Related papers: Semantic Flow Regularization: Teaching LLMs to Gen…

Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as the fundamental unit. However, existing methods still lack…

Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models still has two main problems: (i) GRPO-style fixed per-prompt…

As synthetic data proliferates across the Internet, it is often reused to train successive generations of generative models. This creates a ``self-consuming loop" that can lead to training instability or \textit{model collapse}. Common…

Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching…

Large language models exhibit systematic negation sensitivity, yet no operational framework exists to measure this vulnerability at deployment scale, especially in high-stakes decisions. We introduce Syntactic Framing Fragility (SFF), a…

LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mode in current propose-then-select pipelines. Although…

Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large language models (LLMs) have driven their adoption in SR.…

Synthetic survey data generated by large language models (LLMs) suffers from a fundamental circularity: the same model family that generates text responses also maps them to numerical scales. We calibrate and validate Semantic Similarity…

Regularization is an effective way to promote the generalization performance of machine learning models. In this paper, we focus on label smoothing, a form of output distribution regularization that prevents overfitting of a neural network…

Large language models (LLMs) are known to be sensitive to input phrasing, but the mechanisms by which semantic cues shape reasoning remain poorly understood. We investigate this phenomenon in the context of comparative math problems with…

Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic…

Reinforcement learning (RL) is often credited with improving language model reasoning and generalization at the expense of degrading memorized knowledge. We challenge this narrative by observing that RL-enhanced models consistently…

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…

Text style transfer aims to paraphrase a sentence in one style into another style while preserving content. Due to lack of parallel training data, state-of-art methods are unsupervised and rely on large datasets that share content.…

Normalizing Flows provide a principled framework for high-dimensional density estimation and generative modeling by constructing invertible transformations with tractable Jacobian determinants. We propose Fractal Flow, a novel normalizing…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

Recall the classical text generation works, the generation framework can be briefly divided into two phases: \textbf{idea reasoning} and \textbf{surface realization}. The target of idea reasoning is to figure out the main idea which will be…

Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approaches supervise only the final answer while ignoring the…

Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models…