and 2D…

ARKVALE boosts LLM inference efficiency by intelligently evicting and recalling key-value pairs from cache, improving latency and throughput without significant accuracy loss.

Node Injection-based Fairness Attack (NIFA) reveals GNNs’ vulnerability to realistic fairness attacks by injecting a small percentage of nodes, significantly undermining fairness even in fairness-awar…

MMStar benchmark tackles flawed LVLMs evaluation by focusing on vision-critical samples, minimizing data leakage, and introducing new metrics for fair multi-modal gain assessment.

Evidential deep learning’s uncertainty quantification is unreliable; this paper reveals its limitations, proposes model uncertainty incorporation for improved performance.

Cross-Attention-only Time Series Transformer (CATS) outperforms existing models by removing self-attention, improving long-term forecasting accuracy, and reducing computational cost.