Tag
SALA is a Semantic-Aware Logical Alignment framework that improves demonstration selection for complex reasoning in in-context learning by automatically learning task-specific reasoning operations and using dynamic time warping for flexible alignment, outperforming existing methods.
This paper introduces SA-Pass, a method for evaluating semantic alignment in autoformalization, and presents ShadowBench, a Lean 4 benchmark with 178 problems, demonstrating high agreement with expert judgments.
MedMix is a semantic-alignment framework for federated multimodal sparse Mixture-of-Experts that addresses modality heterogeneity by coordinating routing and expert specialization, achieving improved performance in medical AI datasets.
The paper proposes BLPM, an EEG-language foundation model that uses continuous latent predictive modeling and semantic alignment to map EEG signals to text embeddings, achieving generalizable neural decoding across diverse tasks and datasets.
The paper proposes SentiLLM, a framework that uses semantic-aligned structural abstraction to distill non-verbal modalities into text-like tokens for multimodal sentiment analysis with LLMs. It introduces a dual-stream salience-context calibration mechanism and achieves superior performance on four datasets.
SMETA-ZSL proposes a method for generalized zero-shot threat classification using semantic meta-alignment and contrastive finetuning, outperforming prior methods by 10.8 points on average across 7 benchmarks.
MOSAIC is a novel framework that uses a frozen LLM to generate semantic embeddings and hierarchical prediction prompts for knowledge tracing, achieving state-of-the-art results on multiple benchmarks.
FAST-GOAL is a fine-tuning method that enhances CLIP's ability to align global and local semantics in images and lengthy text, introducing FLISM and TSL modules and the GLIT100k dataset. It achieves improvements on long caption datasets.
This paper proposes a data-driven framework using embeddings from multilingual LLMs to detect lexical gaps between languages, achieving high accuracy in Korean-English pairs.
SemBridge is a novel embedding initialization method that leverages multilingual bridge models to establish semantic alignments between source and target vocabularies, improving cross-lingual sparse encoder adaptation and retrieval performance across multiple languages.
Qwen-Image-VAE-2.0 is a high-compression Variational Autoencoder suite that improves reconstruction fidelity and diffusability through enhanced architecture, large-scale training, and semantic alignment strategies.