Posters

STAR, a novel unsupervised adaptation framework, drastically improves automatic speech recognition (ASR) robustness across diverse domains using only unlabeled data and outperforms existing self-train…

Self-Supervised Transformation Learning (STL) enhances equivariant representations by replacing transformation labels with image-pair-derived representations, improving performance on diverse classifi…

SAMI: Self-Supervised Alignment with Mutual Information, effectively teaches language models to follow principles without human preference labels by maximizing the mutual information between principle…

DAQ-SDP enhances self-supervised adversarial training by using diverse augmented queries, a self-supervised double perturbation scheme, and a novel Aug-Adv Pairwise-BatchNorm method, bridging the gap …

Self-Retrieval revolutionizes information retrieval by unifying indexing, retrieval, and reranking within a single large language model, achieving significantly improved performance.

Self-Refining Diffusion Samplers (SRDS) dramatically speeds up diffusion model sampling by leveraging Parareal iterations for parallel-in-time computation, maintaining high-quality outputs.

Self-play adversarial language game boosts LLM reasoning!

Self-Play Fine-Tuning (SPIN-Diffusion) revolutionizes diffusion model training, achieving superior text-to-image results with less data via iterative self-improvement, surpassing supervised and RLHF m…

Self-Labeling Improves Generative Model Training for Combinatorial Problems

Self-healing machine learning (SHML) autonomously diagnoses and fixes model performance degradation caused by data shifts, outperforming reason-agnostic methods.

LLMs excel at reasoning tasks, but their application to combinatorial problems (CPs) is underexplored. This paper introduces Self-Guiding Exploration (SGE), a novel prompting strategy that significan…

Self-guided MAE boosts self-supervised learning by intelligently masking image patches based on internal clustering patterns, dramatically accelerating training without external data.

Self-Distilled Depth Refinement (SDDR) tackles noisy depth maps via a novel noisy Poisson fusion approach, achieving significant improvements in depth accuracy and edge quality.

LLMs self-discover optimal reasoning structures for complex problems, boosting performance by up to 32% compared to existing methods.

Self-Calibrating Conformal Prediction (SC-CP) marries model calibration and conformal prediction for more efficient and interpretable prediction intervals with prediction-conditional validity.

Self-Calibrated Tuning (SCT) enhances vision-language model OOD detection by adaptively weighting OOD regularization based on prediction uncertainty, mitigating issues caused by inaccurate feature ext…

Enhance Transformer models via Selective Self-Attention (SSA), a principled context control method that boosts accuracy and efficiency.

SelectIT leverages LLMs’ intrinsic uncertainty to efficiently select high-quality instruction tuning data, enhancing model performance without extra resources.

SEL-BALD tackles the challenge of human discretion in active learning by proposing novel algorithms that account for instance rejection, significantly boosting sample efficiency.

This paper presents novel statistical methods to reliably watermark and segment LLMs-generated text, ensuring source traceability even after user modifications.