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

Model-based reinforcement learning (MBRL) typically relies on modeling environment dynamics for data efficiency. However, due to the accumulation of model errors over long-horizon rollouts, such methods often face challenges in maintaining…

Mental health disorders impose a substantial global socioeconomic burden. While large language models (LLMs) offer 24/7, non-judgmental interactions to address this gap, pretrained models lack contextual coherence and emotional alignment…

Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Neural Function Evaluations (NFEs), posing a challenge for…

Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent capabilities of Large Language Models (LLMs) without external supervision. However, current methods rely on…

Sequential Recommender Systems (SRS), which model a user's interaction history to predict the next item of interest, are widely used in various applications. However, existing SRS often struggle with low-popularity items, a challenge known…

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain…

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data where the source…

Low-resource target-language generation is often limited by scarce parallel data, while high-resource source-language monolingual data is abundant but difficult to use with standard supervised fine-tuning. We propose Source-Grounded…

Latent reasoning offers a computation-efficient alternative to Chain-of-Thought but often suffers from performance degradation due to distributional misalignment and ambiguous chain definitions. Ideally, latent reasoning should function as…

Large reasoning models (LRMs) generate complex reasoning traces with planning, reflection, verification, and backtracking. In this work, we introduce ReasoningFlow, a unified schema for analyzing the semantic structures of these complex…

Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy. Most available filter pruning methods require complex treatments such as iterative pruning, features…

Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter…

Multivariate Time Series Forecasting plays a key role in many applications. Recent works have explored using Large Language Models for MTSF to take advantage of their reasoning abilities. However, many methods treat LLMs as end-to-end…

Semantic communication (SemCom) is an emerging paradigm that leverages semantic-level understanding to improve communication efficiency, particularly in resource-constrained scenarios. However, existing SemCom systems often overlook diverse…

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive…

Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets, where unsafe prompts are paired with standard refusal templates, often leads to false…

Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple…