相关论文: AdaptFuse: Training-Free Sequential Preference Lea…

Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an…

Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To overcome this…

Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this…

High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain private, which hinders the democratization of AI. High human…

Recent Vision-Language Pretrained (VLP) models have become the backbone for many downstream tasks, but they are utilized as frozen model without learning. Prompt learning is a method to improve the pre-trained VLP model by adding a…

Large Language Models (LLMs) show promise for equation discovery, yet their outputs are highly sensitive to prompt phrasing, a phenomenon we term instruction brittleness. Static prompts cannot adapt to the evolving state of a multi-step…

Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest,…

Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed…

With recent advancements in large language models (LLMs), alignment has emerged as an effective technique for keeping LLMs consensus with human intent. Current methods primarily involve direct training through Supervised Fine-tuning (SFT)…

Despite the success of recommender systems in alleviating information overload, fairness issues have raised concerns in recent years, potentially leading to unequal treatment for certain user groups. While efforts have been made to improve…

We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a)…

Modern Bayesian inference involves a mixture of computational techniques for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows for data analysis. Typical problems in Bayesian workflows…

Large language models (LLMs) exhibit complementary strengths in various tasks, motivating the research of LLM ensembling. However, existing work focuses on training an extra reward model or fusion model to select or combine all candidate…

Recent advancements in Large Language Models (LLMs) demonstrate remarkable capabilities across various fields. These developments have led to more direct communication between humans and LLMs in various situations, such as social…

Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word prediction and sequence probability estimation). We present an…

This paper introduces a novel approach to creating adaptive language agents by integrating active inference with large language models (LLMs). While LLMs demonstrate remarkable capabilities, their reliance on static prompts limits…

Large language models are increasingly used as proxies for human subjects in social science research, yet external validity requires that synthetic agents faithfully reflect the preferences of target human populations. We introduce…

The sequential nature of modern LLMs makes them expensive and slow, and speculative sampling has proven to be an effective solution to this problem. Methods like EAGLE perform autoregression at the feature level, reusing top-layer features…

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

User representation modeling has become increasingly crucial for personalized applications, yet existing approaches struggle with generalizability across domains and sensitivity to noisy behavioral signals. We present InstructUE, an…