Related papers: GRACE: Gradient-aligned Reasoning Data Curation fo…
Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but…
As deep learning models and datasets rapidly scale up, network training is extremely time-consuming and resource-costly. Instead of training on the entire dataset, learning with a small synthetic dataset becomes an efficient solution.…
Gradient regularization (GR) is a method that penalizes the gradient norm of the training loss during training. While some studies have reported that GR can improve generalization performance, little attention has been paid to it from the…
While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or partially correct solutions.…
Text-to-image flow matching transformers degrade sharply in long-tail settings: tail-class outputs collapse in fidelity and diversity, limiting their value as synthetic augmentation for rare conditions. We trace this to low head-versus-tail…
Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the…
Vision-Language Models (VLMs) struggle to translate high-level instructions into the precise spatial affordances required for robotic manipulation. While visual Chain-of-Thought (CoT) methods exist, they are often computationally intensive.…
Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling…
Traditional single-task image restoration methods excel in handling specific degradation types but struggle with multiple degradations. To address this limitation, we propose Grouped Restoration with Image Degradation Similarity (GRIDS), a…
Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…
Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a…
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length…
Gradient boosting is a state-of-the-art prediction technique that sequentially produces a model in the form of linear combinations of simple predictors---typically decision trees---by solving an infinite-dimensional convex optimization…
Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…
Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborative Reasoning (CORE), a training-time collaboration…
Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge.…
Multimodal reasoning in vision-language models (VLMs) typically relies on a two-stage process: supervised fine-tuning (SFT) and reinforcement learning (RL). In standard SFT, all tokens contribute equally to the loss, even though reasoning…
In real-world applications of reinforcement learning (RL), noise from inherent stochasticity of environments is inevitable. However, current policy evaluation algorithms, which plays a key role in many RL algorithms, are either prone to…
Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer…
Multi-step reasoning ability is fundamental to many natural language tasks, yet it is unclear what constitutes a good reasoning chain and how to evaluate them. Most existing methods focus solely on whether the reasoning chain leads to the…