相关论文: DataInf: Efficiently Estimating Data Influence in …

Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs). While coding data is known to boost LLM reasoning abilities during pretraining, its role in activating internal…

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…

Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences,…

As machine learning is increasingly deployed in the real world, it is paramount that we develop the tools necessary to analyze the decision-making of the models we train and deploy to end-users. Recently, researchers have shown that…

Customer feedback can be an important signal for improving commercial machine translation systems. One solution for fixing specific translation errors is to remove the related erroneous training instances followed by re-training of the…

In recent years, Large Language Models (LLMs) through Transformer structures have dominated many machine learning tasks, especially text processing. However, these models require massive amounts of data for training and induce high resource…

The entry of large language models (LLMs) into research and commercial spaces has led to a trend of ever-larger models, with initial promises of generalisability, followed by a widespread desire to downsize and create specialised models…

Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods such as TracIn and Influence Functions leverage influence to identify…

As diffusion models become increasingly popular, the misuse of copyrighted and private images has emerged as a major concern. One promising solution to mitigate this issue is identifying the contribution of specific training samples in…

Precise attribute intensity control--generating Large Language Model (LLM) outputs with specific, user-defined attribute intensities--is crucial for AI systems adaptable to diverse user expectations. Current LLM alignment methods, however,…

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Large Language Models (LLMs) herald a transformative era in artificial intelligence (AI). However, the expansive scale of data and parameters of LLMs requires high-demand computational and memory resources, restricting their accessibility…

Understanding the process of learning in neural networks is crucial for improving their performance and interpreting their behavior. This can be approximately understood by asking how a model's output is influenced when we fine-tune on a…

Influence functions (IF) have been seen as a technique for explaining model predictions through the lens of the training data. Their utility is assumed to be in identifying training examples "responsible" for a prediction so that, for…

Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse downstream bioinformatics tasks. However, such models often rely…

Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While…

Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding…

Reinforcement learning from human feedback (RLHF), which aligns a diffusion model with input prompt, has become a crucial step in building reliable generative AI models. Most works in this area use a discrete-time formulation, which is…

Despite the artificial intelligence (AI) revolution, deep learning has yet to achieve much success with tabular data due to heterogeneous feature space and limited sample sizes without viable transfer learning. The new era of generative AI,…

Diffusion models, such as Stable Diffusion (SD), offer the ability to generate high-resolution images with diverse features, but they come at a significant computational and memory cost. In classifier-free guided diffusion models, prolonged…