Related papers: SeMe: Training-Free Language Model Merging via Sem…

Large reasoning models (LRMs) excel at a long chain of reasoning but often fail to faithfully follow instructions regarding output format, constraints, or specific requirements. We investigate whether this gap can be closed by integrating…

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a…

Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate…

Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of smaller models (e.g., BERT) on downstream tasks. However, it…

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Large Language Models (LLMs) have driven substantial progress in artificial intelligence in recent years, exhibiting impressive capabilities across a wide range of tasks, including mathematical problem-solving. Inspired by the success of…

Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…

Achieving high-performing language models which include medium- and lower-resource languages remains a challenge. Massively multilingual models still underperform compared to language-specific adaptations, especially at smaller model…

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

Widely used language-model benchmarks are increasingly saturated, with frontier systems often receiving near-tied scores that standard metrics cannot resolve. Rather than constructing harder alternatives, we ask whether existing tasks can…

Recent advances in large language models (LLMs) have accelerated progress toward artificial general intelligence, with inference-time scaling emerging as a key technique. Contemporary approaches leverage either sequential reasoning…

Word alignments are useful for tasks like statistical and neural machine translation (NMT) and cross-lingual annotation projection. Statistical word aligners perform well, as do methods that extract alignments jointly with translations in…

Ensembling different large language models (LLMs) to unleash their complementary potential and harness their individual strengths is highly valuable. Nevertheless, vocabulary discrepancies among various LLMs have constrained previous…

Federated Learning (FL) is a recent model training paradigm in which client devices collaboratively train a model without ever aggregating their data. Crucially, this scheme offers users potential privacy and security benefits by only ever…

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…

Hierarchical Imitation Learning (HIL) is a promising approach for tackling long-horizon decision-making tasks. While it is a challenging task due to the lack of detailed supervisory labels for sub-goal learning, and reliance on hundreds to…

We propose semantic fusion, a lightweight scheme that augments a Transformer language model (LM) with a parallel, fuzzy-membership feature channel that encodes token-level semantics. Each token is represented by a vector of interpretable…

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time reasoning to multi-model collaboration. We study language model networks, where pre-trained language…