Posters

CRITICEVAL: A new benchmark reliably evaluates LLMs’ ability to identify and correct flaws in their responses, addressing limitations of existing methods by offering comprehensive and reliable evaluat…

New definitions of differential privacy enable machine learning algorithms to credit sources appropriately, balancing data utility and copyright compliance.

Credal Learning Theory uses convex sets of probabilities to model data distribution variability, providing theoretical risk bounds for machine learning models in dynamic environments.

Credal Deep Ensembles (CreDEs) improve uncertainty quantification in deep learning by predicting probability intervals, enhancing accuracy and calibration, particularly for out-of-distribution data.

CRAYM: Neural field optimization via camera RAY matching enhances 3D reconstruction by using camera rays, not pixels, improving both novel view synthesis and geometry.

LLM-based text embeddings are powerful but lack interpretability. This paper introduces QA-Emb, a novel method that uses an LLM to answer yes/no questions about a text, thereby producing an interpreta…

CoVoMix: Generating human-like, multi-speaker conversations with zero-shot speech synthesis.

COVE: Consistent high-quality video editing achieved by leveraging diffusion feature correspondence for temporal consistency.

A new Covariate Shift Corrected Pearson Chi-squared Conditional Randomization (csPCR) test accurately assesses conditional independence even when data distributions vary between source and target popu…

Coupled Mamba: Enhanced multi-modal fusion via coupled state space model boosts accuracy and efficiency.

COUNTGD: A new multi-modal model counts objects in images using text or visual examples, significantly improving open-world counting accuracy.

This paper proposes a novel method to achieve optimal counterfactual fairness in machine learning models while minimizing predictive performance degradation.

Biologically inspired Counter-Current Learning (CCL) uses dual networks for deep learning, offering comparable performance to other biologically plausible algorithms while enhancing biological realism…

CoSW: a novel conditional sample weighting method for robust smoke segmentation, achieves state-of-the-art results by handling inconsistent noisy labels through a multi-prototype framework.

Coke: A cost-efficient KBQA strategy using LLMs and KGMs, maximizing accuracy while minimizing GPT-4 fees by up to 20.89%

Cost-aware Bayesian optimization gets a boost with the Pandora’s Box Gittins Index, a novel acquisition function that efficiently balances exploration and exploitation while considering evaluation cos…

COSMIC efficiently compresses satellite images via a lightweight encoder and diffusion compensation, enabling practical onboard processing and high compression ratios.

CosAE: a novel autoencoder using learnable Fourier series achieves state-of-the-art image restoration by encoding frequency coefficients in its narrow bottleneck, preserving fine details even with ext…

This paper presents novel algorithms for linear bandits that are robust to corrupted rewards, achieving minimax optimality and optimal scaling for gap-dependent misspecification, extending to reinforc…

CorDA: Context-oriented weight decomposition enhances large language model fine-tuning by integrating task context, improving efficiency and mitigating catastrophic forgetting.